{ "schemaVersion": "1.0", "name": "BenchLM leaderboards", "description": "Overall and category leaderboards derived from the public BenchLM ranking logic.", "canonicalUrl": "https://benchlm.ai/data/leaderboard.json", "generatedAt": "2026-09-02T00:50:21.010Z", "sourceLastUpdated": "September 1, 2026", "sourceFiles": [ "src/data/benchmarks.json", "src/data/provenance.js", "src/data/modelReleaseMetadata.js", "src/data/scoring.js" ], "counts": { "overall": 225, "categories": { "agentic": 142, "coding": 146, "reasoning": 2, "multimodalGrounded": 35, "knowledge": 56, "multilingual": 12, "instructionFollowing": 43, "math": 7 } }, "rankingMode": "bench-align-v5", "items": [ { "rank": 1, "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", "score": 82.74, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 2, "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", "score": 82.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 3, "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", "score": 82.34, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 59, "scoreConfidence": 3 }, { "rank": 4, "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", "score": 81.69, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 3 }, { "rank": 5, "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", "score": 79.92, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 30, "scoreConfidence": 2 }, { "rank": 6, "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", "score": 78.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 7, "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", "score": 78.3, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 8, "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", "score": 76.52, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 19, "scoreConfidence": 2 }, { "rank": 9, "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", "score": 75.96, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 10, "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", "score": 75.06, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 11, "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", "score": 74.9, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 12, "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", "score": 73.04, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 32, "scoreConfidence": 3 }, { "rank": 13, "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", "score": 72.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 14, "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", "score": 72.5, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 15, "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", "score": 72.23, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 16, "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", "score": 72.21, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 17, "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", "score": 71.9, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 18, "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", "score": 71.27, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 19, "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", "score": 70.59, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 20, "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", "score": 68.9, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 21, "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", "score": 68.69, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 26, "scoreConfidence": 3 }, { "rank": 22, "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", "score": 68.17, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 23, "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", "score": 67.89, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 24, "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", "score": 67.65, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 25, "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", "score": 67.4, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 26, "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", "score": 67.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 27, "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", "score": 67.19, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 28, "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", "score": 66.93, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 29, "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", "score": 66.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 30, "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", "score": 66.65, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 31, "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", "score": 66.51, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 32, "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", "score": 66.39, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 33, "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", "score": 65.82, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 34, "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", "score": 65.6, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 65.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 36, "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", "score": 65.45, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 37, "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", "score": 65.04, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 38, "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", "score": 65.03, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 39, "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", "score": 64.72, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 40, "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", "score": 64.56, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 41, "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", "score": 64.47, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 42, "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", "score": 64.35, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 43, "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", "score": 64.