{ "schemaVersion": "1.0", "name": "BenchLM curated comparisons", "description": "Curated and high-value model comparisons. BenchLM supports more pairwise comparison pages than this export includes.", "canonicalUrl": "https://benchlm.ai/data/comparisons.json", "generatedAt": "2026-09-02T00:50:21.010Z", "sourceLastUpdated": "September 1, 2026", "sourceFiles": [ "src/data/featuredComparisons.js", "src/lib/prebuiltComparisons.js" ], "counts": { "exportedComparisons": 400, "totalPairwiseComparisons": 82215 }, "items": [ { "slug": "claude-opus-5-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gpt-5-6-sol.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 81.69, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 0.6500000000000057, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 92, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 64.6, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 83, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 92.5, "winner": "B", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 94.6, "winner": null, "benchmarkCount": 18 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-sonnet-5-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 16.97, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 81.9, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 76.7, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 88.3, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 57.4, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-sol-vs-kimi-k3", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 81.69, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 1.769999999999996, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 92, "winner": "B", "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 83, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 94.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-8-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 75.96, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 5.730000000000004, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 26, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 80.3, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 81.1, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 77, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 72.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 62.7, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 53.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "gemini-3-5-flash-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gemini-3-5-flash-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-5-flash-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 64.2, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 8.299999999999997, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 24, "benchmarkCountB": 22, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 77.2, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 55.1, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 83.8, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 74.7, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 40.2, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 32.9, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gemini-3-5-flash-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/gemini-3-5-flash-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-5-flash-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "modelB": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.93, "scoreB": 64.2, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 2.730000000000004, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 24, "benchmarkCountB": 22, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.1, "avgB": 77.2, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 62.7, "avgB": 55.1, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.4, "avgB": 83.8, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59.5, "avgB": 74.7, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.3, "avgB": 40.2, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 73.6, "avgB": 32.9, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gemini-3-6-flash-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/gemini-3-6-flash-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-6-flash-vs-gemini-3-7-flash.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "gemini-3-6-flash", "canonicalModelKey": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.06, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.01, "upper": 80.1 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 75.06, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gemini-3-6-flash", "canonicalModelKey": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.06, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.01, "upper": 80.1 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, "scoreDiff": 14.060000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gemini-3-5-flash-vs-gemini-3-6-flash", "url": "https://benchlm.ai/compare/gemini-3-5-flash-vs-gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-5-flash-vs-gemini-3-6-flash.md", "modelA": { "slug": "gemini-3-6-flash", "canonicalModelKey": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.06, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.01, "upper": 80.1 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, "modelB": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.06, "scoreB": 64.2, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gemini-3-6-flash", "canonicalModelKey": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.06, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.01, "upper": 80.1 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, "scoreDiff": 10.86, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 22, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 83, "avgB": 77.2, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 55.1, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83.8, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 74.7, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 40.2, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 32.9, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gemini-3-1-flash-lite-vs-gemini-3-5-flash-lite", "url": "https://benchlm.ai/compare/gemini-3-1-flash-lite-vs-gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-flash-lite-vs-gemini-3-5-flash-lite.md", "modelA": { "slug": "gemini-3-5-flash-lite", "canonicalModelKey": "gemini-3-5-flash-lite", "model": "Gemini 3.5 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.04, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 52.89, "upper": 77.19 }, "rankingEligible": true, "overallRank": 37, "url": "https://benchlm.ai/models/gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-lite.md" }, "modelB": { "slug": "gemini-3-1-flash-lite", "canonicalModelKey": "gemini-3-1-flash-lite", "model": "Gemini 3.1 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.82, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.61, "upper": 77.03 }, "rankingEligible": true, "overallRank": 129, "url": "https://benchlm.ai/models/gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-lite.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.04, "scoreB": 50.82, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gemini-3-5-flash-lite", "canonicalModelKey": "gemini-3-5-flash-lite", "model": "Gemini 3.5 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.04, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 52.89, "upper": 77.19 }, "rankingEligible": true, "overallRank": 37, "url": "https://benchlm.ai/models/gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-lite.md" }, "scoreDiff": 14.220000000000006, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 5, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 63.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": 54.2, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 73.2, "winner": null, "benchmarkCount": 1 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.2, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-4-8-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 75.96, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 11.239999999999995, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 16, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 80.3, "winner": "A", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 81.1, "winner": "B", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 77, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 72.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 62.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 53.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-8-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gpt-5-5.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 3.279999999999987, "winsA": 1, "winsB": 2, "comparableCategoryCount": 3, "benchmarkCountA": 33, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 81.6, "winner": "B", "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 58.6, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 70.4, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 85, "winner": "B", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 57.8, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 47.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-claude-opus-4-8", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-claude-opus-4-8.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 3.75, "winsA": 4, "winsB": 1, "comparableCategoryCount": 5, "benchmarkCountA": 33, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 75.1, "winner": "A", "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 78.6, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 65.1, "winner": "A", "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 75.8, "winner": "B", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 60, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": null, "winner": null, "benchmarkCount": 4 } } }, { "slug": "gemini-3-5-flash-vs-gpt-5-5", "url": "https://benchlm.ai/compare/gemini-3-5-flash-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-5-flash-vs-gpt-5-5.md", "modelA": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.2, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 8.480000000000004, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 22, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 77.2, "avgB": 81.6, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 55.1, "avgB": 58.6, "winner": "B", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83.8, "avgB": 70.4, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 74.7, "avgB": 85, "winner": null, "benchmarkCount": 6 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 40.2, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 32.9, "avgB": 47.6, "winner": "B", "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-7-vs-gemini-3-5-flash", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-gemini-3-5-flash.md", "modelA": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "modelB": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.2, "scoreB": 72.23, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 8.030000000000001, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 22, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 77.2, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 55.1, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83.8, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 40.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 32.9, "avgB": 38.6, "winner": "B", "benchmarkCount": 2 } } }, { "slug": "gemini-3-1-pro-vs-gemini-3-5-flash", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gemini-3-5-flash.md", "modelA": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.2, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "scoreDiff": 7.990000000000002, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 22, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 77.2, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 55.1, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83.8, "avgB": 82.6, "winner": "A", "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 74.7, "avgB": 77.1, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 40.2, "avgB": null, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 32.9, "avgB": 31.8, "winner": "A", "benchmarkCount": 2 } } }, { "slug": "claude-opus-4-7-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 72.23, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 0.45000000000000284, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 38.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 0.4700000000000131, "winsA": 2, "winsB": 1, "comparableCategoryCount": 3, "benchmarkCountA": 33, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 75.1, "winner": "A", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 78.6, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 65.1, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": 75.8, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": 60, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-fable-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 82.49, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 9.809999999999988, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 84.6, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 89.2, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 57.9, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13.319999999999993, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 33, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 87, "winner": "B", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 93.5, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "gemini-3-1-pro-vs-gpt-5-5", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 16.470000000000006, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 33, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": null, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": null, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 82.6, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": 77.1, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 31.8, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gemini-3-1-flash-lite-vs-gpt-5-5", "url": "https://benchlm.ai/compare/gemini-3-1-flash-lite-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-flash-lite-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "gemini-3-1-flash-lite", "canonicalModelKey": "gemini-3-1-flash-lite", "model": "Gemini 3.1 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.82, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.61, "upper": 77.03 }, "rankingEligible": true, "overallRank": 129, "url": "https://benchlm.ai/models/gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-lite.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 50.82, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 21.860000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 73.2, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-gpt-5-5", "url": "https://benchlm.ai/compare/glm-5-2-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 9.800000000000004, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 33, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 81, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 62.1, "winner": "B", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": 59.6, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 95.9, "winner": null, "benchmarkCount": 7 } } }, { "slug": "glm-5-1-vs-gpt-5-5", "url": "https://benchlm.ai/compare/glm-5-1-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-1-vs-gpt-5-5.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 66.68, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 6, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 65.4, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 61.3, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": 52.3, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 62, "winner": null, "benchmarkCount": 7 } } }, { "slug": "gpt-5-5-vs-kimi-k2-7-code", "url": "https://benchlm.ai/compare/gpt-5-5-vs-kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-kimi-k2-7-code.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 54.01, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 18.67000000000001, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": null, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": null, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-7-vs-gpt-5-5-pro", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-gpt-5-5-pro.md", "modelA": { "slug": "gpt-5-5-pro", "canonicalModelKey": "gpt-5-5-pro", "model": "GPT-5.5 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.35, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.8, "upper": 78.91 }, "rankingEligible": true, "overallRank": 42, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md" }, "modelB": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.35, "scoreB": 72.23, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 7.88000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 6, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.1, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 48.1, "avgB": 38.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-7-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.23, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 16.020000000000003, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 8, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 82.6, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 38.6, "avgB": 31.8, "winner": "A", "benchmarkCount": 2 } } }, { "slug": "glm-5-reasoning-vs-gpt-5-5", "url": "https://benchlm.ai/compare/glm-5-reasoning-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-reasoning-vs-gpt-5-5.md", "modelA": { "slug": "glm-5-reasoning", "canonicalModelKey": "glm-5-reasoning", "model": "GLM-5 (Reasoning)", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 60.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.04, "upper": 72.07 }, "rankingEligible": true, "overallRank": 67, "url": "https://benchlm.ai/models/glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/glm-5-reasoning.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.55, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 12.13000000000001, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81.6, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 58.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-kimi-k2-7-code", "url": "https://benchlm.ai/compare/glm-5-2-vs-kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-kimi-k2-7-code.md", "modelA": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "modelB": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "rankingMode": "bench-align-v5", "scoreA": 62.88, "scoreB": 54.01, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "scoreDiff": 8.870000000000005, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 20, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 62.1, "avgB": null, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 59.6, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 95.9, "avgB": null, "winner": null, "benchmarkCount": 4 } } }, { "slug": "glm-5-1-vs-kimi-k2-7-code", "url": "https://benchlm.ai/compare/glm-5-1-vs-kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-1-vs-kimi-k2-7-code.md", "modelA": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "modelB": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.68, "scoreB": 54.01, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "scoreDiff": 12.670000000000009, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 21, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 65.4, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 61.3, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 52.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 62, "avgB": null, "winner": null, "benchmarkCount": 6 } } }, { "slug": "kimi-k2-7-code-vs-ling-2-6-flash", "url": "https://benchlm.ai/compare/kimi-k2-7-code-vs-ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k2-7-code-vs-ling-2-6-flash.md", "modelA": { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 44.18, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.66, "upper": 55.69 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, "modelB": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "rankingMode": "bench-align-v5", "scoreA": 44.18, "scoreB": 54.01, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "scoreDiff": 9.829999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-5-vs-ling-2-6-flash", "url": "https://benchlm.ai/compare/gpt-5-5-vs-ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-ling-2-6-flash.md", "modelA": { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 44.18, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.66, "upper": 55.69 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 44.18, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 28.500000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81.6, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 58.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-1-vs-ling-2-6-flash", "url": "https://benchlm.ai/compare/glm-5-1-vs-ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-1-vs-ling-2-6-flash.md", "modelA": { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 44.18, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.66, "upper": 55.69 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, "modelB": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 44.18, "scoreB": 66.68, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "scoreDiff": 22.500000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 65.4, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 61.3, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 52.3, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 62, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-7-vs-ling-2-6-flash", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-ling-2-6-flash.md", "modelA": { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 44.18, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.66, "upper": 55.69 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, "modelB": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 44.18, "scoreB": 72.23, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 28.050000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 38.6, "winner": null, "benchmarkCount": 2 } } }, { "slug": "qwen3-6-27b-vs-qwen3-6-35b-a3b", "url": "https://benchlm.ai/compare/qwen3-6-27b-vs-qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-6-27b-vs-qwen3-6-35b-a3b.md", "modelA": { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.57, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.05, "upper": 65.08 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, "modelB": { "slug": "qwen3-6-35b-a3b", "canonicalModelKey": "qwen3-6-35b-a3b", "model": "Qwen3.6-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 51.32, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.81, "upper": 62.84 }, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 53.57, "scoreB": 51.32, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.57, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.05, "upper": 65.08 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, "scoreDiff": 2.25, "winsA": 5, "winsB": 0, "comparableCategoryCount": 5, "benchmarkCountA": 38, "benchmarkCountB": 41, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 59.3, "avgB": 51.5, "winner": "A", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 77.5, "avgB": 73.8, "winner": "A", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.7, "avgB": 76.3, "winner": "A", "benchmarkCount": 19 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.3, "avgB": 51.4, "winner": "A", "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 89.2, "avgB": 88.2, "winner": "A", "benchmarkCount": 5 } } }, { "slug": "qwen3-5-27b-vs-qwen3-6-27b", "url": "https://benchlm.ai/compare/qwen3-5-27b-vs-qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-5-27b-vs-qwen3-6-27b.md", "modelA": { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.57, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.05, "upper": 65.08 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, "modelB": { "slug": "qwen3-5-27b", "canonicalModelKey": "qwen3-5-27b", "model": "Qwen3.5-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 59.7, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.77, "upper": 69.63 }, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md" }, "rankingMode": "bench-align-v5", "scoreA": 53.57, "scoreB": 59.7, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "qwen3-5-27b", "canonicalModelKey": "qwen3-5-27b", "model": "Qwen3.5-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 59.7, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.77, "upper": 69.63 }, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md" }, "scoreDiff": 6.130000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 38, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 59.3, "avgB": 52, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 77.5, "avgB": 64.9, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.7, "avgB": null, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 60.6, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.3, "avgB": 82.7, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 95, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 82.2, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 89.2, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "gemma-4-31b-vs-qwen3-6-27b", "url": "https://benchlm.ai/compare/gemma-4-31b-vs-qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/compare/gemma-4-31b-vs-qwen3-6-27b.md", "modelA": { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.57, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.05, "upper": 65.08 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, "modelB": { "slug": "gemma-4-31b", "canonicalModelKey": "gemma-4-31b", "model": "Gemma 4 31B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 60.08, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 43.34, "upper": 76.82 }, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md" }, "rankingMode": "bench-align-v5", "scoreA": 53.57, "scoreB": 60.08, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gemma-4-31b", "canonicalModelKey": "gemma-4-31b", "model": "Gemma 4 31B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 60.08, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 43.34, "upper": 76.82 }, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md" }, "scoreDiff": 6.509999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 38, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 59.3, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 77.5, "avgB": 41.6, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.7, "avgB": 76.9, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.3, "avgB": 52.9, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 89.2, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-gpt-5-5-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-5-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-5-pro", "canonicalModelKey": "gpt-5-5-pro", "model": "GPT-5.5 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.35, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.8, "upper": 78.91 }, "rankingEligible": true, "overallRank": 42, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 64.35, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 21.650000000000006, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 90.1, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 57.2, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 48.1, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-7", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-7.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 72.23, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13.769999999999996, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 38.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-claude-opus-4-8", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-opus-4-8.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 75.96, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 6.530000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 80.3, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 81.1, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 77, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 72.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 62.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 53.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-3-5-sonnet-vs-grok-4", "url": "https://benchlm.ai/compare/claude-3-5-sonnet-vs-grok-4", "markdownUrl": "https://benchlm.ai/md/compare/claude-3-5-sonnet-vs-grok-4.md", "modelA": { "slug": "claude-3-5-sonnet", "canonicalModelKey": "claude-3-5-sonnet", "model": "Claude 3.5 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 48.36, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.85, "upper": 59.87 }, "rankingEligible": true, "overallRank": 144, "url": "https://benchlm.ai/models/claude-3-5-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-3-5-sonnet.md" }, "modelB": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 48.36, "scoreB": 59.42, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "scoreDiff": 11.060000000000002, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 4, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": 49, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 59.4, "avgB": null, "winner": null, "benchmarkCount": 1 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 1.6, "avgB": 15.3, "winner": "B", "benchmarkCount": 2 } } }, { "slug": "gpt-4o-vs-grok-4-1", "url": "https://benchlm.ai/compare/gpt-4o-vs-grok-4-1", "markdownUrl": "https://benchlm.ai/md/compare/gpt-4o-vs-grok-4-1.md", "modelA": { "slug": "gpt-4o", "canonicalModelKey": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.96, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.58, "upper": 60.34 }, "rankingEligible": true, "overallRank": 191, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, "modelB": { "slug": "grok-4-1", "canonicalModelKey": "grok-4-1", "model": "Grok 4.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 60.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 72.24 }, "rankingEligible": true, "overallRank": 65, "url": "https://benchlm.ai/models/grok-4-1", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 40.96, "scoreB": 60.73, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "grok-4-1", "canonicalModelKey": "grok-4-1", "model": "Grok 4.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 60.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 72.24 }, "rankingEligible": true, "overallRank": 65, "url": "https://benchlm.ai/models/grok-4-1", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1.md" }, "scoreDiff": 19.769999999999996, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 0.3, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gemini-2-5-pro-vs-o3", "url": "https://benchlm.ai/compare/gemini-2-5-pro-vs-o3", "markdownUrl": "https://benchlm.ai/md/compare/gemini-2-5-pro-vs-o3.md", "modelA": { "slug": "gemini-2-5-pro", "canonicalModelKey": "gemini-2-5-pro", "model": "Gemini 2.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.77, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.38, "upper": 75.17 }, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md" }, "modelB": { "slug": "o3", "canonicalModelKey": "o3", "model": "o3", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 46.82, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 43.88, "upper": 49.76 }, "rankingEligible": true, "overallRank": 157, "url": "https://benchlm.ai/models/o3", "markdownUrl": "https://benchlm.ai/md/models/o3.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.77, "scoreB": 46.82, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gemini-2-5-pro", "canonicalModelKey": "gemini-2-5-pro", "model": "Gemini 2.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.77, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.38, "upper": 75.17 }, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md" }, "scoreDiff": 9.950000000000003, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 7, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": 63.8, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 27.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 11.6, "avgB": 14.5, "winner": "B", "benchmarkCount": 2 } } }, { "slug": "kimi-2-6-vs-kimi-k2-7-code", "url": "https://benchlm.ai/compare/kimi-2-6-vs-kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/compare/kimi-2-6-vs-kimi-k2-7-code.md", "modelA": { "slug": "kimi-k2-7-code", "canonicalModelKey": "kimi-k2-7-code", "model": "Kimi K2.7 Code", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.01, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.99, "upper": 65.03 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md" }, "modelB": { "slug": "kimi-2-6", "canonicalModelKey": "kimi-2-6", "model": "Kimi K2.6", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 59.09, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 68.96 }, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md" }, "rankingMode": "bench-align-v5", "scoreA": 54.01, "scoreB": 59.09, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "kimi-2-6", "canonicalModelKey": "kimi-2-6", "model": "Kimi K2.6", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 59.09, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 68.96 }, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md" }, "scoreDiff": 5.080000000000005, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 8, "benchmarkCountB": 32, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 73.5, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.4, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 79.8, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 42.2, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 67.1, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-4-7-vs-grok-4-20-beta", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-grok-4-20-beta.md", "modelA": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "modelB": { "slug": "grok-4-20-beta", "canonicalModelKey": "grok-4-20-beta", "model": "Grok 4.20", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 55.42, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.52, "upper": 72.32 }, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.23, "scoreB": 55.42, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 16.810000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 8, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 47.1, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 67.1, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.1, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 53.3, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 38.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gpt-4o-vs-grok-4", "url": "https://benchlm.ai/compare/gpt-4o-vs-grok-4", "markdownUrl": "https://benchlm.ai/md/compare/gpt-4o-vs-grok-4.md", "modelA": { "slug": "gpt-4o", "canonicalModelKey": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.96, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.58, "upper": 60.34 }, "rankingEligible": true, "overallRank": 191, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, "modelB": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 40.96, "scoreB": 59.42, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "scoreDiff": 18.46, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 0.3, "avgB": 15.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-4-1-opus-thinking-vs-grok-4", "url": "https://benchlm.ai/compare/claude-4-1-opus-thinking-vs-grok-4", "markdownUrl": "https://benchlm.ai/md/compare/claude-4-1-opus-thinking-vs-grok-4.md", "modelA": { "slug": "claude-4-1-opus-thinking", "canonicalModelKey": "claude-4-1-opus-thinking", "model": "Claude 4.1 Opus Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 35.27, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.26, "upper": 54.27 }, "rankingEligible": true, "overallRank": 206, "url": "https://benchlm.ai/models/claude-4-1-opus-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus-thinking.md" }, "modelB": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 35.27, "scoreB": 59.42, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "scoreDiff": 24.15, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 15.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-opus-4-7-vs-grok-4-1-fast", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-grok-4-1-fast", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-grok-4-1-fast.md", "modelA": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "modelB": { "slug": "grok-4-1-fast", "canonicalModelKey": "grok-4-1-fast", "model": "Grok 4.1 Fast", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.66, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 28.09, "upper": 73.22 }, "rankingEligible": true, "overallRank": 131, "url": "https://benchlm.ai/models/grok-4-1-fast", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.23, "scoreB": 50.66, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 21.570000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 8, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 38.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gemini-3-1-pro-vs-grok-3-beta", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-grok-3-beta", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-grok-3-beta.md", "modelA": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "modelB": { "slug": "grok-3-beta", "canonicalModelKey": "grok-3-beta", "model": "Grok 3 [Beta]", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.33, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 8.65, "upper": 72 }, "rankingEligible": true, "overallRank": 197, "url": "https://benchlm.ai/models/grok-3-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-3-beta.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.21, "scoreB": 40.33, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "scoreDiff": 15.880000000000003, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 23, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 82.6, "avgB": null, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 77.1, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 31.8, "avgB": 2.8, "winner": "A", "benchmarkCount": 2 } } }, { "slug": "claude-4-sonnet-vs-grok-4", "url": "https://benchlm.ai/compare/claude-4-sonnet-vs-grok-4", "markdownUrl": "https://benchlm.ai/md/compare/claude-4-sonnet-vs-grok-4.md", "modelA": { "slug": "claude-4-sonnet", "canonicalModelKey": "claude-4-sonnet", "model": "Claude 4 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 42.07, "provisionalDisplayScore": 56, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.83, "upper": 45.31 }, "rankingEligible": true, "overallRank": 187, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md" }, "modelB": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 42.07, "scoreB": 59.42, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "scoreDiff": 17.35, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "coding": { "categoryLabel": "Coding", "avgA": 72.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 15.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-opus-4-7-vs-gpt-4o", "url": "https://benchlm.ai/compare/claude-opus-4-7-vs-gpt-4o", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-vs-gpt-4o.md", "modelA": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "modelB": { "slug": "gpt-4o", "canonicalModelKey": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.96, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.58, "upper": 60.34 }, "rankingEligible": true, "overallRank": 191, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.23, "scoreB": 40.96, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-4-7", "canonicalModelKey": "claude-opus-4-7", "model": "Claude Opus 4.7", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.23, "provisionalDisplayScore": 65, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.3, "upper": 84.15 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md" }, "scoreDiff": 31.270000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 8, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 38.6, "avgB": 0.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-fable-vs-claude-fable-5-1", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-fable-5-1.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 82.49, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 0.25, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 84.6, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 89.2, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 57.9, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-claude-mythos-5-1", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-mythos-5-1.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 0, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 82.74, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-opus-5.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 0.3999999999999915, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 90.4, "winner": "B", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 64.7, "winner": "A", "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-fable-5-1-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-kimi-k3.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 79.92, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 2.819999999999993, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": null, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 61, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gpt-5-6-sol.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 81.69, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 1.0499999999999972, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 64.6, "winner": "A", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 92.5, "winner": "B", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 94.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-claude-mythos-5-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-mythos-5-1.md", "modelA": { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 86, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 86, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-1-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-mythos-5-1-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-1-vs-claude-opus-5.md", "modelA": { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.34, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 82.34, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.7, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-1-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-mythos-5-1-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-1-vs-kimi-k3.md", "modelA": { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 79.92, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 79.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 61, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-mythos-5-1-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-mythos-5-1-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-1-vs-gpt-5-6-sol.md", "modelA": { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 81.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 81.69, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 1, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 94.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-5-vs-muse-voice-transcribe", "url": "https://benchlm.ai/compare/claude-opus-5-vs-muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-muse-voice-transcribe.md", "modelA": { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.34, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 82.34, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.7, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "kimi-k3-vs-muse-voice-transcribe", "url": "https://benchlm.ai/compare/kimi-k3-vs-muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-muse-voice-transcribe.md", "modelA": { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 79.92, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 79.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 61, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-6-sol-vs-muse-voice-transcribe", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-muse-voice-transcribe.md", "modelA": { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 81.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 81.69, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 94.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-muse-voice-transcribe", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-muse-voice-transcribe.md", "modelA": { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md" }, "modelB": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.74, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 82.74, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 81.2, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 65, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-vs-muse-voice-transcribe", "url": "https://benchlm.ai/compare/claude-fable-vs-muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-muse-voice-transcribe.md", "modelA": { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.49, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 82.49, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 84.6, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.2, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 57.9, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "mercury-2-vs-mercury-2-5-preview", "url": "https://benchlm.ai/compare/mercury-2-vs-mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/compare/mercury-2-vs-mercury-2-5-preview.md", "modelA": { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md" }, "modelB": { "slug": "mercury-2", "canonicalModelKey": "mercury-2", "model": "Mercury 2", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 48.13, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 34.94, "upper": 61.33 }, "rankingEligible": true, "overallRank": 147, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 48.13, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "mercury-2", "canonicalModelKey": "mercury-2", "model": "Mercury 2", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 48.13, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 34.94, "upper": 61.33 }, "rankingEligible": true, "overallRank": 147, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md" }, "scoreDiff": 48.13, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-5-vs-mercury-2-5-preview", "url": "https://benchlm.ai/compare/claude-opus-5-vs-mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-mercury-2-5-preview.md", "modelA": { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.34, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 82.34, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.7, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "kimi-k3-vs-mercury-2-5-preview", "url": "https://benchlm.ai/compare/kimi-k3-vs-mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-mercury-2-5-preview.md", "modelA": { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 79.92, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 79.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 61, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-6-sol-vs-mercury-2-5-preview", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-mercury-2-5-preview.md", "modelA": { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 81.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 81.69, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 94.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-mercury-2-5-preview", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-mercury-2-5-preview.md", "modelA": { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md" }, "modelB": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.74, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 82.74, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 81.2, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 65, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "hy3-vs-hy4-preview", "url": "https://benchlm.ai/compare/hy3-vs-hy4-preview", "markdownUrl": "https://benchlm.ai/md/compare/hy3-vs-hy4-preview.md", "modelA": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "modelB": { "slug": "hy3", "canonicalModelKey": "hy3", "model": "Hy3", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 67.65, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 58.81, "upper": 76.49 }, "rankingEligible": true, "overallRank": 24, "url": "https://benchlm.ai/models/hy3", "markdownUrl": "https://benchlm.ai/md/models/hy3.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.3, "scoreB": 67.65, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "scoreDiff": 10.649999999999991, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 28, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 65.7, "avgB": null, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.2, "avgB": null, "winner": null, "benchmarkCount": 1 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.4, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-opus-5-vs-hy4-preview", "url": "https://benchlm.ai/compare/claude-opus-5-vs-hy4-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-hy4-preview.md", "modelA": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.3, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 4.040000000000006, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 28, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 26 }, "coding": { "categoryLabel": "Coding", "avgA": 65.7, "avgB": 89.5, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.2, "avgB": 66.9, "winner": "B", "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.4, "avgB": 64.7, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 6 } } }, { "slug": "hy4-preview-vs-kimi-k3", "url": "https://benchlm.ai/compare/hy4-preview-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/hy4-preview-vs-kimi-k3.md", "modelA": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.3, "scoreB": 79.92, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 1.6200000000000045, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 28, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": 65.7, "avgB": null, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.2, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.4, "avgB": 61, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gpt-5-6-sol-vs-hy4-preview", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-hy4-preview", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-hy4-preview.md", "modelA": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.3, "scoreB": 81.69, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 3.3900000000000006, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 28, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 65.7, "avgB": 64.6, "winner": "A", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.2, "avgB": 83, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.4, "avgB": 94.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-fable-5-1-vs-hy4-preview", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-hy4-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-hy4-preview.md", "modelA": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "modelB": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.3, "scoreB": 82.74, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 4.439999999999998, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 28, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 65.7, "avgB": 81.2, "winner": "B", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.2, "avgB": null, "winner": null, "benchmarkCount": 1 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.4, "avgB": 65, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "ling-3-0-flash-vs-ling-3-0-flash-fin", "url": "https://benchlm.ai/compare/ling-3-0-flash-vs-ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/compare/ling-3-0-flash-vs-ling-3-0-flash-fin.md", "modelA": { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, "modelB": { "slug": "ling-3-0-flash", "canonicalModelKey": "ling-3-0-flash", "model": "Ling 3.0 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.62, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.1, "upper": 65.13 }, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 53.62, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "ling-3-0-flash", "canonicalModelKey": "ling-3-0-flash", "model": "Ling 3.0 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.62, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.1, "upper": 65.13 }, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md" }, "scoreDiff": 53.62, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 17, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 72.2, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 47.1, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 31.1, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 74.5, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 90.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "ling-3-0-flash-fin-vs-ling-3-0-flash-fp8", "url": "https://benchlm.ai/compare/ling-3-0-flash-fin-vs-ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/compare/ling-3-0-flash-fin-vs-ling-3-0-flash-fp8.md", "modelA": { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, "modelB": { "slug": "ling-3-0-flash-fp8", "canonicalModelKey": "ling-3-0-flash-fp8", "model": "Ling 3.0 Flash FP8", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fp8.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 57, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "ling-3-0-flash-fp8", "canonicalModelKey": "ling-3-0-flash-fp8", "model": "Ling 3.0 Flash FP8", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fp8.md" }, "scoreDiff": 57, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 40.4, "winner": null, "benchmarkCount": 1 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 84, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 73.4, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-5-vs-ling-3-0-flash-fin", "url": "https://benchlm.ai/compare/claude-opus-5-vs-ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-ling-3-0-flash-fin.md", "modelA": { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.34, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 82.34, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.7, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "kimi-k3-vs-ling-3-0-flash-fin", "url": "https://benchlm.ai/compare/kimi-k3-vs-ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-ling-3-0-flash-fin.md", "modelA": { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 79.92, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 79.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 61, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-6-sol-vs-ling-3-0-flash-fin", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-ling-3-0-flash-fin.md", "modelA": { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 81.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 81.69, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 94.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-3-vs-glm-5-3-flash", "url": "https://benchlm.ai/compare/glm-5-3-vs-glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-3-vs-glm-5-3-flash.md", "modelA": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "modelB": { "slug": "glm-5-3", "canonicalModelKey": "glm-5-3", "model": "GLM-5.3", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.41, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 50.9, "upper": 73.93 }, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.25, "scoreB": 62.41, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "glm-5-3", "canonicalModelKey": "glm-5-3", "model": "GLM-5.3", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.41, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 50.9, "upper": 73.93 }, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md" }, "scoreDiff": 1.1599999999999966, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "glm-5-2-vs-glm-5-3-flash", "url": "https://benchlm.ai/compare/glm-5-2-vs-glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-glm-5-3-flash.md", "modelA": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.25, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "scoreDiff": 1.6300000000000026, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 62.1, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 59.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "glm-5-1-vs-glm-5-3-flash", "url": "https://benchlm.ai/compare/glm-5-1-vs-glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-1-vs-glm-5-3-flash.md", "modelA": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "modelB": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.25, "scoreB": 66.68, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "scoreDiff": 5.430000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 65.4, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 61.3, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 52.3, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 62, "winner": null, "benchmarkCount": 6 } } }, { "slug": "glm-5-vs-glm-5-3-flash", "url": "https://benchlm.ai/compare/glm-5-vs-glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-vs-glm-5-3-flash.md", "modelA": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "modelB": { "slug": "glm-5", "canonicalModelKey": "glm-5", "model": "GLM-5", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 65.49, "provisionalDisplayScore": 56, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 53.78, "upper": 77.2 }, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.25, "scoreB": 65.49, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "glm-5", "canonicalModelKey": "glm-5", "model": "GLM-5", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 65.49, "provisionalDisplayScore": 56, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 53.78, "upper": 77.2 }, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md" }, "scoreDiff": 4.239999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 56.2, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 66.3, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 60.8, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 66.4, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 92.6, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 83.1, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 56.3, "winner": null, "benchmarkCount": 8 } } }, { "slug": "glm-5-3-flash-vs-glm-5-reasoning", "url": "https://benchlm.ai/compare/glm-5-3-flash-vs-glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-3-flash-vs-glm-5-reasoning.md", "modelA": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "modelB": { "slug": "glm-5-reasoning", "canonicalModelKey": "glm-5-reasoning", "model": "GLM-5 (Reasoning)", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 60.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.04, "upper": 72.07 }, "rankingEligible": true, "overallRank": 67, "url": "https://benchlm.ai/models/glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/glm-5-reasoning.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.25, "scoreB": 60.55, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "scoreDiff": 0.7000000000000028, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "qwen3-8-27b-vs-qwen3-8-flash-next", "url": "https://benchlm.ai/compare/qwen3-8-27b-vs-qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-8-27b-vs-qwen3-8-flash-next.md", "modelA": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "modelB": { "slug": "qwen3-8-27b", "canonicalModelKey": "qwen3-8-27b", "model": "Qwen3.8-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 71.9, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 69.73, "upper": 74.07 }, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.91, "scoreB": 71.9, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "qwen3-8-27b", "canonicalModelKey": "qwen3-8-27b", "model": "Qwen3.8-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 71.9, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 69.73, "upper": 74.07 }, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md" }, "scoreDiff": 10.990000000000009, "winsA": 4, "winsB": 0, "comparableCategoryCount": 4, "benchmarkCountA": 24, "benchmarkCountB": 28, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 84.3, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 62.5, "avgB": 61.7, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 90.6, "avgB": 90.2, "winner": "A", "benchmarkCount": 11 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.4, "avgB": 38.7, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.3, "avgB": 79.5, "winner": "A", "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "qwen3-8-flash-next-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/qwen3-8-flash-next-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-8-flash-next-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.91, "scoreB": 78.55, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 17.64, "winsA": 0, "winsB": 3, "comparableCategoryCount": 3, "benchmarkCountA": 24, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 86.1, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 62.5, "avgB": 67.7, "winner": "B", "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 90.6, "avgB": 86.3, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 78.3, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.4, "avgB": 50.2, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.3, "avgB": 82.8, "winner": "B", "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "qwen3-7-flash-vs-qwen3-8-flash-next", "url": "https://benchlm.ai/compare/qwen3-7-flash-vs-qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-7-flash-vs-qwen3-8-flash-next.md", "modelA": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "modelB": { "slug": "qwen3-7-flash", "canonicalModelKey": "qwen3-7-flash", "model": "Qwen3.7 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.91, "scoreB": 0, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "scoreDiff": 60.91, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 62.5, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 90.6, "avgB": null, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.4, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "qwen3-5-flash-vs-qwen3-8-flash-next", "url": "https://benchlm.ai/compare/qwen3-5-flash-vs-qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-5-flash-vs-qwen3-8-flash-next.md", "modelA": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "modelB": { "slug": "qwen3-5-flash", "canonicalModelKey": "qwen3-5-flash", "model": "Qwen3.5 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 47.56, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.54, "upper": 70.59 }, "rankingEligible": true, "overallRank": 152, "url": "https://benchlm.ai/models/qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.91, "scoreB": 47.56, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "scoreDiff": 13.349999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 62.5, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 90.6, "avgB": null, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.4, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 4.7, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-opus-5-vs-qwen3-8-flash-next", "url": "https://benchlm.ai/compare/claude-opus-5-vs-qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-qwen3-8-flash-next.md", "modelA": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.91, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 21.430000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 62.5, "avgB": 89.5, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 90.6, "avgB": 66.9, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.4, "avgB": 64.7, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "granite-4-0-h-1b-vs-granite-4-2-8b", "url": "https://benchlm.ai/compare/granite-4-0-h-1b-vs-granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/compare/granite-4-0-h-1b-vs-granite-4-2-8b.md", "modelA": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "modelB": { "slug": "granite-4-0-h-1b", "canonicalModelKey": "granite-4-0-h-1b", "model": "Granite-4.0-H-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-h-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-1b.md" }, "rankingMode": "bench-align-v5", "scoreA": 46.32, "scoreB": 0, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "scoreDiff": 46.32, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": 36.5, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "granite-4-0-1b-vs-granite-4-2-8b", "url": "https://benchlm.ai/compare/granite-4-0-1b-vs-granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/compare/granite-4-0-1b-vs-granite-4-2-8b.md", "modelA": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "modelB": { "slug": "granite-4-0-1b", "canonicalModelKey": "granite-4-0-1b", "model": "Granite-4.0-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-1b.md" }, "rankingMode": "bench-align-v5", "scoreA": 46.32, "scoreB": 0, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "scoreDiff": 46.32, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": 36.5, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-opus-5-vs-granite-4-2-8b", "url": "https://benchlm.ai/compare/claude-opus-5-vs-granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-granite-4-2-8b.md", "modelA": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 46.32, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 36.02, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": 36.5, "avgB": 89.5, "winner": null, "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.2, "avgB": 64.7, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 7 } } }, { "slug": "granite-4-2-8b-vs-kimi-k3", "url": "https://benchlm.ai/compare/granite-4-2-8b-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/granite-4-2-8b-vs-kimi-k3.md", "modelA": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 46.32, "scoreB": 79.92, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 33.6, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 36.5, "avgB": null, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.2, "avgB": 61, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gpt-5-6-sol-vs-granite-4-2-8b", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-granite-4-2-8b.md", "modelA": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 46.32, "scoreB": 81.69, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 35.37, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 36.5, "avgB": 64.6, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.2, "avgB": 94.6, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.3, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 5 } } }, { "slug": "apodex-1-1-vs-apodex-1-1-mini", "url": "https://benchlm.ai/compare/apodex-1-1-vs-apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-apodex-1-1-mini.md", "modelA": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "modelB": { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.11, "scoreB": 0, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "scoreDiff": 56.11, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 10, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 77.