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 44, "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", "score": 63.82, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 45, "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", "score": 63.52, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 46, "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", "score": 63.51, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 47, "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", "score": 62.98, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 48, "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", "score": 62.88, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 49, "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", "score": 62.85, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 1 }, { "rank": 50, "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", "score": 62.41, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 51, "slug": "mimo-v2-omni", "canonicalModelKey": "mimo-v2-omni", "model": "MiMo-V2-Omni", "creator": "Xiaomi", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 62.17, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 51.23, "upper": 73.1 }, "rankingEligible": true, "overallRank": 51, "url": "https://benchlm.ai/models/mimo-v2-omni", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-omni.md", "score": 62.17, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 52, "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", "score": 62.1, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 53, "slug": "glm-5v-turbo", "canonicalModelKey": "glm-5v-turbo", "model": "GLM-5V-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 62.09, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 50.56, "upper": 73.63 }, "rankingEligible": true, "overallRank": 53, "url": "https://benchlm.ai/models/glm-5v-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5v-turbo.md", "score": 62.09, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 54, "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", "score": 61.47, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 55, "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", "score": 61.29, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 56, "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", "score": 61.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 57, "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", "score": 61.22, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 58, "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", "score": 61.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 59, "slug": "agents-a1-f16-gguf", "canonicalModelKey": "agents-a1-f16-gguf", "model": "Agents-A1-F16-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.33, "upper": 71.07 }, "rankingEligible": true, "overallRank": 59, "url": "https://benchlm.ai/models/agents-a1-f16-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-f16-gguf.md", "score": 61.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 60, "slug": "agents-a1-fp8", "canonicalModelKey": "agents-a1-fp8", "model": "Agents-A1-FP8", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.33, "upper": 71.07 }, "rankingEligible": true, "overallRank": 60, "url": "https://benchlm.ai/models/agents-a1-fp8", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-fp8.md", "score": 61.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 61, "slug": "agents-a1-q4-k-m-gguf", "canonicalModelKey": "agents-a1-q4-k-m-gguf", "model": "Agents-A1-Q4_K_M-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.33, "upper": 71.07 }, "rankingEligible": true, "overallRank": 61, "url": "https://benchlm.ai/models/agents-a1-q4-k-m-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-q4-k-m-gguf.md", "score": 61.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 62, "slug": "agents-a1-q8-0-gguf", "canonicalModelKey": "agents-a1-q8-0-gguf", "model": "Agents-A1-Q8_0-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 51.33, "upper": 71.07 }, "rankingEligible": true, "overallRank": 62, "url": "https://benchlm.ai/models/agents-a1-q8-0-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-q8-0-gguf.md", "score": 61.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 63, "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", "score": 61, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 64, "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", "score": 60.91, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 65, "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", "score": 60.73, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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", "score": 60.62, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 67, "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", "score": 60.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 68, "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", "score": 60.27, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 69, "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", "score": 60.21, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 70, "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", "score": 60.12, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 71, "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", "score": 60.08, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 72, "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", "score": 59.77, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 73, "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", "score": 59.74, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 74, "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", "score": 59.7, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 75, "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", "score": 59.67, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 76, "slug": "grok-4-1-fast-reasoning", "canonicalModelKey": "grok-4-1-fast-reasoning", "model": "Grok 4.1 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 59.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 45.62, "upper": 73.47 }, "rankingEligible": true, "overallRank": 76, "url": "https://benchlm.ai/models/grok-4-1-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast-reasoning.md", "score": 59.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 77, "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", "score": 59.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 78, "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", "score": 59.46, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 79, "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", "score": 59.42, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 80, "slug": "gpt-5-high", "canonicalModelKey": "gpt-5-high", "model": "GPT-5 (high)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.4, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 47.88, "upper": 70.91 }, "rankingEligible": true, "overallRank": 80, "url": "https://benchlm.ai/models/gpt-5-high", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-high.md", "score": 59.4, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 81, "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", "score": 59.09, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 82, "slug": "deepseek-v3-2-thinking", "canonicalModelKey": "deepseek-v3-2-thinking", "model": "DeepSeek V3.2 (Thinking)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.89, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 47.37, "upper": 70.4 }, "rankingEligible": true, "overallRank": 82, "url": "https://benchlm.ai/models/deepseek-v3-2-thinking", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2-thinking.md", "score": 58.89, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 83, "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", "score": 58.77, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 84, "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", "score": 58.74, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 85, "slug": "minimax-m2-5", "canonicalModelKey": "minimax-m2-5", "model": "MiniMax M2.5", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.49, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.9, "upper": 67.09 }, "rankingEligible": true, "overallRank": 85, "url": "https://benchlm.ai/models/minimax-m2-5", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-5.md", "score": 58.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 86, "slug": "glm-4-5", "canonicalModelKey": "glm-4-5", "model": "GLM-4.5", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.32, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 46.81, "upper": 69.84 }, "rankingEligible": true, "overallRank": 86, "url": "https://benchlm.ai/models/glm-4-5", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5.md", "score": 58.32, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 87, "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", "score": 57.95, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 88, "slug": "gpt-5-2-codex", "canonicalModelKey": "gpt-5-2-codex", "model": "GPT-5.2-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 57.86, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 54.73, "upper": 61 }, "rankingEligible": true, "overallRank": 88, "url": "https://benchlm.ai/models/gpt-5-2-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-codex.md", "score": 57.86, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 89, "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", "score": 57.75, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 90, "slug": "gpt-5-3-codex-spark", "canonicalModelKey": "gpt-5-3-codex-spark", "model": "GPT-5.3-Codex-Spark", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 57.65, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 46.14, "upper": 69.17 }, "rankingEligible": true, "overallRank": 90, "url": "https://benchlm.ai/models/gpt-5-3-codex-spark", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex-spark.md", "score": 57.65, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 91, "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", "score": 57.35, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 92, "slug": "claude-opus-4-5-thinking", "canonicalModelKey": "claude-opus-4-5-thinking", "model": "Claude Opus 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 57.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.74, "upper": 68.77 }, "rankingEligible": true, "overallRank": 92, "url": "https://benchlm.ai/models/claude-opus-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5-thinking.md", "score": 57.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 93, "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", "score": 57.12, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 94, "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", "score": 56.77, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 95, "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", "score": 56.75, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 96, "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", "score": 56.69, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 12, "scoreConfidence": 3 }, { "rank": 97, "slug": "trinity-large-preview", "canonicalModelKey": "trinity-large-preview", "model": "Trinity-Large-Preview", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 56.67, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.15, "upper": 68.18 }, "rankingEligible": true, "overallRank": 97, "url": "https://benchlm.ai/models/trinity-large-preview", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-preview.md", "score": 56.67, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 98, "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", "score": 56.21, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 99, "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", "score": 56.11, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 100, "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", "score": 56.09, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 101, "slug": "grok-4-fast-reasoning", "canonicalModelKey": "grok-4-fast-reasoning", "model": "Grok 4 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 55.76, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 41.74, "upper": 69.78 }, "rankingEligible": true, "overallRank": 101, "url": "https://benchlm.ai/models/grok-4-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-fast-reasoning.md", "score": 55.76, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 102, "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", "score": 55.42, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 103, "slug": "deepseek-llm-2-0", "canonicalModelKey": "deepseek-llm-2-0", "model": "DeepSeek LLM 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 55.24, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 43.72, "upper": 66.75 }, "rankingEligible": true, "overallRank": 103, "url": "https://benchlm.ai/models/deepseek-llm-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-llm-2-0.md", "score": 55.24, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 104, "slug": "gpt-5-1-codex-max", "canonicalModelKey": "gpt-5-1-codex-max", "model": "GPT-5.1-Codex-Max", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 55.19, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 43.67, "upper": 66.7 }, "rankingEligible": true, "overallRank": 104, "url": "https://benchlm.ai/models/gpt-5-1-codex-max", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex-max.md", "score": 55.19, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 105, "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", "score": 54.64, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 106, "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", "score": 