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.1, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "apodex-1-1-vs-claude-opus-5", "url": "https://benchlm.ai/compare/apodex-1-1-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-claude-opus-5.md", "modelA": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.11, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 26.230000000000004, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 10, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 77.7, "avgB": 89.5, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.1, "avgB": 64.7, "winner": "B", "benchmarkCount": 16 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "apodex-1-1-vs-kimi-k3", "url": "https://benchlm.ai/compare/apodex-1-1-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-kimi-k3.md", "modelA": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.11, "scoreB": 79.92, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 23.810000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 10, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 77.7, "avgB": null, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.1, "avgB": 61, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "apodex-1-1-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/apodex-1-1-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-gpt-5-6-sol.md", "modelA": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.11, "scoreB": 81.69, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 25.58, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 10, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 77.7, "avgB": 64.6, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.1, "avgB": 94.6, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 4 } } }, { "slug": "apodex-1-1-vs-claude-fable-5-1", "url": "https://benchlm.ai/compare/apodex-1-1-vs-claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-claude-fable-5-1.md", "modelA": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "modelB": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.11, "scoreB": 82.74, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 26.629999999999995, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 10, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 77.7, "avgB": 81.2, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.1, "avgB": 65, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "apodex-1-1-mini-vs-claude-opus-5", "url": "https://benchlm.ai/compare/apodex-1-1-mini-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-mini-vs-claude-opus-5.md", "modelA": { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.34, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 82.34, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 2, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 90.8, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.7, "winner": null, "benchmarkCount": 16 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "apodex-1-1-mini-vs-kimi-k3", "url": "https://benchlm.ai/compare/apodex-1-1-mini-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-mini-vs-kimi-k3.md", "modelA": { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 79.92, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 79.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 2, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 89.5, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 61, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "apodex-1-1-mini-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/apodex-1-1-mini-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-mini-vs-gpt-5-6-sol.md", "modelA": { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, "modelB": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 81.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 81.69, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 2, "benchmarkCountB": 26, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 92, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 64.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 83, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 92.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 94.6, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 87.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "apodex-1-1-mini-vs-claude-fable-5-1", "url": "https://benchlm.ai/compare/apodex-1-1-mini-vs-claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-mini-vs-claude-fable-5-1.md", "modelA": { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md" }, "modelB": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 0, "scoreB": 82.74, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 82.74, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 2, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 81.2, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 65, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "ornith-1-5-35b-a3b-vs-ornith-1-5-397b", "url": "https://benchlm.ai/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/ornith-1-5-35b-a3b-vs-ornith-1-5-397b.md", "modelA": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "modelB": { "slug": "ornith-1-5-35b-a3b", "canonicalModelKey": "ornith-1-5-35b-a3b", "model": "Ornith-1.5-35B-A3B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 47.9, "provisionalDisplayScore": 51, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.03, "upper": 57.77 }, "rankingEligible": true, "overallRank": 149, "url": "https://benchlm.ai/models/ornith-1-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-35b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.4, "scoreB": 47.9, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "scoreDiff": 19.500000000000007, "winsA": 3, "winsB": 0, "comparableCategoryCount": 3, "benchmarkCountA": 18, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.6, "avgB": 67.6, "winner": "A", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 78, "avgB": 71.5, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.1, "avgB": 34.2, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "ornith-1-5-397b-vs-ornith-1-5-9b", "url": "https://benchlm.ai/compare/ornith-1-5-397b-vs-ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/compare/ornith-1-5-397b-vs-ornith-1-5-9b.md", "modelA": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "modelB": { "slug": "ornith-1-5-9b", "canonicalModelKey": "ornith-1-5-9b", "model": "Ornith-1.5-9B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 37.33, "provisionalDisplayScore": 39, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 27.46, "upper": 47.2 }, "rankingEligible": true, "overallRank": 205, "url": "https://benchlm.ai/models/ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-9b.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.4, "scoreB": 37.33, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "scoreDiff": 30.070000000000007, "winsA": 3, "winsB": 0, "comparableCategoryCount": 3, "benchmarkCountA": 18, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.6, "avgB": 56.4, "winner": "A", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 78, "avgB": 61.7, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.1, "avgB": 29.1, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "ornith-1-0-397b-vs-ornith-1-5-397b", "url": "https://benchlm.ai/compare/ornith-1-0-397b-vs-ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/ornith-1-0-397b-vs-ornith-1-5-397b.md", "modelA": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "modelB": { "slug": "ornith-1-0-397b", "canonicalModelKey": "ornith-1-0-397b", "model": "Ornith-1.0-397B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.4, "scoreB": 68, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "ornith-1-0-397b", "canonicalModelKey": "ornith-1-0-397b", "model": "Ornith-1.0-397B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md" }, "scoreDiff": 0.5999999999999943, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.6, "avgB": 77.5, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 78, "avgB": 74.6, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.1, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-5-vs-ornith-1-5-397b", "url": "https://benchlm.ai/compare/claude-opus-5-vs-ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-ornith-1-5-397b.md", "modelA": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "modelB": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.4, "scoreB": 82.34, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 14.939999999999998, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 64, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.6, "avgB": 90.8, "winner": "B", "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": 78, "avgB": 89.5, "winner": "B", "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 66.9, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.1, "avgB": 64.7, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "kimi-k3-vs-ornith-1-5-397b", "url": "https://benchlm.ai/compare/kimi-k3-vs-ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-ornith-1-5-397b.md", "modelA": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.4, "scoreB": 79.92, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 12.519999999999996, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.6, "avgB": 89.5, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 78, "avgB": null, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.5, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.1, "avgB": 61, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-5-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-opus-5-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-kimi-k3.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 79.92, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 2.4200000000000017, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 37, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 89.5, "winner": null, "benchmarkCount": 23 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": null, "winner": null, "benchmarkCount": 18 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 78.5, "winner": null, "benchmarkCount": 20 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 61, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-fable-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-opus-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 82.49, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 0.14999999999999147, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 64, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 84.6, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 89.2, "winner": "A", "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 57.9, "winner": "A", "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": null, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-4-8-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-claude-opus-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 75.96, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 6.38000000000001, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 64, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 80.3, "winner": null, "benchmarkCount": 24 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 81.1, "winner": "A", "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 77, "winner": null, "benchmarkCount": 11 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 72.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 62.7, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 53.9, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-opus-5-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-qwen3-8-max.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 78.55, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 3.7900000000000063, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 86.1, "winner": null, "benchmarkCount": 28 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 67.7, "winner": null, "benchmarkCount": 18 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 86.3, "winner": null, "benchmarkCount": 32 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 78.3, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 50.2, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-5-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-opus-5-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-qwen3-7-max.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 11.070000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 69.7, "winner": null, "benchmarkCount": 25 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 77.9, "winner": null, "benchmarkCount": 17 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": null, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 90.4, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 64.2, "winner": null, "benchmarkCount": 21 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 7 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.1, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gpt-5-6-terra.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 9.840000000000003, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 87.4, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 63.4, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 80.7, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 83.9, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 92.9, "winner": null, "benchmarkCount": 18 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-opus-5-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 17.620000000000005, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 64, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 81.9, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 76.7, "winner": "A", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 88.3, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 57.4, "winner": "A", "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-5-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-opus-5-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-qwen3-7-plus.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 16.89, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 71.7, "winner": null, "benchmarkCount": 26 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 75.6, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 81.5, "winner": null, "benchmarkCount": 23 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 91.7, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 60.1, "winner": null, "benchmarkCount": 21 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 7 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-opus-5-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-muse-spark-1-1.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 5.820000000000007, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 80.4, "winner": null, "benchmarkCount": 28 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 61.5, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 88.4, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 62.1, "winner": "A", "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-5-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gemini-3-7-flash.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 21.340000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": null, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": null, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": null, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": null, "winner": null, "benchmarkCount": 15 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-opus-5-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gpt-5-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 9.659999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 81.6, "winner": null, "benchmarkCount": 27 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 58.6, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 70.4, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 85, "winner": "A", "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 57.8, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gpt-5-6-luna.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 15.409999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 84.1, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 62.7, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 78.4, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 59.5, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 92.3, "winner": null, "benchmarkCount": 18 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-opus-5-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-opus-5-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-glm-5-2.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 19.46, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 64, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 81, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 62.1, "winner": null, "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": null, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 59.6, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 9 } } }, { "slug": "claude-opus-4-7-adaptive-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-claude-opus-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 10.13000000000001, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 64, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 75.1, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 78.6, "winner": "A", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 65.1, "winner": null, "benchmarkCount": 10 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 75.8, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 60, "winner": null, "benchmarkCount": 17 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-5-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-opus-5-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-5-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "scoreDiff": 26.130000000000003, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": null, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": null, "winner": null, "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 82.6, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 77.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": null, "winner": null, "benchmarkCount": 18 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-fable-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-fable-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 82.49, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 2.569999999999993, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 84.6, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.2, "winner": null, "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 57.9, "winner": null, "benchmarkCount": 14 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-opus-4-8-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 75.96, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 3.960000000000008, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 80.3, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 81.1, "winner": null, "benchmarkCount": 17 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 77, "winner": null, "benchmarkCount": 14 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 72.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 62.7, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 53.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "kimi-k3-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/kimi-k3-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-qwen3-8-max.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 78.55, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 1.3700000000000045, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 86.1, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 67.7, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 86.3, "winner": null, "benchmarkCount": 28 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 78.3, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 50.2, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "kimi-k3-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/kimi-k3-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-qwen3-7-max.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 8.650000000000006, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 69.7, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 77.9, "winner": null, "benchmarkCount": 17 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": null, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 64.2, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-terra-vs-kimi-k3", "url": "https://benchlm.ai/compare/gpt-5-6-terra-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-terra-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 7.420000000000002, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 87.4, "winner": "A", "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 63.4, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 80.7, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 83.9, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 92.9, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 15.200000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 81.9, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 76.7, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 88.3, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 57.4, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "kimi-k3-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/kimi-k3-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-qwen3-7-plus.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 14.469999999999999, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 71.7, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 75.6, "winner": null, "benchmarkCount": 17 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 81.5, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 91.7, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 60.1, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "kimi-k3-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/kimi-k3-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/kimi-k3-vs-muse-spark-1-1.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 3.4000000000000057, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 80.4, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 61.5, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 88.4, "winner": null, "benchmarkCount": 14 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 62.1, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gemini-3-7-flash-vs-kimi-k3", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 18.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": null, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-5-vs-kimi-k3", "url": "https://benchlm.ai/compare/gpt-5-5-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 7.239999999999995, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 81.6, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 58.6, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 70.4, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 57.8, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-luna-vs-kimi-k3", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 12.989999999999995, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 84.1, "winner": "A", "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 62.7, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 78.4, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 59.5, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-kimi-k3", "url": "https://benchlm.ai/compare/glm-5-2-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 17.04, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 81, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 62.1, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": null, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 59.6, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 7.710000000000008, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 75.1, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 78.6, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 65.1, "winner": null, "benchmarkCount": 13 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 60, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gemini-3-1-pro-vs-kimi-k3", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "scoreDiff": 23.71, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 37, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": null, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 82.6, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-fable-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-fable-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 82.49, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 0.7999999999999972, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 84.6, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 89.2, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 57.9, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-sol-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-qwen3-8-max.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 78.55, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 3.1400000000000006, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 26, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 86.1, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 67.7, "winner": "B", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 86.3, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 78.3, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 50.2, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-sol-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-qwen3-7-max.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 10.420000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 69.7, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 77.9, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 90.4, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 64.2, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 97.1, "winner": null, "benchmarkCount": 6 } } }, { "slug": "gpt-5-6-sol-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 9.189999999999998, "winsA": 6, "winsB": 0, "comparableCategoryCount": 6, "benchmarkCountA": 26, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 87.4, "winner": "A", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 63.4, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 80.7, "winner": "A", "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 83.9, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 92.9, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 80.8, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-sol-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-qwen3-7-plus.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 16.239999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 71.7, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 75.6, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 81.5, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 91.7, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 60.1, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 92.9, "winner": null, "benchmarkCount": 6 } } }, { "slug": "gpt-5-6-sol-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gpt-5-6-sol-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-sol-vs-muse-spark-1-1.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 5.170000000000002, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 26, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 80.4, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 61.5, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 88.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 62.1, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 20.689999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-5-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/gpt-5-5-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 9.009999999999991, "winsA": 3, "winsB": 0, "comparableCategoryCount": 3, "benchmarkCountA": 26, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 81.6, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 58.6, "winner": "A", "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 85, "winner": "A", "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 57.8, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 47.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-luna-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 14.759999999999991, "winsA": 6, "winsB": 0, "comparableCategoryCount": 6, "benchmarkCountA": 26, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 84.1, "winner": "A", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 62.7, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 78.4, "winner": "A", "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 59.5, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 92.3, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 73.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/glm-5-2-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 18.809999999999995, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 26, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 81, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 62.1, "winner": "A", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 59.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 95.9, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 9.480000000000004, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 26, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 75.1, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 78.6, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 65.1, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 75.8, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 60, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-1-pro-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "scoreDiff": 25.479999999999997, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 26, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 82.6, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": 77.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 31.8, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-claude-opus-4-8", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-opus-4-8.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 75.96, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 6.780000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 80.3, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 81.1, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 77, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 72.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 62.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 53.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-qwen3-8-max.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 78.55, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 4.189999999999998, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 86.1, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 67.7, "winner": "A", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 86.3, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 78.3, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 50.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-qwen3-7-max.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 71.27, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 11.469999999999999, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 69.7, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 77.9, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 90.4, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 64.2, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gpt-5-6-terra.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 72.5, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 10.239999999999995, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87.4, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 63.4, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 80.7, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 83.9, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 92.9, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 64.72, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 18.019999999999996, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81.9, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 76.7, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 88.3, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 57.4, "winner": "A", "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-qwen3-7-plus.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 65.45, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 17.289999999999992, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 71.7, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 75.6, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 81.5, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 91.7, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 60.1, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-muse-spark-1-1.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 76.52, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 6.219999999999999, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 80.4, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 61.5, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 88.4, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 62.1, "winner": "A", "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gemini-3-7-flash.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 61, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 21.739999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-5-1-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gpt-5-5.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 10.059999999999988, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81.6, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 58.6, "winner": "A", "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 85, "winner": "A", "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gpt-5-6-luna.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 66.93, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 15.809999999999988, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 18, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 84.1, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 62.7, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.4, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 59.5, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-5-1-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-glm-5-2.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 19.859999999999992, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 62.1, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 59.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-fable-5-1-vs-claude-opus-4-7-adaptive", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-opus-4-7-adaptive.