54.48, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 107, "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", "score": 54.36, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 108, "slug": "step-3-5-flash", "canonicalModelKey": "step-3-5-flash", "model": "Step 3.5 Flash", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 54.22, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 40.09, "upper": 68.34 }, "rankingEligible": true, "overallRank": 108, "url": "https://benchlm.ai/models/step-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-5-flash.md", "score": 54.22, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 109, "slug": "gpt-5-medium", "canonicalModelKey": "gpt-5-medium", "model": "GPT-5 (medium)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 54.06, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 49.86, "upper": 58.27 }, "rankingEligible": true, "overallRank": 109, "url": "https://benchlm.ai/models/gpt-5-medium", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-medium.md", "score": 54.06, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 110, "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", "score": 54.01, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 111, "slug": "nemotron-3-nano-30b", "canonicalModelKey": "nemotron-3-nano-30b", "model": "Nemotron 3 Nano 30B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 53.63, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 42.12, "upper": 65.15 }, "rankingEligible": true, "overallRank": 111, "url": "https://benchlm.ai/models/nemotron-3-nano-30b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-nano-30b.md", "score": 53.63, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 112, "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", "score": 53.62, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 113, "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", "score": 53.57, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 36, "scoreConfidence": 3 }, { "rank": 114, "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", "score": 53.41, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 115, "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", "score": 53.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 116, "slug": "deepseek-v3-1", "canonicalModelKey": "deepseek-v3-1", "model": "DeepSeek V3.1", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 52.92, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 33.51, "upper": 72.32 }, "rankingEligible": true, "overallRank": 116, "url": "https://benchlm.ai/models/deepseek-v3-1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1.md", "score": 52.92, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 117, "slug": "qwen2-5-72b", "canonicalModelKey": "qwen2-5-72b", "model": "Qwen2.5-72B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 52.83, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.32, "upper": 64.35 }, "rankingEligible": true, "overallRank": 117, "url": "https://benchlm.ai/models/qwen2-5-72b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-72b.md", "score": 52.83, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 118, "slug": "deepseek-v3-1-reasoning", "canonicalModelKey": "deepseek-v3-1-reasoning", "model": "DeepSeek V3.1 (Reasoning)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 52.74, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 33.02, "upper": 72.46 }, "rankingEligible": true, "overallRank": 118, "url": "https://benchlm.ai/models/deepseek-v3-1-reasoning", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-1-reasoning.md", "score": 52.74, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 119, "slug": "gpt-5-1-codex", "canonicalModelKey": "gpt-5-1-codex", "model": "GPT-5.1-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 52.63, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.12, "upper": 64.14 }, "rankingEligible": true, "overallRank": 119, "url": "https://benchlm.ai/models/gpt-5-1-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex.md", "score": 52.63, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 120, "slug": "llama-3-1-405b", "canonicalModelKey": "llama-3-1-405b", "model": "Llama 3.1 405B", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 52.38, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.87, "upper": 63.9 }, "rankingEligible": true, "overallRank": 120, "url": "https://benchlm.ai/models/llama-3-1-405b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-1-405b.md", "score": 52.38, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 121, "slug": "nemotron-3-super-120b-a12b", "canonicalModelKey": "nemotron-3-super-120b-a12b", "model": "Nemotron 3 Super 120B A12B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 51.63, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.12, "upper": 63.15 }, "rankingEligible": true, "overallRank": 121, "url": "https://benchlm.ai/models/nemotron-3-super-120b-a12b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-120b-a12b.md", "score": 51.63, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 122, "slug": "llama-3-70b", "canonicalModelKey": "llama-3-70b", "model": "Llama 3 70B", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 51.48, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.97, "upper": 63 }, "rankingEligible": true, "overallRank": 122, "url": "https://benchlm.ai/models/llama-3-70b", "markdownUrl": "https://benchlm.ai/md/models/llama-3-70b.md", "score": 51.48, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 123, "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", "score": 51.32, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 39, "scoreConfidence": 3 }, { "rank": 124, "slug": "deepseek-r1", "canonicalModelKey": "deepseek-r1", "model": "DeepSeek-R1", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 50.96, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 32.5, "upper": 69.43 }, "rankingEligible": true, "overallRank": 124, "url": "https://benchlm.ai/models/deepseek-r1", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1.md", "score": 50.96, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 125, "slug": "deepseek-coder-2-0", "canonicalModelKey": "deepseek-coder-2-0", "model": "DeepSeek Coder 2.0", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 50.93, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.42, "upper": 62.45 }, "rankingEligible": true, "overallRank": 125, "url": "https://benchlm.ai/models/deepseek-coder-2-0", "markdownUrl": "https://benchlm.ai/md/models/deepseek-coder-2-0.md", "score": 50.93, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 126, "slug": "seed-1-6", "canonicalModelKey": "seed-1-6", "model": "Seed 1.6", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 50.88, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.37, "upper": 62.4 }, "rankingEligible": true, "overallRank": 126, "url": "https://benchlm.ai/models/seed-1-6", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6.md", "score": 50.88, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 127, "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", "score": 50.83, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 10, "scoreConfidence": 1 }, { "rank": 128, "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", "score": 50.83, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 129, "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", "score": 50.82, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 130, "slug": "nemotron-3-super-100b", "canonicalModelKey": "nemotron-3-super-100b", "model": "Nemotron 3 Super 100B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.22, "upper": 62.25 }, "rankingEligible": true, "overallRank": 130, "url": "https://benchlm.ai/models/nemotron-3-super-100b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-super-100b.md", "score": 50.73, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 131, "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", "score": 50.66, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 132, "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", "score": 50.62, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 133, "slug": "deepseekmath-v2", "canonicalModelKey": "deepseekmath-v2", "model": "DeepSeekMath V2", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 50.54, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.02, "upper": 62.05 }, "rankingEligible": true, "overallRank": 133, "url": "https://benchlm.ai/models/deepseekmath-v2", "markdownUrl": "https://benchlm.ai/md/models/deepseekmath-v2.md", "score": 50.54, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 134, "slug": "qwen2-5-1m", "canonicalModelKey": "qwen2-5-1m", "model": "Qwen2.5-1M", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 50.54, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39.02, "upper": 62.05 }, "rankingEligible": true, "overallRank": 134, "url": "https://benchlm.ai/models/qwen2-5-1m", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-1m.md", "score": 50.54, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 135, "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", "score": 50.52, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 136, "slug": "seed-2-0-lite", "canonicalModelKey": "seed-2-0-lite", "model": "Seed-2.0-Lite", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 50.49, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.97, "upper": 62 }, "rankingEligible": true, "overallRank": 136, "url": "https://benchlm.ai/models/seed-2-0-lite", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-lite.md", "score": 50.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 137, "slug": "glm-4-7-flash", "canonicalModelKey": "glm-4-7-flash", "model": "GLM-4.7-Flash", "creator": "Z.AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 50.35, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 36.42, "upper": 64.28 }, "rankingEligible": true, "overallRank": 137, "url": "https://benchlm.ai/models/glm-4-7-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7-flash.md", "score": 50.35, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 138, "slug": "ministral-3-14b-reasoning", "canonicalModelKey": "ministral-3-14b-reasoning", "model": "Ministral 3 14B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.99, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.47, "upper": 61.5 }, "rankingEligible": true, "overallRank": 138, "url": "https://benchlm.ai/models/ministral-3-14b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b-reasoning.md", "score": 49.99, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 139, "slug": "mistral-large-3", "canonicalModelKey": "mistral-large-3", "model": "Mistral Large 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.6, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 26.88, "upper": 72.32 }, "rankingEligible": true, "overallRank": 139, "url": "https://benchlm.ai/models/mistral-large-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-3.md", "score": 49.6, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 140, "slug": "aion-2-0", "canonicalModelKey": "aion-2-0", "model": "Aion-2.0", "creator": "Aion Labs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.29, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 37.78, "upper": 60.81 }, "rankingEligible": true, "overallRank": 140, "url": "https://benchlm.ai/models/aion-2-0", "markdownUrl": "https://benchlm.ai/md/models/aion-2-0.md", "score": 49.29, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 141, "slug": "gpt-oss-120b", "canonicalModelKey": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.22, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 36.05, "upper": 62.4 }, "rankingEligible": true, "overallRank": 141, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md", "score": 49.22, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 142, "slug": "mixtral-8x22b-instruct-v0-1", "canonicalModelKey": "mixtral-8x22b-instruct-v0-1", "model": "Mixtral 8x22B Instruct v0.1", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 49.19, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 37.68, "upper": 60.7 }, "rankingEligible": true, "overallRank": 142, "url": "https://benchlm.ai/models/mixtral-8x22b-instruct-v0-1", "markdownUrl": "https://benchlm.ai/md/models/mixtral-8x22b-instruct-v0-1.md", "score": 49.19, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 143, "slug": "o1-preview", "canonicalModelKey": "o1-preview", "model": "o1-preview", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 48.48, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 28.75, "upper": 68.21 }, "rankingEligible": true, "overallRank": 143, "url": "https://benchlm.ai/models/o1-preview", "markdownUrl": "https://benchlm.ai/md/models/o1-preview.md", "score": 48.48, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 144, "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", "score": 48.36, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 145, "slug": "qwen3-max", "canonicalModelKey": "qwen3-max", "model": "Qwen3 Max", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": 48.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.73, "upper": 59.76 }, "rankingEligible": true, "overallRank": 145, "url": "https://benchlm.ai/models/qwen3-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-max.md", "score": 48.