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 10.530000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 75.1, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 78.6, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 65.1, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 75.8, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 60, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-fable-5-1-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "scoreDiff": 26.529999999999994, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 18, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 82.6, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": 77.1, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": null, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-fable-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-fable-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-qwen3-8-max.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 78.55, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 3.9399999999999977, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 86.1, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 67.7, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 86.3, "winner": null, "benchmarkCount": 26 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 78.3, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 50.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-fable-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-qwen3-7-max.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 11.219999999999999, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 69.7, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 77.9, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 90.4, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 64.2, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-fable-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gpt-5-6-terra.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 9.989999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 87.4, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 63.4, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 80.7, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 83.9, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 17.769999999999996, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 81.9, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 76.7, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 88.3, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 57.4, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-fable-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-qwen3-7-plus.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 17.039999999999992, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 71.7, "winner": "A", "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 75.6, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 81.5, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 91.7, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 60.1, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-fable-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-muse-spark-1-1.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 5.969999999999999, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 80.4, "winner": "A", "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 61.5, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 88.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 62.1, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-fable-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gemini-3-7-flash.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 21.489999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": null, "winner": null, "benchmarkCount": 3 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-fable-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-fable-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gpt-5-6-luna.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 15.559999999999988, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 84.1, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 62.7, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 78.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 59.5, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 92.3, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-fable-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-fable-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-glm-5-2.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 19.609999999999992, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 81, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 62.1, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 59.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-fable-vs-claude-opus-4-7-adaptive", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-opus-4-7-adaptive.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 10.280000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 75.1, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 78.6, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 65.1, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 60, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-fable-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-fable-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "scoreDiff": 26.279999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 82.6, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-opus-4-8-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-qwen3-8-max.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 78.55, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 2.5900000000000034, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 54, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 86.1, "winner": null, "benchmarkCount": 23 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 67.7, "winner": null, "benchmarkCount": 16 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 86.3, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 78.3, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 50.2, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 82.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-8-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-qwen3-7-max.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 4.689999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 69.7, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 77.9, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": null, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 90.4, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 64.2, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 97.1, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-8-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gpt-5-6-terra.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 3.4599999999999937, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 87.4, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 63.4, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 80.7, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 83.9, "winner": "B", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 92.9, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 80.8, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-8-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-qwen3-7-plus.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 10.509999999999991, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 71.7, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 75.6, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 81.5, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 91.7, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 60.1, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 92.9, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-8-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-muse-spark-1-1.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 0.5600000000000023, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 80.4, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 61.5, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 88.4, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 62.1, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-8-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gemini-3-7-flash.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 14.959999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 33, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": null, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": null, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": null, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-8-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gpt-5-6-luna.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 9.029999999999987, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 84.1, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 62.7, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 78.4, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 59.5, "winner": "A", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 73.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-8-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-glm-5-2.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 13.079999999999991, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 81, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 62.1, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": null, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 59.6, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 95.9, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-opus-4-8-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-opus-4-8-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-8-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "scoreDiff": 19.749999999999993, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": null, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": null, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 82.6, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": 77.1, "winner": "B", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 31.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "qwen3-7-max-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/qwen3-7-max-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-7-max-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 71.27, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 7.280000000000001, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 54, "benchmarkCountB": 36, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 69.7, "winner": null, "benchmarkCount": 22 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 77.9, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": null, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 90.4, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 64.2, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": 84.4, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-terra-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gpt-5-6-terra-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-terra-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 6.049999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 87.4, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 63.4, "winner": "A", "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 80.7, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 83.9, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 92.9, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 13.829999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 54, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 81.9, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 76.7, "winner": null, "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 88.3, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 57.4, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "qwen3-7-plus-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/qwen3-7-plus-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-7-plus-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 13.099999999999994, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 71.7, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 75.6, "winner": null, "benchmarkCount": 14 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 81.5, "winner": "A", "benchmarkCount": 26 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 91.7, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 60.1, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "muse-spark-1-1-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/muse-spark-1-1-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/muse-spark-1-1-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 2.030000000000001, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 80.4, "winner": null, "benchmarkCount": 23 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 61.5, "winner": "A", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 88.4, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 62.1, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gemini-3-7-flash-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 17.549999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 54, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": null, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": null, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-5-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gpt-5-5-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 5.86999999999999, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 54, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 81.6, "winner": null, "benchmarkCount": 23 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 58.6, "winner": "A", "benchmarkCount": 15 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 70.4, "winner": null, "benchmarkCount": 26 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 85, "winner": null, "benchmarkCount": 6 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 57.8, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-luna-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 11.61999999999999, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 84.1, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 62.7, "winner": "A", "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 78.4, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 59.5, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/glm-5-2-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 15.669999999999995, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 54, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 81, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 62.1, "winner": "A", "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": null, "winner": null, "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 59.6, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 6.340000000000003, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 75.1, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 78.6, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 65.1, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 75.8, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 60, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gemini-3-1-pro-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "scoreDiff": 22.339999999999996, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": null, "winner": null, "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": null, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 82.6, "winner": "A", "benchmarkCount": 24 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": 77.1, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gpt-5-6-terra-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gpt-5-6-terra-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-terra-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 72.5, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 1.230000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 87.4, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 63.4, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 80.7, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 83.9, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 92.9, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 80.8, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-sonnet-5-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 64.72, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 6.549999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 81.9, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 76.7, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 88.3, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 57.4, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "qwen3-7-max-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/qwen3-7-max-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/qwen3-7-max-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 65.45, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 5.819999999999993, "winsA": 4, "winsB": 2, "comparableCategoryCount": 6, "benchmarkCountA": 36, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 71.7, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 75.6, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 81.5, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 91.7, "winner": "B", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 60.1, "winner": "A", "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": 84.5, "winner": "B", "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": 85.4, "winner": "A", "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 92.9, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "muse-spark-1-1-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/muse-spark-1-1-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/muse-spark-1-1-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 5.25, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 80.4, "winner": null, "benchmarkCount": 20 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 61.5, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 88.4, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 62.1, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 10.269999999999996, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": null, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": null, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": null, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-5-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gpt-5-5-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 1.4100000000000108, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 81.6, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 58.6, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 85, "winner": null, "benchmarkCount": 6 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 57.8, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 47.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "gpt-5-6-luna-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 4.339999999999989, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 84.1, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 62.7, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.4, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 59.5, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 92.3, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 73.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "glm-5-2-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/glm-5-2-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 8.389999999999993, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 36, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 81, "winner": "B", "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 62.1, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 59.6, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 95.9, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-7-adaptive-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 0.9399999999999977, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 75.1, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 78.6, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 65.1, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 75.8, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 60, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": null, "winner": null, "benchmarkCount": 4 } } }, { "slug": "gemini-3-1-pro-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "scoreDiff": 15.059999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": null, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": null, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 82.6, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": 77.1, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": null, "winner": null, "benchmarkCount": 10 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 31.8, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-sonnet-5-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 64.72, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 7.780000000000001, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 81.9, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 76.7, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 88.3, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 57.4, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-terra-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gpt-5-6-terra-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-terra-vs-qwen3-7-plus.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 65.45, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 7.049999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 71.7, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 75.6, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 81.5, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 91.7, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 60.1, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 92.9, "winner": null, "benchmarkCount": 6 } } }, { "slug": "gpt-5-6-terra-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gpt-5-6-terra-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-terra-vs-muse-spark-1-1.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 76.52, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 4.019999999999996, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 24, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 80.4, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 61.5, "winner": "A", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 88.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 62.1, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 61, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 11.5, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-5-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gpt-5-5-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 0.18000000000000682, "winsA": 2, "winsB": 1, "comparableCategoryCount": 3, "benchmarkCountA": 24, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 81.6, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 58.6, "winner": "A", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 85, "winner": "B", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 57.8, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 47.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-luna-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 66.93, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 5.569999999999993, "winsA": 6, "winsB": 0, "comparableCategoryCount": 6, "benchmarkCountA": 24, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 84.1, "winner": "A", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 62.7, "winner": "A", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 78.4, "winner": "A", "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 59.5, "winner": "A", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 92.3, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 73.6, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/glm-5-2-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 9.619999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 24, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 81, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 62.1, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 59.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 95.9, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 0.29000000000000625, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 24, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 75.1, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 78.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 65.1, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 75.8, "winner": "A", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 60, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-1-pro-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "scoreDiff": 16.29, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 24, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 82.6, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": 77.1, "winner": "A", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 31.8, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-qwen3-7-plus.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 65.45, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "scoreDiff": 0.730000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 16, "benchmarkCountB": 51, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 71.7, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 75.6, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 81.5, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 91.7, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 60.1, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 84.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 85.4, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 92.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-muse-spark-1-1.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 76.52, "evidenceStatusA": "estimated", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 11.799999999999997, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 16, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 80.4, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 61.5, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 88.4, "winner": "B", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 62.1, "winner": "B", "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-sonnet-5-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gemini-3-7-flash.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 61, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "scoreDiff": 3.719999999999999, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 16, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "claude-sonnet-5-vs-gpt-5-5", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gpt-5-5.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 7.960000000000008, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 16, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 81.6, "winner": "A", "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 58.6, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 70.4, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gpt-5-6-luna.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 66.93, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 2.210000000000008, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 16, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 84.1, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 62.7, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 78.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 59.5, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-sonnet-5-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-glm-5-2.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "scoreDiff": 1.8399999999999963, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 16, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 81, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 62.1, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 59.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 7.489999999999995, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 16, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 75.1, "winner": "A", "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 78.6, "winner": "B", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 65.1, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 60, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-sonnet-5-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-sonnet-5-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-sonnet-5-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "scoreDiff": 8.509999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 16, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 82.6, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "muse-spark-1-1-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/muse-spark-1-1-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/muse-spark-1-1-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 76.52, "evidenceStatusA": "supported", "evidenceStatusB": "supported", "overallWinner": "B", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 11.069999999999993, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 51, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 80.4, "winner": "B", "benchmarkCount": 19 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 61.5, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 88.4, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 62.1, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "scoreDiff": 4.450000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": null, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": null, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-5-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gpt-5-5-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 7.230000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 81.6, "winner": null, "benchmarkCount": 18 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 58.6, "winner": null, "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 70.4, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": 85, "winner": null, "benchmarkCount": 6 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 57.8, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 47.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "gpt-5-6-luna-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 1.480000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 84.1, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 62.7, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 78.4, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": 59.5, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 92.3, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 73.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "glm-5-2-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/glm-5-2-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "scoreDiff": 2.5700000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 81, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 62.1, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": null, "winner": null, "benchmarkCount": 15 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 59.6, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 95.9, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-7-adaptive-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 6.759999999999991, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 75.1, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 78.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 65.1, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": 75.8, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 60, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": null, "winner": null, "benchmarkCount": 4 } } }, { "slug": "gemini-3-1-pro-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "scoreDiff": 9.240000000000002, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 51, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": null, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": null, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 82.6, "winner": "B", "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": 77.1, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": null, "winner": null, "benchmarkCount": 10 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 5 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 31.8, "winner": null, "benchmarkCount": 5 } } }, { "slug": "gemini-3-7-flash-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 61, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 15.519999999999996, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 21, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": null, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 } } }, { "slug": "gpt-5-5-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gpt-5-5-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 72.68, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 3.839999999999989, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 21, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": 81.6, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": 58.6, "winner": "A", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": 70.4, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 5 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": 57.8, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gpt-5-6-luna-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gpt-5-6-luna-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-6-luna-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 66.93, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 9.58999999999999, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 21, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": 84.1, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": 62.7, "winner": "B", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": 78.4, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 59.5, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/glm-5-2-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 62.88, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 13.639999999999993, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 21, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": 81, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": 62.1, "winner": "B", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": 59.6, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 72.