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 146, "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", "score": 48.18, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 147, "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", "score": 48.13, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 148, "slug": "trinity-large-thinking", "canonicalModelKey": "trinity-large-thinking", "model": "Trinity-Large-Thinking", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 47.92, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 30.73, "upper": 65.11 }, "rankingEligible": true, "overallRank": 148, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md", "score": 47.92, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 149, "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", "score": 47.9, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 150, "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", "score": 47.79, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 151, "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", "score": 47.57, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 152, "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", "score": 47.56, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 153, "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", "score": 47.56, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 154, "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", "score": 47.33, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 155, "slug": "o3-pro", "canonicalModelKey": "o3-pro", "model": "o3-pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 47.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 42.84, "upper": 51.55 }, "rankingEligible": true, "overallRank": 155, "url": "https://benchlm.ai/models/o3-pro", "markdownUrl": "https://benchlm.ai/md/models/o3-pro.md", "score": 47.2, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 156, "slug": "glm-4-5-air", "canonicalModelKey": "glm-4-5-air", "model": "GLM-4.5-Air", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 47.08, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 28.25, "upper": 65.92 }, "rankingEligible": true, "overallRank": 156, "url": "https://benchlm.ai/models/glm-4-5-air", "markdownUrl": "https://benchlm.ai/md/models/glm-4-5-air.md", "score": 47.08, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 157, "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", "score": 46.82, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 158, "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", "score": 46.69, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 159, "slug": "gpt-5-nano", "canonicalModelKey": "gpt-5-nano", "model": "GPT-5 nano", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 46.53, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 35.01, "upper": 58.04 }, "rankingEligible": true, "overallRank": 159, "url": "https://benchlm.ai/models/gpt-5-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-nano.md", "score": 46.53, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 160, "slug": "mistral-small-4", "canonicalModelKey": "mistral-small-4", "model": "Mistral Small 4", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 46.35, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.84, "upper": 57.87 }, "rankingEligible": true, "overallRank": 160, "url": "https://benchlm.ai/models/mistral-small-4", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4.md", "score": 46.35, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 161, "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", "score": 46.32, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 162, "slug": "o1-pro", "canonicalModelKey": "o1-pro", "model": "o1-pro", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 46.12, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.61, "upper": 57.63 }, "rankingEligible": true, "overallRank": 162, "url": "https://benchlm.ai/models/o1-pro", "markdownUrl": "https://benchlm.ai/md/models/o1-pro.md", "score": 46.12, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 163, "slug": "z-1", "canonicalModelKey": "z-1", "model": "Z-1", "creator": "Z", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 45.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.21, "upper": 57.24 }, "rankingEligible": true, "overallRank": 163, "url": "https://benchlm.ai/models/z-1", "markdownUrl": "https://benchlm.ai/md/models/z-1.md", "score": 45.73, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 164, "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", "score": 45.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 165, "slug": "nemotron-4-15b", "canonicalModelKey": "nemotron-4-15b", "model": "Nemotron-4 15B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 45.68, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.17, "upper": 57.19 }, "rankingEligible": true, "overallRank": 165, "url": "https://benchlm.ai/models/nemotron-4-15b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-4-15b.md", "score": 45.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 166, "slug": "seed-1-6-flash", "canonicalModelKey": "seed-1-6-flash", "model": "Seed 1.6 Flash", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 45.68, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.17, "upper": 57.19 }, "rankingEligible": true, "overallRank": 166, "url": "https://benchlm.ai/models/seed-1-6-flash", "markdownUrl": "https://benchlm.ai/md/models/seed-1-6-flash.md", "score": 45.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 167, "slug": "mistral-8x7b", "canonicalModelKey": "mistral-8x7b", "model": "Mistral 8x7B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 45.58, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 34.07, "upper": 57.1 }, "rankingEligible": true, "overallRank": 167, "url": "https://benchlm.ai/models/mistral-8x7b", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b.md", "score": 45.58, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 168, "slug": "moonshot-v1", "canonicalModelKey": "moonshot-v1", "model": "Moonshot v1", "creator": "Moonshot AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 45.38, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.87, "upper": 56.9 }, "rankingEligible": true, "overallRank": 168, "url": "https://benchlm.ai/models/moonshot-v1", "markdownUrl": "https://benchlm.ai/md/models/moonshot-v1.md", "score": 45.38, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 169, "slug": "seed-2-0-mini", "canonicalModelKey": "seed-2-0-mini", "model": "Seed-2.0-Mini", "creator": "ByteDance", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 45.19, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.67, "upper": 56.7 }, "rankingEligible": true, "overallRank": 169, "url": "https://benchlm.ai/models/seed-2-0-mini", "markdownUrl": "https://benchlm.ai/md/models/seed-2-0-mini.md", "score": 45.19, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 170, "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", "score": 45.05, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 171, "slug": "nemotron-ultra-253b", "canonicalModelKey": "nemotron-ultra-253b", "model": "Nemotron Ultra 253B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 44.99, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.48, "upper": 56.5 }, "rankingEligible": true, "overallRank": 171, "url": "https://benchlm.ai/models/nemotron-ultra-253b", "markdownUrl": "https://benchlm.ai/md/models/nemotron-ultra-253b.md", "score": 44.99, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 172, "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", "score": 44.