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 4.310000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 21, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": 75.1, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": 78.6, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": 65.1, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": 60, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gemini-3-1-pro-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 56.21, "evidenceStatusA": "supported", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "scoreDiff": 20.309999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 21, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": null, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": 82.6, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gemini-3-7-flash-vs-gpt-5-5", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-gpt-5-5", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-gpt-5-5.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 72.68, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 11.680000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 33, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81.6, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 58.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 70.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 85, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 57.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 47.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-gpt-5-6-luna.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 66.93, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 5.930000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 84.1, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 62.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 78.4, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 59.5, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 92.3, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 73.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-7-flash-vs-glm-5-2", "url": "https://benchlm.ai/compare/gemini-3-7-flash-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-7-flash-vs-glm-5-2.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "scoreDiff": 1.8800000000000026, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 81, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 62.1, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 59.6, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 95.9, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gemini-3-7-flash.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 11.209999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 75.1, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 78.6, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 65.1, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 60, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "gemini-3-1-pro-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gemini-3-7-flash.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "scoreDiff": 4.789999999999999, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 82.6, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 2 } } }, { "slug": "gpt-5-5-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/gpt-5-5-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/gpt-5-5-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "modelB": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.68, "scoreB": 66.93, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-5", "canonicalModelKey": "gpt-5-5", "model": "GPT-5.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.68, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 64.14, "upper": 81.23 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md" }, "scoreDiff": 5.75, "winsA": 1, "winsB": 2, "comparableCategoryCount": 3, "benchmarkCountA": 33, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.6, "avgB": 84.1, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 58.6, "avgB": 62.7, "winner": "B", "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 70.4, "avgB": 78.4, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 85, "avgB": 59.5, "winner": "A", "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.8, "avgB": 92.3, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 47.6, "avgB": 73.6, "winner": "B", "benchmarkCount": 3 } } }, { "slug": "glm-5-2-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/glm-5-2-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/glm-5-2-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "modelB": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.93, "scoreB": 62.88, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 4.050000000000004, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 24, "benchmarkCountB": 20, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.1, "avgB": 81, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 62.7, "avgB": 62.1, "winner": "A", "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.3, "avgB": 59.6, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 73.6, "avgB": 95.9, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.93, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 5.279999999999987, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 24, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.1, "avgB": 75.1, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 62.7, "avgB": 78.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.4, "avgB": 65.1, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59.5, "avgB": 75.8, "winner": "B", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.3, "avgB": 60, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 73.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "gemini-3-1-pro-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.93, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "scoreDiff": 10.720000000000006, "winsA": 1, "winsB": 1, "comparableCategoryCount": 2, "benchmarkCountA": 24, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.1, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 62.7, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.4, "avgB": 82.6, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59.5, "avgB": 77.1, "winner": "B", "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.3, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 73.6, "avgB": 31.8, "winner": "A", "benchmarkCount": 3 } } }, { "slug": "claude-opus-4-7-adaptive-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-glm-5-2.md", "modelA": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "modelB": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "rankingMode": "bench-align-v5", "scoreA": 62.88, "scoreB": 72.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "B", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 9.329999999999991, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 20, "benchmarkCountB": 21, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81, "avgB": 75.1, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 62.1, "avgB": 78.6, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 65.1, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 4 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 59.6, "avgB": 60, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 95.9, "avgB": null, "winner": null, "benchmarkCount": 5 } } }, { "slug": "gemini-3-1-pro-vs-glm-5-2", "url": "https://benchlm.ai/compare/gemini-3-1-pro-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/gemini-3-1-pro-vs-glm-5-2.md", "modelA": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 62.88, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "scoreDiff": 6.670000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 20, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81, "avgB": null, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 62.1, "avgB": null, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 82.6, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 77.1, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 59.6, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": 95.9, "avgB": 31.8, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-opus-4-7-adaptive-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-opus-4-7-adaptive-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-opus-4-7-adaptive-vs-gemini-3-1-pro.md", "modelA": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "modelB": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.21, "scoreB": 56.21, "evidenceStatusA": "estimated", "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "scoreDiff": 15.999999999999993, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 21, "benchmarkCountB": 23, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 75.1, "avgB": null, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 78.6, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 65.1, "avgB": 82.6, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 75.8, "avgB": 77.1, "winner": "B", "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 31.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-claude-opus-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-5.md", "modelA": { "slug": "claude-opus-5", "canonicalModelKey": "claude-opus-5", "model": "Claude Opus 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 82.34, "provisionalDisplayScore": 84, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 79.1, "upper": 85.59 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.34, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 3.6599999999999966, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 64, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 90.8, "avgB": 87, "winner": null, "benchmarkCount": 21 }, "coding": { "categoryLabel": "Coding", "avgA": 89.5, "avgB": 89.7, "winner": "B", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.9, "avgB": 93.5, "winner": null, "benchmarkCount": 11 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.7, "avgB": 68.5, "winner": null, "benchmarkCount": 16 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 4 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-mythos-5-vs-kimi-k3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-kimi-k3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-kimi-k3.md", "modelA": { "slug": "kimi-k3", "canonicalModelKey": "kimi-3", "model": "Kimi K3", "creator": "Moonshot AI", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 79.92, "provisionalDisplayScore": 82, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 77.66, "upper": 82.19 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 79.92, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 6.079999999999998, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 37, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 89.5, "avgB": 87, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 93.5, "winner": null, "benchmarkCount": 14 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 61, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-6-sol", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-6-sol.md", "modelA": { "slug": "gpt-5-6-sol", "canonicalModelKey": "gpt-5-6-sol", "model": "GPT-5.6 Sol", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 81.69, "provisionalDisplayScore": 80, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 78.87, "upper": 84.5 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 81.69, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 4.310000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 26, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 92, "avgB": 87, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 64.6, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 92.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 94.6, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 87.5, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-fable-5-1-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-fable-5-1-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-5-1-vs-claude-mythos-5.md", "modelA": { "slug": "claude-fable-5-1", "canonicalModelKey": "claude-fable-5-1", "model": "Claude Fable 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 82.74, "provisionalDisplayScore": 79, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 71.23, "upper": 94.26 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.74, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 3.260000000000005, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 18, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 81.2, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 65, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-fable-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-fable-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-fable-vs-claude-mythos-5.md", "modelA": { "slug": "claude-fable", "canonicalModelKey": "claude-fable-5", "model": "Claude Fable 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": 82.49, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 80.26, "upper": 84.73 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 82.49, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 3.510000000000005, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 12, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.6, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.2, "avgB": 89.7, "winner": "B", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 57.9, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-8", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-8.md", "modelA": { "slug": "claude-opus-4-8", "canonicalModelKey": "claude-opus-4-8", "model": "Claude Opus 4.8", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.96, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 73.5, "upper": 78.43 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 75.96, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 10.040000000000006, "winsA": 0, "winsB": 3, "comparableCategoryCount": 3, "benchmarkCountA": 33, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.3, "avgB": 87, "winner": "B", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 81.1, "avgB": 89.7, "winner": "B", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 72.1, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.7, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": 53.9, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-qwen3-8-max", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-8-max.md", "modelA": { "slug": "qwen3-8-max", "canonicalModelKey": "qwen3-8-max", "model": "Qwen3.8 Max", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.55, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 76.4, "upper": 80.7 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 78.55, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 7.450000000000003, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 54, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 86.1, "avgB": 87, "winner": null, "benchmarkCount": 17 }, "coding": { "categoryLabel": "Coding", "avgA": 67.7, "avgB": 89.7, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 86.3, "avgB": 93.5, "winner": null, "benchmarkCount": 25 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 78.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 50.2, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-7-max", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-7-max.md", "modelA": { "slug": "qwen3-7-max", "canonicalModelKey": "qwen3-7-max", "model": "Qwen3.7 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 71.27, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 63.59, "upper": 78.94 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 71.27, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 14.730000000000004, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.7, "avgB": 87, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 77.9, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 90.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 64.2, "avgB": 68.5, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-gpt-5-6-terra", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-6-terra.md", "modelA": { "slug": "gpt-5-6-terra", "canonicalModelKey": "gpt-5-6-terra", "model": "GPT-5.6 Terra", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 72.5, "provisionalDisplayScore": 76, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 63.24, "upper": 81.76 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.5, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13.5, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87.4, "avgB": 87, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 63.4, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.7, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 83.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.9, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 80.8, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-claude-sonnet-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-sonnet-5.md", "modelA": { "slug": "claude-sonnet-5", "canonicalModelKey": "claude-sonnet-5", "model": "Claude Sonnet 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.72, "provisionalDisplayScore": 75, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.18, "upper": 78.26 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.72, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 21.28, "winsA": 0, "winsB": 3, "comparableCategoryCount": 3, "benchmarkCountA": 16, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81.9, "avgB": 87, "winner": "B", "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 76.7, "avgB": 89.7, "winner": "B", "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.3, "avgB": 93.5, "winner": "B", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.4, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-7-plus", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-7-plus.md", "modelA": { "slug": "qwen3-7-plus", "canonicalModelKey": "qwen3-7-plus", "model": "Qwen3.7 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.45, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.69, "upper": 76.21 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.45, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.549999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 51, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 71.7, "avgB": 87, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 75.6, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.5, "avgB": 93.5, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 91.7, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60.1, "avgB": 68.5, "winner": null, "benchmarkCount": 8 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 84.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.4, "avgB": null, "winner": null, "benchmarkCount": 6 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-muse-spark-1-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-muse-spark-1-1.md", "modelA": { "slug": "muse-spark-1-1", "canonicalModelKey": "muse-spark-1-1", "model": "Muse Spark 1.1", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 76.52, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 71.9, "upper": 81.14 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 76.52, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 9.480000000000004, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 21, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 80.4, "avgB": 87, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 61.5, "avgB": 89.7, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 88.4, "avgB": 93.5, "winner": "B", "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.1, "avgB": 68.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemini-3-7-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-7-flash.md", "modelA": { "slug": "gemini-3-7-flash", "canonicalModelKey": "gemini-3-7-flash", "model": "Gemini 3.7 Flash", "creator": "Google", "sourceType": "Pending", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": 61, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.48, "upper": 72.51 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 61, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 0, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-6-luna", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-6-luna.md", "modelA": { "slug": "gpt-5-6-luna", "canonicalModelKey": "gpt-5-6-luna", "model": "GPT-5.6 Luna", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 66.93, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.29, "upper": 76.58 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.93, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 19.069999999999993, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 24, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 84.1, "avgB": 87, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 62.7, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.4, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.3, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 73.6, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-glm-5-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-2.md", "modelA": { "slug": "glm-5-2", "canonicalModelKey": "glm-5-2", "model": "GLM-5.2", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.88, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.66, "upper": 77.1 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 62.88, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23.119999999999997, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 20, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 81, "avgB": 87, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 62.1, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 59.6, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 95.9, "avgB": 97.6, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-7-adaptive", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-7-adaptive.md", "modelA": { "slug": "claude-opus-4-7-adaptive", "canonicalModelKey": "claude-opus-4-7-max", "model": "Claude Opus 4.7 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 72.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 62.34, "upper": 82.07 }, "rankingEligible": true, "overallRank": 16, "url": "https://benchlm.ai/models/claude-opus-4-7-adaptive", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7-adaptive.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 72.21, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13.790000000000006, "winsA": 0, "winsB": 3, "comparableCategoryCount": 3, "benchmarkCountA": 21, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 75.1, "avgB": 87, "winner": "B", "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 78.6, "avgB": 89.7, "winner": "B", "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 65.1, "avgB": 93.5, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 75.8, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 60, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gemini-3-1-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-1-pro.md", "modelA": { "slug": "gemini-3-1-pro", "canonicalModelKey": "gemini-3-1-pro", "model": "Gemini 3.1 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.21, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.17, "upper": 72.24 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.21, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.79, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 23, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 82.6, "avgB": 93.5, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 77.1, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 31.8, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-muse-spark-1-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-muse-spark-1-2.md", "modelA": { "slug": "muse-spark-1-2", "canonicalModelKey": "muse-spark-1-2", "model": "Muse Spark 1.2", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.29, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.78, "upper": 72.81 }, "rankingEligible": true, "overallRank": 55, "url": "https://benchlm.ai/models/muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-2.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.29, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24.71, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 3, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemini-3-5-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-5-flash.md", "modelA": { "slug": "gemini-3-5-flash", "canonicalModelKey": "gemini-3-5-flash", "model": "Gemini 3.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.2, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 54.19, "upper": 74.21 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.2, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 21.799999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 22, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 77.2, "avgB": 87, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 55.1, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 83.8, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 74.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 40.2, "avgB": 68.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 32.9, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-6", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-6.md", "modelA": { "slug": "claude-opus-4-6", "canonicalModelKey": "claude-opus-4-6", "model": "Claude Opus 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 67.89, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 53.87, "upper": 81.9 }, "rankingEligible": true, "overallRank": 23, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.89, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18.11, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 33, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 73, "avgB": 87, "winner": "B", "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 68.1, "avgB": 89.7, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77.3, "avgB": 93.5, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 69.1, "avgB": 68.5, "winner": null, "benchmarkCount": 9 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 36.3, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-deepseek-v4-pro-0813", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-deepseek-v4-pro-0813.md", "modelA": { "slug": "deepseek-v4-pro-0813", "canonicalModelKey": "deepseek-v4-pro-max", "model": "DeepSeek V4 Pro 0813", "creator": "DeepSeek", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.22, "provisionalDisplayScore": 64, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.35, "upper": 71.09 }, "rankingEligible": true, "overallRank": 57, "url": "https://benchlm.ai/models/deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-0813.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 61.22, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24.78, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 34, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 74.5, "avgB": 87, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 70.9, "avgB": 89.7, "winner": "B", "benchmarkCount": 12 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 62.5, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 95.2, "avgB": 97.6, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-gpt-5-4", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-4", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-4.md", "modelA": { "slug": "gpt-5-4", "canonicalModelKey": "gpt-5-4", "model": "GPT-5.4", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 73.04, "provisionalDisplayScore": 64, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 69.63, "upper": 76.45 }, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 73.04, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 12.959999999999994, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 37, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 77.2, "avgB": 87, "winner": "B", "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 57.7, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 73.2, "avgB": 93.5, "winner": null, "benchmarkCount": 11 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 74, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.6, "avgB": 68.5, "winner": "B", "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 42.5, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-kimi-2-6", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-kimi-2-6", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-kimi-2-6.md", "modelA": { "slug": "kimi-2-6", "canonicalModelKey": "kimi-2-6", "model": "Kimi K2.6", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 59.09, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 68.96 }, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 59.09, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.909999999999997, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 32, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 73.5, "avgB": 87, "winner": "B", "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 64.4, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 79.8, "avgB": 93.5, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 42.2, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 67.1, "avgB": 97.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-mythos-5-vs-glm-5-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-1.md", "modelA": { "slug": "glm-5-1", "canonicalModelKey": "glm-5-1", "model": "GLM-5.1", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "203K", "contextWindowTokens": 203000, "displayScore": 66.68, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.9, "upper": 77.46 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.68, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 19.319999999999993, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 21, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 65.4, "avgB": 87, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 61.3, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 52.3, "avgB": 68.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 62, "avgB": 97.6, "winner": null, "benchmarkCount": 7 } } }, { "slug": "claude-mythos-5-vs-claude-sonnet-4-6", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-sonnet-4-6.md", "modelA": { "slug": "claude-sonnet-4-6", "canonicalModelKey": "claude-sonnet-4-6", "model": "Claude Sonnet 4.6", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 64.47, "provisionalDisplayScore": 60, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 51.06, "upper": 77.88 }, "rankingEligible": true, "overallRank": 41, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.47, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 21.53, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 20, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 65.2, "avgB": 87, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 69.1, "avgB": 89.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77.4, "avgB": 93.5, "winner": "B", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 66, "avgB": 68.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 26.4, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-inkling", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-inkling", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-inkling.md", "modelA": { "slug": "inkling", "canonicalModelKey": "inkling", "model": "Inkling", "creator": "Thinking Machines Lab", "sourceType": "Open Weight", "reasoningType": "Hybrid", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 66.51, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 59.05, "upper": 73.97 }, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.51, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 19.489999999999995, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 69.4, "avgB": 87, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 68.6, "avgB": 89.7, "winner": "B", "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.5, "avgB": 93.5, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.6, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 79.8, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.1, "avgB": 97.6, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-minimax-m3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-minimax-m3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-minimax-m3.md", "modelA": { "slug": "minimax-m3", "canonicalModelKey": "minimax-m3", "model": "MiniMax M3", "creator": "MiniMax", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 68.17, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 62.45, "upper": 73.89 }, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 68.17, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 17.83, "winsA": 0, "winsB": 3, "comparableCategoryCount": 3, "benchmarkCountA": 22, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 72.3, "avgB": 87, "winner": "B", "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 72.2, "avgB": 89.7, "winner": "B", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 64.9, "avgB": 93.5, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 85.7, "avgB": 97.6, "winner": "B", "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-6-plus", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-6-plus.md", "modelA": { "slug": "qwen3-6-plus", "canonicalModelKey": "qwen3-6-plus", "model": "Qwen3.6 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 64.56, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.9, "upper": 74.23 }, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 64.56, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 21.439999999999998, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 43, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 61.6, "avgB": 87, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 70.3, "avgB": 89.7, "winner": "B", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 79.8, "avgB": 93.5, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 62, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 57.1, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.3, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 84.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": 60.5, "avgB": 97.6, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-mythos-5-vs-inkling-small", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-inkling-small", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-inkling-small.md", "modelA": { "slug": "inkling-small", "canonicalModelKey": "inkling-small", "model": "Inkling-Small", "creator": "Thinking Machines Lab", "sourceType": "Open Weight", "reasoningType": "Hybrid", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 63.52, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 57.93, "upper": 69.12 }, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 63.52, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 22.479999999999997, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 20, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 70.1, "avgB": 87, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 62.4, "avgB": 89.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.6, "avgB": 93.5, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 40.1, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.4, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 82.2, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 92.9, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-glm-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5.md", "modelA": { "slug": "glm-5", "canonicalModelKey": "glm-5", "model": "GLM-5", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 65.49, "provisionalDisplayScore": 56, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 53.78, "upper": 77.2 }, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 65.49, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.510000000000005, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 36, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 56.2, "avgB": 87, "winner": null, "benchmarkCount": 13 }, "coding": { "categoryLabel": "Coding", "avgA": 66.3, "avgB": 89.7, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 60.8, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 66.4, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 92.6, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 83.1, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": 56.3, "avgB": 97.6, "winner": null, "benchmarkCount": 9 } } }, { "slug": "claude-mythos-5-vs-gpt-5-4-mini", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-4-mini.md", "modelA": { "slug": "gpt-5-4-mini", "canonicalModelKey": "gpt-5-4-mini", "model": "GPT-5.4 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 56.69, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.17, "upper": 68.2 }, "rankingEligible": true, "overallRank": 96, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.69, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.310000000000002, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 14, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 65.7, "avgB": 87, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.6, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 47.8, "avgB": 68.5, "winner": "B", "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 21.7, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-5.md", "modelA": { "slug": "claude-opus-4-5", "canonicalModelKey": "claude-opus-4-5", "model": "Claude Opus 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 63.51, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.13, "upper": 77.89 }, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 63.51, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 22.490000000000002, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 45, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 62.6, "avgB": 87, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 71.7, "avgB": 89.7, "winner": "B", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 69.9, "avgB": 93.5, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 64.4, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 58.1, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 69.5, "avgB": null, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 85.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": 57.5, "avgB": 97.6, "winner": null, "benchmarkCount": 8 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-397b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-397b.md", "modelA": { "slug": "qwen3-5-397b", "canonicalModelKey": "qwen3-5-397b", "model": "Qwen3.5 397B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 57.75, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 46.24, "upper": 69.27 }, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 57.75, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 28.25, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 38, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 56.5, "avgB": 87, "winner": null, "benchmarkCount": 15 }, "coding": { "categoryLabel": "Coding", "avgA": 66.5, "avgB": 89.7, "winner": "B", "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 79.6, "avgB": 93.5, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 63.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.6, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 92.6, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 84.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": 90.6, "avgB": 97.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-mythos-5-vs-muse-glimmer-30b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-muse-glimmer-30b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-muse-glimmer-30b.md", "modelA": { "slug": "muse-glimmer-30b", "canonicalModelKey": "muse-glimmer-30b", "model": "Muse Glimmer 30B", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": null, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-glimmer-30b", "markdownUrl": "https://benchlm.ai/md/models/muse-glimmer-30b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 54, "scoreB": 86, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 14, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 65.9, "avgB": 87, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 57.8, "avgB": 89.7, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 75.7, "avgB": 93.5, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 77, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 94.7, "avgB": 97.6, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-mai-thinking-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mai-thinking-1.md", "modelA": { "slug": "mai-thinking-1", "canonicalModelKey": "mai-thinking-1", "model": "MAI-Thinking-1", "creator": "Microsoft", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 50.52, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.65, "upper": 60.39 }, "rankingEligible": true, "overallRank": 135, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 50.52, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35.48, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 14, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 46, "avgB": 87, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 65.5, "avgB": 89.7, "winner": "B", "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 72.5, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 85, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 89.7, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-gemini-3-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-pro.md", "modelA": { "slug": "gemini-3-pro", "canonicalModelKey": "gemini-3-pro", "model": "Gemini 3 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 67.25, "provisionalDisplayScore": 53, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.19, "upper": 79.3 }, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 67.25, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18.75, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 12, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": null, "avgB": 87, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 81.1, "avgB": 93.5, "winner": null, "benchmarkCount": 8 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 31.1, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": null, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 32.9, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-5-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-2.md", "modelA": { "slug": "gpt-5-2", "canonicalModelKey": "gpt-5-2", "model": "GPT-5.2", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 57.95, "provisionalDisplayScore": 52, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.94, "upper": 65.96 }, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 57.95, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 28.049999999999997, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 55.7, "avgB": 87, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 70.6, "avgB": 89.7, "winner": "B", "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 80.4, "avgB": 93.5, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 52.9, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 92.4, "avgB": 68.5, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 35.2, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-qwen3-6-27b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-6-27b.md", "modelA": { "slug": "qwen3-6-27b", "canonicalModelKey": "qwen3-6-27b", "model": "Qwen3.6-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.57, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.05, "upper": 65.08 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 53.57, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32.43, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 38, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 59.3, "avgB": 87, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 77.5, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.7, "avgB": 93.5, "winner": null, "benchmarkCount": 17 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.3, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 89.2, "avgB": 97.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-mythos-5-vs-ling-3-0-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ling-3-0-flash.md", "modelA": { "slug": "ling-3-0-flash", "canonicalModelKey": "ling-3-0-flash", "model": "Ling 3.0 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 53.62, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.1, "upper": 65.13 }, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 53.62, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32.38, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 17, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 72.2, "avgB": 87, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 47.1, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 31.1, "avgB": 68.5, "winner": "B", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 74.5, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 90.1, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-kimi-k2-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-kimi-k2-5.md", "modelA": { "slug": "kimi-k2-5", "canonicalModelKey": "kimi-k2-5", "model": "Kimi K2.5", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 58.74, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 50.13, "upper": 67.34 }, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 58.74, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 27.259999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 45, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 55, "avgB": 87, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 59.4, "avgB": 89.7, "winner": null, "benchmarkCount": 9 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 78.5, "avgB": 93.5, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 61, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 56.9, "avgB": 68.5, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 93.9, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 82.3, "avgB": null, "winner": null, "benchmarkCount": 3 }, "math": { "categoryLabel": "Mathematics", "avgA": 60.6, "avgB": 97.6, "winner": null, "benchmarkCount": 10 } } }, { "slug": "claude-mythos-5-vs-nemotron-3-ultra", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-nemotron-3-ultra.md", "modelA": { "slug": "nemotron-3-ultra", "canonicalModelKey": "nemotron-3-ultra-500b", "model": "Nemotron 3 Ultra", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 45.68, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 35.81, "upper": 55.55 }, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 45.68, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 40.32, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 19, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 51.3, "avgB": 87, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 58.3, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 61.9, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 53.8, "avgB": 68.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 81.7, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 83, "avgB": null, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-27b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-27b.md", "modelA": { "slug": "qwen3-5-27b", "canonicalModelKey": "qwen3-5-27b", "model": "Qwen3.5-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 59.7, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.77, "upper": 69.63 }, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 59.7, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.299999999999997, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 16, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 52, "avgB": 87, "winner": "B", "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 64.9, "avgB": 89.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 60.6, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 82.7, "avgB": 68.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 95, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 82.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-122b-a10b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-122b-a10b.md", "modelA": { "slug": "qwen3-5-122b-a10b", "canonicalModelKey": "qwen3-5-122b-a10b", "model": "Qwen3.5-122B-A10B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 59.49, "provisionalDisplayScore": 47, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 47.64, "upper": 71.34 }, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 59.49, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.509999999999998, "winsA": 0, "winsB": 2, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 56.4, "avgB": 87, "winner": "B", "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 72, "avgB": 89.7, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 77.2, "avgB": 93.5, "winner": "B", "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 60.2, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 83.6, "avgB": 68.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 93.4, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 82.2, "avgB": null, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-6-35b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-6-35b-a3b.md", "modelA": { "slug": "qwen3-6-35b-a3b", "canonicalModelKey": "qwen3-6-35b-a3b", "model": "Qwen3.6-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 51.32, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.81, "upper": 62.84 }, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 51.32, "scoreB": 86, "evidenceStatusA": "estimated", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 34.68, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 41, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 51.5, "avgB": 87, "winner": null, "benchmarkCount": 14 }, "coding": { "categoryLabel": "Coding", "avgA": 73.8, "avgB": 89.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 76.3, "avgB": 93.5, "winner": null, "benchmarkCount": 16 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.4, "avgB": 68.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 88.2, "avgB": 97.6, "winner": null, "benchmarkCount": 6 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-35b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-35b-a3b.md", "modelA": { "slug": "qwen3-5-35b-a3b", "canonicalModelKey": "qwen3-5-35b-a3b", "model": "Qwen3.5-35B-A3B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 56.09, "provisionalDisplayScore": 40, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 44.13, "upper": 68.06 }, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 56.09, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.909999999999997, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 16, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 51, "avgB": 87, "winner": "B", "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 60.6, "avgB": 89.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": 59, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 81.6, "avgB": 68.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": 91.9, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": 81, "avgB": null, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": null, "avgB": 97.6, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-4-7", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-4-7", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-4-7.md", "modelA": { "slug": "glm-4-7", "canonicalModelKey": "glm-4-7", "model": "GLM-4.7", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 60.62, "provisionalDisplayScore": 36, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 46.23, "upper": 75.01 }, "rankingEligible": true, "overallRank": 66, "url": "https://benchlm.ai/models/glm-4-7", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 60.62, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.380000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 13, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 45.7, "avgB": 87, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 75.4, "avgB": 89.7, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": null, "avgB": 93.5, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 51.8, "avgB": 68.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 1.8, "avgB": 97.6, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-gpt-5-4-nano", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-4-nano.md", "modelA": { "slug": "gpt-5-4-nano", "canonicalModelKey": "gpt-5-4-nano", "model": "GPT-5.4 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 66.39, "provisionalDisplayScore": 36, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55.08, "upper": 77.69 }, "rankingEligible": true, "overallRank": 32, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md" }, "modelB": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 66.39, "scoreB": 86, "evidenceStatusA": "supported", "evidenceStatusB": null, "overallWinner": "B", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 19.61, "winsA": 0, "winsB": 1, "comparableCategoryCount": 1, "benchmarkCountA": 13, "benchmarkCountB": 15, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 42.9, "avgB": 87, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": null, "avgB": 89.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 66.1, "avgB": 93.5, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 43.8, "avgB": 68.5, "winner": "B", "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 21, "avgB": 97.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-sakana-fugu-ultra", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-sakana-fugu-ultra", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-sakana-fugu-ultra.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "sakana-fugu-ultra", "canonicalModelKey": "sakana-fugu-ultra", "model": "Sakana Fugu-Ultra", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu-ultra", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-ultra.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 78, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 8, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 82.1, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 64.5, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 86.6, "winner": "A", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 93.6, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 95.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-4-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-4-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-4-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-4-pro", "canonicalModelKey": "gpt-5-4-pro", "model": "GPT-5.4 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1.05M", "contextWindowTokens": 1050000, "displayScore": 61.47, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.53, "upper": 78.41 }, "rankingEligible": true, "overallRank": 54, "url": "https://benchlm.ai/models/gpt-5-4-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 61.47, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24.53, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 89.3, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 94, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 83.3, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 58.7, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 46.9, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-holo3-35b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-holo3-35b-a3b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "holo3-35b-a3b", "canonicalModelKey": "holo3-35b-a3b", "model": "Holo3-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 74, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-35b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 74, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 12, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 82.6, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-swe-1-7", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-swe-1-7", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-swe-1-7.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "swe-1-7", "canonicalModelKey": "swe-1-7", "model": "SWE-1.7", "creator": "Cognition", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 73, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/swe-1-7", "markdownUrl": "https://benchlm.ai/md/models/swe-1-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 73, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 81.5, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-sakana-fugu", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-sakana-fugu", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-sakana-fugu.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "sakana-fugu", "canonicalModelKey": "sakana-fugu", "model": "Sakana Fugu", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 73, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 73, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 13, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 80.2, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 59.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 85.1, "winner": "A", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 86.6, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 95.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-grok-4-6", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4-6", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4-6.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4-6", "canonicalModelKey": "grok-4-6", "model": "Grok 4.6", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "500K", "contextWindowTokens": 500000, "displayScore": 62.98, "provisionalDisplayScore": 72, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.47, "upper": 74.5 }, "rankingEligible": true, "overallRank": 47, "url": "https://benchlm.ai/models/grok-4-6", "markdownUrl": "https://benchlm.ai/md/models/grok-4-6.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62.98, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23.020000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-5-3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-3.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "glm-5-3", "canonicalModelKey": "glm-5-3", "model": "GLM-5.3", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 62.41, "provisionalDisplayScore": 71, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 50.9, "upper": 73.93 }, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62.41, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23.590000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-exaone-4-0-32b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-exaone-4-0-32b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-exaone-4-0-32b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "exaone-4-0-32b", "canonicalModelKey": "exaone-4-0-32b", "model": "Exaone 4.0 32B", "creator": "LG AI Research", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/exaone-4-0-32b", "markdownUrl": "https://benchlm.ai/md/models/exaone-4-0-32b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 70, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 16, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 81.8, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-holo3-122b-a10b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-holo3-122b-a10b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "holo3-122b-a10b", "canonicalModelKey": "holo3-122b-a10b", "model": "Holo3-122B-A10B", "creator": "H Company", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/holo3-122b-a10b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 70, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 16, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 78.9, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-ornith-1-5-397b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-5-397b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-5-397b", "canonicalModelKey": "ornith-1-5-397b", "model": "Ornith-1.5-397B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 67.4, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 57.53, "upper": 77.27 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 67.4, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18.599999999999994, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 86.6, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 78, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 51.1, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-dots3-note-preview", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-dots3-note-preview.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "dots3-note-preview", "canonicalModelKey": "dots3-note-preview", "model": "dots3-note Preview", "creator": "Dots Studio", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 68.69, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 58.82, "upper": 78.55 }, "rankingEligible": true, "overallRank": 21, "url": "https://benchlm.ai/models/dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/models/dots3-note-preview.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 68.69, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 17.310000000000002, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 31, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 83.3, "winner": null, "benchmarkCount": 12 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 71.7, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 79.1, "winner": null, "benchmarkCount": 12 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 81.4, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 52.6, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 85.1, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gemini-3-6-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-6-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-3-6-flash", "canonicalModelKey": "gemini-3-6-flash", "model": "Gemini 3.6 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 75.06, "provisionalDisplayScore": 69, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.01, "upper": 80.1 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 75.06, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 10.939999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 83, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-hy4-preview", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-hy4-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-hy4-preview.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "hy4-preview", "canonicalModelKey": "hy4-preview", "model": "Hy4 preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 78.3, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 68.43, "upper": 88.17 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 78.3, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 7.700000000000003, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 28, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 16 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 65.7, "winner": null, "benchmarkCount": 10 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 66.2, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 60.4, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-ornith-1-0-397b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-0-397b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-0-397b", "canonicalModelKey": "ornith-1-0-397b", "model": "Ornith-1.0-397B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 68, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 77.5, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 74.6, "winner": "A", "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-5-3-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-3-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "glm-5-3-flash", "canonicalModelKey": "glm-5-3-flash", "model": "GLM-5.3-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 61.25, "provisionalDisplayScore": 67, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.73, "upper": 72.76 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 61.25, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24.75, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 13, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 74.7, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "apodex-1-1-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/apodex-1-1-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/apodex-1-1-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "apodex-1-1", "canonicalModelKey": "apodex-1-1", "model": "Apodex 1.1", "creator": "Apodex", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": 56.11, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 44.6, "upper": 67.63 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 56.11, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.89, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 10, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 77.7, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 56.1, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-qwen3-8-27b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-8-27b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-8-27b", "canonicalModelKey": "qwen3-8-27b", "model": "Qwen3.8-27B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 71.9, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 69.73, "upper": 74.07 }, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 71.9, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 14.099999999999994, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 28, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 84.3, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 61.7, "winner": null, "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 90.2, "winner": "A", "benchmarkCount": 11 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 38.7, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 79.5, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-grok-4-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4-5", "canonicalModelKey": "grok-4-5", "model": "Grok 4.5", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "500K", "contextWindowTokens": 500000, "displayScore": 74.9, "provisionalDisplayScore": 66, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 70.39, "upper": 79.41 }, "rankingEligible": true, "overallRank": 11, "url": "https://benchlm.ai/models/grok-4-5", "markdownUrl": "https://benchlm.ai/md/models/grok-4-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 74.9, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 11.099999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 10, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 83.3, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 64.7, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 52.6, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "celeris-1-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/celeris-1-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/celeris-1-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "celeris-1", "canonicalModelKey": "celeris-1", "model": "Celeris-1", "creator": "Celeris", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 63, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/celeris-1", "markdownUrl": "https://benchlm.ai/md/models/celeris-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 63, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 75.9, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 80.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gpt-5-3-codex", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-3-codex.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-3-codex", "canonicalModelKey": "gpt-5-3-codex", "model": "GPT-5.3 Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 65.6, "provisionalDisplayScore": 63, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 61.48, "upper": 69.72 }, "rankingEligible": true, "overallRank": 34, "url": "https://benchlm.ai/models/gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 65.6, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.400000000000006, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 71.4, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 67.2, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-deepseek-v3-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-deepseek-v3-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-deepseek-v3-2.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "deepseek-v3-2", "canonicalModelKey": "deepseek-v3-2", "model": "DeepSeek V3.2", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 54.64, "provisionalDisplayScore": 63, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 37.04, "upper": 72.24 }, "rankingEligible": true, "overallRank": 105, "url": "https://benchlm.ai/models/deepseek-v3-2", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 54.64, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 31.36, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 60.9, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 17.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-composer-2-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-composer-2-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-composer-2-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "composer-2-5", "canonicalModelKey": "composer-2-5", "model": "Composer 2.5", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 69.3, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "btl-4-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/btl-4-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/btl-4-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "btl-4", "canonicalModelKey": "btl-4", "model": "BTL-4", "creator": "Bad Theory Labs", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/btl-4", "markdownUrl": "https://benchlm.ai/md/models/btl-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 78.4, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-8-flash-next", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-8-flash-next.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-8-flash-next", "canonicalModelKey": "qwen3-8-flash-next", "model": "Qwen3.8-Flash-Next", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 60.91, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.39, "upper": 72.42 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.91, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.090000000000003, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 62.5, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 90.6, "winner": "A", "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 43.4, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 81.3, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-o1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-o1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-o1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "o1", "canonicalModelKey": "o1", "model": "o1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 48.18, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.66, "upper": 59.69 }, "rankingEligible": true, "overallRank": 146, "url": "https://benchlm.ai/models/o1", "markdownUrl": "https://benchlm.ai/md/models/o1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 48.18, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 37.82, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 75.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 92.2, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 9.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-mistral-medium-3-5-128b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mistral-medium-3-5-128b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mistral-medium-3-5-128b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mistral-medium-3-5-128b", "canonicalModelKey": "mistral-medium-3-5-128b", "model": "Mistral Medium 3.5 128B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-medium-3-5-128b", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3-5-128b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 61, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 77.6, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-zaya1-8b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-zaya1-8b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-zaya1-8b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "zaya1-8b", "canonicalModelKey": "zaya1-8b", "model": "ZAYA1-8B", "creator": "Zyphra", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 31.16, "provisionalDisplayScore": 60, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 21.29, "upper": 41.03 }, "rankingEligible": true, "overallRank": 210, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 31.16, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 54.84, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 73.6, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 64.1, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 80.4, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-composer-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-composer-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-composer-2.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "composer-2", "canonicalModelKey": "composer-2", "model": "Composer 2", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 58, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 28, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 61.7, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 58, "winner": null, "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-4-1-opus-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-4-1-opus-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-4-1-opus-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-4-1-opus", "canonicalModelKey": "claude-4-1-opus", "model": "Claude 4.1 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 45.05, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 42.05, "upper": 48.06 }, "rankingEligible": true, "overallRank": 170, "url": "https://benchlm.ai/models/claude-4-1-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 45.05, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 40.95, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 74.5, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-laguna-s-2-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-laguna-s-2-1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "laguna-s-2-1", "canonicalModelKey": "laguna-s-2-1", "model": "Laguna S 2.1", "creator": "Poolside", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-s-2-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 57, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 70.2, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 59.4, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-6-max-preview", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-6-max-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-6-max-preview.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-6-max-preview", "canonicalModelKey": "qwen3-6-max-preview", "model": "Qwen 3.6 Max (preview)", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 60.21, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 41.15, "upper": 79.27 }, "rankingEligible": true, "overallRank": 69, "url": "https://benchlm.ai/models/qwen3-6-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-max-preview.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.21, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.79, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 9, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 65.4, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 51, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 73.9, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 18.4, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-mimo-v2-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mimo-v2-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mimo-v2-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mimo-v2-flash", "canonicalModelKey": "mimo-v2-flash", "model": "MiMo-V2-Flash", "creator": "Xiaomi", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 53.25, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.29, "upper": 68.21 }, "rankingEligible": true, "overallRank": 115, "url": "https://benchlm.ai/models/mimo-v2-flash", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 53.25, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32.75, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 73.4, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 84.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "agents-a1-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/agents-a1-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/agents-a1-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "agents-a1", "canonicalModelKey": "agents-a1", "model": "Agents-A1", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.33, "upper": 71.07 }, "rankingEligible": true, "overallRank": 58, "url": "https://benchlm.ai/models/agents-a1", "markdownUrl": "https://benchlm.ai/md/models/agents-a1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 61.2, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 24.799999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 75.5, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 60.2, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 47.6, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 94.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-deepseek-v4-flash-0731", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-deepseek-v4-flash-0731", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-deepseek-v4-flash-0731.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "deepseek-v4-flash-0731", "canonicalModelKey": "deepseek-v4-flash-max", "model": "DeepSeek V4 Flash 0731", "creator": "DeepSeek", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepseek-v4-flash-0731", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-flash-0731.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 57, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 35, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 63.8, "winner": null, "benchmarkCount": 11 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 68.8, "winner": "A", "benchmarkCount": 13 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 55.3, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 94.8, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-ling-3-0-flash-fp8", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ling-3-0-flash-fp8.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ling-3-0-flash-fp8", "canonicalModelKey": "ling-3-0-flash-fp8", "model": "Ling 3.0 Flash FP8", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fp8", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fp8.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 57, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 40.4, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 84, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 73.4, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-mimo-v2-5-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mimo-v2-5-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mimo-v2-5-pro", "canonicalModelKey": "mimo-v2-5-pro", "model": "MiMo-V2.5-Pro", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 68.9, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 59.51, "upper": 78.29 }, "rankingEligible": true, "overallRank": 20, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 68.9, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 17.099999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 68.4, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 57.2, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 48, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemini-3-5-flash-lite", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-5-flash-lite.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-3-5-flash-lite", "canonicalModelKey": "gemini-3-5-flash-lite", "model": "Gemini 3.5 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.04, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 52.89, "upper": 77.19 }, "rankingEligible": true, "overallRank": 37, "url": "https://benchlm.ai/models/gemini-3-5-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-lite.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 65.04, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.959999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 63.4, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 54.2, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 72.2, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-4-sonnet-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-4-sonnet-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-4-sonnet-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-4-sonnet", "canonicalModelKey": "claude-4-sonnet", "model": "Claude 4 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 42.07, "provisionalDisplayScore": 56, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.83, "upper": 45.31 }, "rankingEligible": true, "overallRank": 187, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 42.07, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 43.93, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 72.7, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-lfm2-5-2-6b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-lfm2-5-2-6b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "lfm2-5-2-6b", "canonicalModelKey": "lfm2-5-2-6b", "model": "LFM2.5-2.6B", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.9, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.39, "upper": 54.42 }, "rankingEligible": true, "overallRank": 181, "url": "https://benchlm.ai/models/lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-2-6b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 42.9, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 43.1, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 59.2, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-kimi-k2-5-reasoning", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-kimi-k2-5-reasoning.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "kimi-k2-5-reasoning", "canonicalModelKey": "kimi-k2-5-reasoning", "model": "Kimi K2.5 (Reasoning)", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 60.12, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.61, "upper": 71.63 }, "rankingEligible": true, "overallRank": 70, "url": "https://benchlm.ai/models/kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5-reasoning.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.12, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.880000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 9, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 55, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 76.8, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 78.5, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 87.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gemini-3-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-3-flash", "canonicalModelKey": "gemini-3-flash", "model": "Gemini 3 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 59.74, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 39.96, "upper": 79.52 }, "rankingEligible": true, "overallRank": 73, "url": "https://benchlm.ai/models/gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 59.74, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.259999999999998, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 27.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-interfaze-beta", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-interfaze-beta", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-interfaze-beta.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "interfaze-beta", "canonicalModelKey": "interfaze-beta", "model": "Interfaze Beta", "creator": "Interfaze", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/interfaze-beta", "markdownUrl": "https://benchlm.ai/md/models/interfaze-beta.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 55, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 31, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 9, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 71.1, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 89.9, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-muse-spark", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-muse-spark", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-muse-spark.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "muse-spark", "canonicalModelKey": "muse-spark", "model": "Muse Spark", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 70.59, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 60.6, "upper": 80.58 }, "rankingEligible": true, "overallRank": 19, "url": "https://benchlm.ai/models/muse-spark", "markdownUrl": "https://benchlm.ai/md/models/muse-spark.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 70.59, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 15.409999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 24, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 59, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 67.8, "winner": "A", "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 82.5, "winner": null, "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 42.5, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 50.4, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 32.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-5-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-1", "canonicalModelKey": "gpt-5-1", "model": "GPT-5.1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 53.41, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.9, "upper": 64.93 }, "rankingEligible": true, "overallRank": 114, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 53.41, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32.59, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 26.4, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-ornith-1-0-35b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-0-35b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-0-35b", "canonicalModelKey": "ornith-1-0-35b", "model": "Ornith-1.0-35B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-35b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 54, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 32, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 64.2, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 65.9, "winner": "A", "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-grok-4-3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4-3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4-3.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4-3", "canonicalModelKey": "grok-4-3", "model": "Grok 4.3", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 63.82, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 52.9, "upper": 74.74 }, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 63.82, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 22.18, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-haiku-4-5-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-haiku-4-5-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-haiku-4-5-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-haiku-4-5", "canonicalModelKey": "claude-haiku-4-5", "model": "Claude Haiku 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 57.35, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.84, "upper": 68.86 }, "rankingEligible": true, "overallRank": 91, "url": "https://benchlm.ai/models/claude-haiku-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 57.35, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 28.65, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 73.3, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 4.9, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-mimo-v2-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mimo-v2-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mimo-v2-5", "canonicalModelKey": "mimo-v2-5", "model": "MiMo-V2.5", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 59.46, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 47.94, "upper": 70.97 }, "rankingEligible": true, "overallRank": 78, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 59.46, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.54, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 10, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 65.8, "winner": null, "benchmarkCount": 8 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 56.1, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 79, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-235b-2507", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-235b-2507.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-235b-2507", "canonicalModelKey": "qwen3-235b-2507", "model": "Qwen3 235B 2507", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 56.75, "provisionalDisplayScore": 53, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.23, "upper": 68.26 }, "rankingEligible": true, "overallRank": 95, "url": "https://benchlm.ai/models/qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 56.75, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.25, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 78.9, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": 79.4, "winner": null, "benchmarkCount": 2 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemini-3-pro-deep-think", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-pro-deep-think", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-pro-deep-think.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-3-pro-deep-think", "canonicalModelKey": "gemini-3-pro-deep-think", "model": "Gemini 3 Pro Deep Think", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 62.1, "provisionalDisplayScore": 52, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 50.59, "upper": 73.62 }, "rankingEligible": true, "overallRank": 52, "url": "https://benchlm.ai/models/gemini-3-pro-deep-think", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro-deep-think.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62.1, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23.9, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 45.1, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-o4-mini-high", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-o4-mini-high", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-o4-mini-high.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "o4-mini-high", "canonicalModelKey": "o4-mini-high", "model": "o4-mini (high)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 50.62, "provisionalDisplayScore": 52, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.11, "upper": 62.14 }, "rankingEligible": true, "overallRank": 132, "url": "https://benchlm.ai/models/o4-mini-high", "markdownUrl": "https://benchlm.ai/md/models/o4-mini-high.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 50.62, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35.38, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 20.2, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-mellum2-12b-a2-5b-thinking", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mellum2-12b-a2-5b-thinking", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mellum2-12b-a2-5b-thinking.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mellum2-12b-a2-5b-thinking", "canonicalModelKey": "mellum2-12b-a2-5b-thinking", "model": "Mellum2-12B-A2.5B-Thinking", "creator": "JetBrains", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 51, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mellum2-12b-a2-5b-thinking", "markdownUrl": "https://benchlm.ai/md/models/mellum2-12b-a2-5b-thinking.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 51, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 57.6, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 76.5, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-step-3-7-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-step-3-7-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "step-3-7-flash", "canonicalModelKey": "step-3-7-flash", "model": "Step 3.7 Flash", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 50.83, "provisionalDisplayScore": 51, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.31, "upper": 62.34 }, "rankingEligible": true, "overallRank": 127, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 50.83, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35.17, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 66.4, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 56.3, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-ornith-1-5-35b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-5-35b-a3b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-5-35b-a3b", "canonicalModelKey": "ornith-1-5-35b-a3b", "model": "Ornith-1.5-35B-A3B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 47.9, "provisionalDisplayScore": 51, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.03, "upper": 57.77 }, "rankingEligible": true, "overallRank": 149, "url": "https://benchlm.ai/models/ornith-1-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-35b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.9, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.1, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 67.6, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 71.5, "winner": "A", "benchmarkCount": 8 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 34.2, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-o3-mini", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-o3-mini", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-o3-mini.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "o3-mini", "canonicalModelKey": "o3-mini", "model": "o3-mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 46.69, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 31.65, "upper": 61.73 }, "rankingEligible": true, "overallRank": 158, "url": "https://benchlm.ai/models/o3-mini", "markdownUrl": "https://benchlm.ai/md/models/o3-mini.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 46.69, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 39.31, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 49.3, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 77.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 93.9, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-soofi-s-30b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-soofi-s-30b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-soofi-s-30b-a3b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "soofi-s-30b-a3b", "canonicalModelKey": "soofi-s-30b-a3b", "model": "Soofi S 30B-A3B", "creator": "Soofi Project", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/soofi-s-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/soofi-s-30b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 50, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 36, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 49.9, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-lfm2-5-8b-a1b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-lfm2-5-8b-a1b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "lfm2-5-8b-a1b", "canonicalModelKey": "lfm2-5-8b-a1b", "model": "LFM2.5-8B-A1B", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 41.78, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.27, "upper": 53.3 }, "rankingEligible": true, "overallRank": 188, "url": "https://benchlm.ai/models/lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-8b-a1b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 41.78, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 44.22, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 68.8, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 50, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-plus", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-plus.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-5-plus", "canonicalModelKey": "qwen3-5-plus", "model": "Qwen3.5 Plus", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 47.79, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.82, "upper": 61.76 }, "rankingEligible": true, "overallRank": 150, "url": "https://benchlm.ai/models/qwen3-5-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.79, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.21, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 16.3, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-kimi-k2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-kimi-k2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-kimi-k2.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "kimi-k2", "canonicalModelKey": "kimi-k2", "model": "Kimi K2", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 26.24, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.05, "upper": 36.43 }, "rankingEligible": true, "overallRank": 213, "url": "https://benchlm.ai/models/kimi-k2", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 26.24, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 59.760000000000005, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 16.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-minimax-m2-7", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-minimax-m2-7.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "minimax-m2-7", "canonicalModelKey": "minimax-m2-7", "model": "MiniMax M2.7", "creator": "MiniMax", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 62.85, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 55, "upper": 70.7 }, "rankingEligible": true, "overallRank": 49, "url": "https://benchlm.ai/models/minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-7.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 62.85, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 23.15, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 57, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 53.3, "winner": null, "benchmarkCount": 11 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-grok-4", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4", "canonicalModelKey": "grok-4", "model": "Grok 4", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.42, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 48.8, "upper": 70.04 }, "rankingEligible": true, "overallRank": 79, "url": "https://benchlm.ai/models/grok-4", "markdownUrl": "https://benchlm.ai/md/models/grok-4.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 59.42, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.58, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 15.3, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-o3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-o3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-o3.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "o3", "canonicalModelKey": "o3", "model": "o3", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 46.82, "provisionalDisplayScore": 49, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 43.88, "upper": 49.76 }, "rankingEligible": true, "overallRank": 157, "url": "https://benchlm.ai/models/o3", "markdownUrl": "https://benchlm.ai/md/models/o3.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 46.82, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 39.18, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 14.5, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-granite-4-2-8b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-granite-4-2-8b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "granite-4-2-8b", "canonicalModelKey": "granite-4-2-8b", "model": "Granite 4.2 8B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 46.32, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.8, "upper": 57.83 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 46.32, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 39.68, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 14, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 36.5, "winner": null, "benchmarkCount": 7 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 72.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 79.3, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-nemotron-3-nano-omni-30b-a3b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-nemotron-3-nano-omni-30b-a3b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-nemotron-3-nano-omni-30b-a3b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "nemotron-3-nano-omni-30b-a3b", "canonicalModelKey": "nemotron-3-nano-omni-30b-a3b", "model": "Nemotron 3 Nano Omni 30B A3B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 44.49, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.98, "upper": 56 }, "rankingEligible": true, "overallRank": 172, "url": "https://benchlm.ai/models/nemotron-3-nano-omni-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-omni-30b-a3b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 44.49, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 41.51, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 32, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 76.3, "winner": "A", "benchmarkCount": 9 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 76.3, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 74.2, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gpt-4-1-nano", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-4-1-nano.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-4-1-nano", "canonicalModelKey": "gpt-4-1-nano", "model": "GPT-4.1 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 42.38, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.86, "upper": 53.89 }, "rankingEligible": true, "overallRank": 183, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 42.38, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 43.62, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 50.3, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 83.2, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 1, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-pokee-isaac-28b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-pokee-isaac-28b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-pokee-isaac-28b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "pokee-isaac-28b", "canonicalModelKey": "pokee-isaac-28b", "model": "Pokee-Isaac 28B", "creator": "Pokee AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "10M", "contextWindowTokens": 10000000, "displayScore": null, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pokee-isaac-28b", "markdownUrl": "https://benchlm.ai/md/models/pokee-isaac-28b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 48, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 9 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 60.7, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemma-4-26b-a4b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemma-4-26b-a4b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemma-4-26b-a4b", "canonicalModelKey": "gemma-4-26b-a4b", "model": "Gemma 4 26B A4B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 57.12, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 39.05, "upper": 75.18 }, "rankingEligible": true, "overallRank": 93, "url": "https://benchlm.ai/models/gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-26b-a4b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 57.12, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 28.880000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 73.8, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 43.4, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-claude-sonnet-4-5", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-sonnet-4-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-sonnet-4-5", "canonicalModelKey": "claude-sonnet-4-5", "model": "Claude Sonnet 4.5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 54.48, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.96, "upper": 65.99 }, "rankingEligible": true, "overallRank": 106, "url": "https://benchlm.ai/models/claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 54.48, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 31.520000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 11, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 55.4, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 77.2, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 13.6, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 83.4, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 11.2, "winner": null, "benchmarkCount": 4 } } }, { "slug": "claude-mythos-5-vs-gemini-3-1-flash-lite", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-3-1-flash-lite.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-3-1-flash-lite", "canonicalModelKey": "gemini-3-1-flash-lite", "model": "Gemini 3.1 Flash-Lite", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.82, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.61, "upper": 77.03 }, "rankingEligible": true, "overallRank": 129, "url": "https://benchlm.ai/models/gemini-3-1-flash-lite", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-lite.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 50.82, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35.18, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 73.2, "winner": "A", "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-hy3-preview", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-hy3-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-hy3-preview.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "hy3-preview", "canonicalModelKey": "hy3-preview", "model": "Hy3 Preview", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 43.71, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.84, "upper": 53.58 }, "rankingEligible": true, "overallRank": 176, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 43.71, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 42.29, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 54.4, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 74.4, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 87.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-zaya1-74b-preview", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-zaya1-74b-preview.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "zaya1-74b-preview", "canonicalModelKey": "zaya1-74b-preview", "model": "ZAYA1-74B-Preview", "creator": "Zyphra", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/models/zaya1-74b-preview.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 46, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 40, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 53.2, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 66.1, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 76.4, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-qwen3-235b-2507-reasoning", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-235b-2507-reasoning", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-235b-2507-reasoning.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-235b-2507-reasoning", "canonicalModelKey": "qwen3-235b-2507-reasoning", "model": "Qwen3 235B 2507 (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.77, "provisionalDisplayScore": 45, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 47.26, "upper": 70.29 }, "rankingEligible": true, "overallRank": 83, "url": "https://benchlm.ai/models/qwen3-235b-2507-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507-reasoning.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 58.77, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 27.229999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 6.4, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-4-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-4-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-4-1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-4-1", "canonicalModelKey": "gpt-4-1", "model": "GPT-4.1", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.83, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 30.52, "upper": 71.13 }, "rankingEligible": true, "overallRank": 128, "url": "https://benchlm.ai/models/gpt-4-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 50.83, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 35.17, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 54.6, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 66.3, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 87.4, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 4.1, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-4-1-mini", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-4-1-mini.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-4-1-mini", "canonicalModelKey": "gpt-4-1-mini", "model": "GPT-4.1 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 44.4, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.89, "upper": 55.92 }, "rankingEligible": true, "overallRank": 173, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 44.4, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 41.6, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 23.6, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 64.2, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 88.5, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 4.5, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-grok-4-20-beta", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4-20-beta.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4-20-beta", "canonicalModelKey": "grok-4-20-beta", "model": "Grok 4.20", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 55.42, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.52, "upper": 72.32 }, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 55.42, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 30.58, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 18, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 47.1, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 67.1, "winner": "A", "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 70.1, "winner": null, "benchmarkCount": 7 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 53.3, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemini-2-5-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-2-5-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-2-5-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-2-5-flash", "canonicalModelKey": "gemini-2-5-flash", "model": "Gemini 2.5 Flash", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 47.56, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.4, "upper": 70.73 }, "rankingEligible": true, "overallRank": 153, "url": "https://benchlm.ai/models/gemini-2-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.56, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.44, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 4.7, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-5-flash", "canonicalModelKey": "qwen3-5-flash", "model": "Qwen3.5 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 47.56, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 24.54, "upper": 70.59 }, "rankingEligible": true, "overallRank": 152, "url": "https://benchlm.ai/models/qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.56, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.44, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 4.7, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-mellum2-12b-a2-5b-instruct", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mellum2-12b-a2-5b-instruct", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mellum2-12b-a2-5b-instruct.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mellum2-12b-a2-5b-instruct", "canonicalModelKey": "mellum2-12b-a2-5b-instruct", "model": "Mellum2-12B-A2.5B-Instruct", "creator": "JetBrains", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 44, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mellum2-12b-a2-5b-instruct", "markdownUrl": "https://benchlm.ai/md/models/mellum2-12b-a2-5b-instruct.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 44, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 42, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 40.9, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 75.8, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-laguna-m-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-laguna-m-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-laguna-m-1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "laguna-m-1", "canonicalModelKey": "laguna-m-1", "model": "Laguna M.1", "creator": "Poolside", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 43, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 43, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 45.8, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 64.8, "winner": "A", "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-4-6", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-4-6", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-4-6.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "glm-4-6", "canonicalModelKey": "glm-4-6", "model": "GLM-4.6", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 54.36, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 35.64, "upper": 73.07 }, "rankingEligible": true, "overallRank": 107, "url": "https://benchlm.ai/models/glm-4-6", "markdownUrl": "https://benchlm.ai/md/models/glm-4-6.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 54.36, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 31.64, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 3, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 3.4, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gemma-4-31b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemma-4-31b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemma-4-31b", "canonicalModelKey": "gemma-4-31b", "model": "Gemma 4 31B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 60.08, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 43.34, "upper": 76.82 }, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.08, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 8, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 41.6, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 76.9, "winner": null, "benchmarkCount": 4 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 52.9, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-grok-3-beta", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-3-beta", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-3-beta.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-3-beta", "canonicalModelKey": "grok-3-beta", "model": "Grok 3 [Beta]", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.33, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 8.65, "upper": 72 }, "rankingEligible": true, "overallRank": 197, "url": "https://benchlm.ai/models/grok-3-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-3-beta.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 40.33, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 45.67, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 2, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 2.8, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-deepseek-v3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-deepseek-v3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-deepseek-v3.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "deepseek-v3", "canonicalModelKey": "deepseek-v3", "model": "DeepSeek V3", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 44.38, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 25.19, "upper": 63.57 }, "rankingEligible": true, "overallRank": 174, "url": "https://benchlm.ai/models/deepseek-v3", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 44.38, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 41.62, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 38.9, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 72.7, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 86.1, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 1.7, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-3-5-sonnet-vs-claude-mythos-5", "url": "https://benchlm.ai/compare/claude-3-5-sonnet-vs-claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/compare/claude-3-5-sonnet-vs-claude-mythos-5.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-3-5-sonnet", "canonicalModelKey": "claude-3-5-sonnet", "model": "Claude 3.5 Sonnet", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 48.36, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.85, "upper": 59.87 }, "rankingEligible": true, "overallRank": 144, "url": "https://benchlm.ai/models/claude-3-5-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-3-5-sonnet.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 48.36, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 37.64, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 49, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 59.4, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 1.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-gpt-4o", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-4o", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-4o.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-4o", "canonicalModelKey": "gpt-4o", "model": "GPT-4o", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.96, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.58, "upper": 60.34 }, "rankingEligible": true, "overallRank": 191, "url": "https://benchlm.ai/models/gpt-4o", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 40.96, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 45.04, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 0.3, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-llama-4-scout", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-llama-4-scout", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-llama-4-scout.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "llama-4-scout", "canonicalModelKey": "llama-4-scout", "model": "Llama 4 Scout", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "10M", "contextWindowTokens": 10000000, "displayScore": 39.55, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 20.68, "upper": 58.41 }, "rankingEligible": true, "overallRank": 200, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 39.55, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 46.45, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-llama-4-maverick", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-llama-4-maverick.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "llama-4-maverick", "canonicalModelKey": "llama-4-maverick", "model": "Llama 4 Maverick", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 22.76, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 15.17, "upper": 30.34 }, "rankingEligible": true, "overallRank": 215, "url": "https://benchlm.ai/models/llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/models/llama-4-maverick.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 22.76, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 63.239999999999995, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 0.7, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-ling-2-6-flash", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ling-2-6-flash.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ling-2-6-flash", "canonicalModelKey": "ling-2-6-flash", "model": "Ling 2.6 Flash", "creator": "InclusionAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 44.18, "provisionalDisplayScore": 42, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.66, "upper": 55.69 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 44.18, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 41.82, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gemma-4-12b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemma-4-12b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemma-4-12b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemma-4-12b", "canonicalModelKey": "gemma-4-12b", "model": "Gemma 4 12B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 47.33, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 35.82, "upper": 58.85 }, "rankingEligible": true, "overallRank": 154, "url": "https://benchlm.ai/models/gemma-4-12b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-12b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.33, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.67, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 12, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 69.1, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": 43.4, "winner": null, "benchmarkCount": 2 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 77.5, "winner": null, "benchmarkCount": 6 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 77.5, "winner": null, "benchmarkCount": 2 } } }, { "slug": "claude-mythos-5-vs-gemini-2-5-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gemini-2-5-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gemini-2-5-pro", "canonicalModelKey": "gemini-2-5-pro", "model": "Gemini 2.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 56.77, "provisionalDisplayScore": 41, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 38.38, "upper": 75.17 }, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 56.77, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 29.229999999999997, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 63.8, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 27.4, "winner": "A", "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 11.6, "winner": null, "benchmarkCount": 3 } } }, { "slug": "claude-mythos-5-vs-minicpm5-1b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-minicpm5-1b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-minicpm5-1b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "minicpm5-1b", "canonicalModelKey": "minicpm5-1b", "model": "MiniCPM5-1B", "creator": "OpenBMB", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": 11.08, "provisionalDisplayScore": 40, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 1.21, "upper": 20.95 }, "rankingEligible": true, "overallRank": 225, "url": "https://benchlm.ai/models/minicpm5-1b", "markdownUrl": "https://benchlm.ai/md/models/minicpm5-1b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 11.08, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 74.92, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 14, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 44, "winner": null, "benchmarkCount": 7 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 58.5, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": 33.1, "winner": null, "benchmarkCount": 5 } } }, { "slug": "claude-mythos-5-vs-ornith-1-0-9b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-0-9b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-0-9b", "canonicalModelKey": "ornith-1-0-9b", "model": "Ornith-1.0-9B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 40, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-9b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 40, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 46, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 43.1, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 59.2, "winner": "A", "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-laguna-xs-2", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-laguna-xs-2.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "laguna-xs-2", "canonicalModelKey": "laguna-xs-2", "model": "Laguna XS.2", "creator": "Poolside", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 39, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 39, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 47, "winsA": 1, "winsB": 0, "comparableCategoryCount": 1, "benchmarkCountA": 15, "benchmarkCountB": 5, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 35.7, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 60.8, "winner": "A", "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-ornith-1-5-9b", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-ornith-1-5-9b.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "ornith-1-5-9b", "canonicalModelKey": "ornith-1-5-9b", "model": "Ornith-1.5-9B", "creator": "Ornith AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 37.33, "provisionalDisplayScore": 39, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 27.46, "upper": 47.2 }, "rankingEligible": true, "overallRank": 205, "url": "https://benchlm.ai/models/ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-9b.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 37.33, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 48.67, "winsA": 2, "winsB": 0, "comparableCategoryCount": 2, "benchmarkCountA": 15, "benchmarkCountB": 16, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 56.4, "winner": null, "benchmarkCount": 10 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 61.7, "winner": "A", "benchmarkCount": 6 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 29.1, "winner": "A", "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-nemotron-3-5-lightning-30b-a3b-nvfp4", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-nemotron-3-5-lightning-30b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-nemotron-3-5-lightning-30b-a3b-nvfp4.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "nemotron-3-5-lightning-30b-a3b-nvfp4", "canonicalModelKey": "nemotron-3-5-lightning-30b-a3b-nvfp4", "model": "Nemotron 3.5 Lightning 30B A3B NVFP4", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 26.55, "provisionalDisplayScore": 37, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 16.68, "upper": 36.42 }, "rankingEligible": true, "overallRank": 212, "url": "https://benchlm.ai/models/nemotron-3-5-lightning-30b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-5-lightning-30b-a3b-nvfp4.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 26.55, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 59.45, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 13, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": 29.1, "winner": null, "benchmarkCount": 6 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 42.1, "winner": null, "benchmarkCount": 5 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 80.5, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 72.9, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-lfm2-5-vl-450m", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-lfm2-5-vl-450m", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-lfm2-5-vl-450m.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "lfm2-5-vl-450m", "canonicalModelKey": "lfm2-5-vl-450m", "model": "LFM2.5-VL-450M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 35, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 35, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 51, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 7, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 6 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 20.5, "winner": null, "benchmarkCount": 4 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 61.2, "winner": null, "benchmarkCount": 1 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-command-a-plus", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-command-a-plus", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-command-a-plus.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "command-a-plus", "canonicalModelKey": "command-a-plus", "model": "Command A+", "creator": "Cohere", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 47.57, "provisionalDisplayScore": 31, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.06, "upper": 59.09 }, "rankingEligible": true, "overallRank": 151, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 47.57, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 38.43, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": 59.3, "winner": null, "benchmarkCount": 5 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-lfm2-5-230m", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-lfm2-5-230m", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-lfm2-5-230m.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "lfm2-5-230m", "canonicalModelKey": "lfm2-5-230m", "model": "LFM2.5-230M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 31, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-230m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-230m.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 31, "evidenceStatusA": null, "evidenceStatusB": null, "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 55, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 6, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": 21.2, "winner": null, "benchmarkCount": 5 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": 50.1, "winner": null, "benchmarkCount": 2 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-claude-opus-4-6-thinking", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-claude-opus-4-6-thinking", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-claude-opus-4-6-thinking.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "claude-opus-4-6-thinking", "canonicalModelKey": "claude-opus-4-6-thinking", "model": "Claude Opus 4.6 (Adaptive)", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 65.03, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 53.52, "upper": 76.55 }, "rankingEligible": true, "overallRank": 38, "url": "https://benchlm.ai/models/claude-opus-4-6-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6-thinking.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 65.03, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.97, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-grok-4-1", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-grok-4-1", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-grok-4-1.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "grok-4-1", "canonicalModelKey": "grok-4-1", "model": "Grok 4.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 60.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.22, "upper": 72.24 }, "rankingEligible": true, "overallRank": 65, "url": "https://benchlm.ai/models/grok-4-1", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.73, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.270000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-hy3", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-hy3", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-hy3.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "hy3", "canonicalModelKey": "hy3", "model": "Hy3", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 67.65, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 58.81, "upper": 76.49 }, "rankingEligible": true, "overallRank": 24, "url": "https://benchlm.ai/models/hy3", "markdownUrl": "https://benchlm.ai/md/models/hy3.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 67.65, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18.349999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-5-reasoning", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-reasoning.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "glm-5-reasoning", "canonicalModelKey": "glm-5-reasoning", "model": "GLM-5 (Reasoning)", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 60.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 49.04, "upper": 72.07 }, "rankingEligible": true, "overallRank": 67, "url": "https://benchlm.ai/models/glm-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/glm-5-reasoning.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.55, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.450000000000003, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 4 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-glm-5-turbo", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-glm-5-turbo", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-glm-5-turbo.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "glm-5-turbo", "canonicalModelKey": "glm-5-turbo", "model": "GLM-5-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 65.82, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.91, "upper": 76.74 }, "rankingEligible": true, "overallRank": 33, "url": "https://benchlm.ai/models/glm-5-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5-turbo.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 65.82, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 20.180000000000007, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 1, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 5 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-qwen3-5-397b-reasoning", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-qwen3-5-397b-reasoning", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-qwen3-5-397b-reasoning.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "qwen3-5-397b-reasoning", "canonicalModelKey": "qwen3-5-397b-reasoning", "model": "Qwen3.5 397B (Reasoning)", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 60.27, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.76, "upper": 71.78 }, "rankingEligible": true, "overallRank": 68, "url": "https://benchlm.ai/models/qwen3-5-397b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b-reasoning.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 60.27, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 25.729999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-mimo-v2-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-mimo-v2-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-mimo-v2-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "mimo-v2-pro", "canonicalModelKey": "mimo-v2-pro", "model": "MiMo-V2-Pro", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 66.65, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 57.84, "upper": 75.46 }, "rankingEligible": true, "overallRank": 30, "url": "https://benchlm.ai/models/mimo-v2-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 66.65, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 19.349999999999994, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 4, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 7 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": 78, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-2-instant", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-2-instant", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-2-instant.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-2-instant", "canonicalModelKey": "gpt-5-2-instant", "model": "GPT-5.2 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.77, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.26, "upper": 71.29 }, "rankingEligible": true, "overallRank": 72, "url": "https://benchlm.ai/models/gpt-5-2-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-instant.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 59.77, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.229999999999997, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-2-pro", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-2-pro", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-2-pro.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-2-pro", "canonicalModelKey": "gpt-5-2-pro", "model": "GPT-5.2 Pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 67.19, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 56.87, "upper": 77.52 }, "rankingEligible": true, "overallRank": 27, "url": "https://benchlm.ai/models/gpt-5-2-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-pro.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 67.19, "evidenceStatusA": null, "evidenceStatusB": "supported", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 18.810000000000002, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } }, { "slug": "claude-mythos-5-vs-gpt-5-3-instant", "url": "https://benchlm.ai/compare/claude-mythos-5-vs-gpt-5-3-instant", "markdownUrl": "https://benchlm.ai/md/compare/claude-mythos-5-vs-gpt-5-3-instant.md", "modelA": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "modelB": { "slug": "gpt-5-3-instant", "canonicalModelKey": "gpt-5-3-instant", "model": "GPT-5.3 Instant", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 59.67, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 48.15, "upper": 71.18 }, "rankingEligible": true, "overallRank": 75, "url": "https://benchlm.ai/models/gpt-5-3-instant", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-instant.md" }, "rankingMode": "bench-align-v5", "scoreA": 86, "scoreB": 59.67, "evidenceStatusA": null, "evidenceStatusB": "estimated", "overallWinner": "A", "winner": { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md" }, "scoreDiff": 26.33, "winsA": 0, "winsB": 0, "comparableCategoryCount": 0, "benchmarkCountA": 15, "benchmarkCountB": 0, "categoryResults": { "agentic": { "categoryLabel": "Agentic", "avgA": 87, "avgB": null, "winner": null, "benchmarkCount": 4 }, "coding": { "categoryLabel": "Coding", "avgA": 89.7, "avgB": null, "winner": null, "benchmarkCount": 3 }, "multimodalGrounded": { "categoryLabel": "Multimodal & Grounded", "avgA": 93.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "reasoning": { "categoryLabel": "Reasoning", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "knowledge": { "categoryLabel": "Knowledge", "avgA": 68.5, "avgB": null, "winner": null, "benchmarkCount": 3 }, "instructionFollowing": { "categoryLabel": "Instruction Following", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 0 }, "multilingual": { "categoryLabel": "Multilingual", "avgA": null, "avgB": null, "winner": null, "benchmarkCount": 1 }, "math": { "categoryLabel": "Mathematics", "avgA": 97.6, "avgB": null, "winner": null, "benchmarkCount": 1 } } } ] }