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 173, "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", "score": 44.4, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 174, "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", "score": 44.38, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 175, "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", "score": 44.18, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 176, "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", "score": 43.71, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 177, "slug": "mistral-medium-3", "canonicalModelKey": "mistral-medium-3", "model": "Mistral Medium 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 43.49, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.98, "upper": 55 }, "rankingEligible": true, "overallRank": 177, "url": "https://benchlm.ai/models/mistral-medium-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3.md", "score": 43.49, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 178, "slug": "gemma-4-e4b", "canonicalModelKey": "gemma-4-e4b", "model": "Gemma 4 E4B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 43.37, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.86, "upper": 54.89 }, "rankingEligible": true, "overallRank": 178, "url": "https://benchlm.ai/models/gemma-4-e4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e4b.md", "score": 43.37, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 179, "slug": "sarvam-105b", "canonicalModelKey": "sarvam-105b", "model": "Sarvam 105B", "creator": "Sarvam", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 43.26, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.75, "upper": 54.78 }, "rankingEligible": true, "overallRank": 179, "url": "https://benchlm.ai/models/sarvam-105b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-105b.md", "score": 43.26, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 180, "slug": "gpt-5-mini", "canonicalModelKey": "gpt-5-mini", "model": "GPT-5 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.97, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 39.53, "upper": 46.41 }, "rankingEligible": true, "overallRank": 180, "url": "https://benchlm.ai/models/gpt-5-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-mini.md", "score": 42.97, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 181, "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", "score": 42.9, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 182, "slug": "deepseek-r1-distill-qwen-32b", "canonicalModelKey": "deepseek-r1-distill-qwen-32b", "model": "DeepSeek R1 Distill Qwen 32B", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.89, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.38, "upper": 54.41 }, "rankingEligible": true, "overallRank": 182, "url": "https://benchlm.ai/models/deepseek-r1-distill-qwen-32b", "markdownUrl": "https://benchlm.ai/md/models/deepseek-r1-distill-qwen-32b.md", "score": 42.89, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 183, "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", "score": 42.38, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 184, "slug": "gemma-4-e2b", "canonicalModelKey": "gemma-4-e2b", "model": "Gemma 4 E2B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.33, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.82, "upper": 53.85 }, "rankingEligible": true, "overallRank": 184, "url": "https://benchlm.ai/models/gemma-4-e2b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e2b.md", "score": 42.33, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 185, "slug": "gpt-oss-20b", "canonicalModelKey": "gpt-oss-20b", "model": "GPT-OSS 20B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 27.12, "upper": 57.39 }, "rankingEligible": true, "overallRank": 185, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md", "score": 42.25, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 186, "slug": "mistral-large-2", "canonicalModelKey": "mistral-large-2", "model": "Mistral Large 2", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.12, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.61, "upper": 53.63 }, "rankingEligible": true, "overallRank": 186, "url": "https://benchlm.ai/models/mistral-large-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-2.md", "score": 42.12, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 187, "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", "score": 42.07, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 188, "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", "score": 41.78, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 189, "slug": "gemma-3-27b", "canonicalModelKey": "gemma-3-27b", "model": "Gemma 3 27B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 41.26, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.97, "upper": 65.54 }, "rankingEligible": true, "overallRank": 189, "url": "https://benchlm.ai/models/gemma-3-27b", "markdownUrl": "https://benchlm.ai/md/models/gemma-3-27b.md", "score": 41.26, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 190, "slug": "sarvam-30b", "canonicalModelKey": "sarvam-30b", "model": "Sarvam 30B", "creator": "Sarvam", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": 41.1, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 29.58, "upper": 52.61 }, "rankingEligible": true, "overallRank": 190, "url": "https://benchlm.ai/models/sarvam-30b", "markdownUrl": "https://benchlm.ai/md/models/sarvam-30b.md", "score": 41.1, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 191, "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", "score": 40.96, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 192, "slug": "ministral-3-8b-reasoning", "canonicalModelKey": "ministral-3-8b-reasoning", "model": "Ministral 3 8B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.94, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 29.42, "upper": 52.45 }, "rankingEligible": true, "overallRank": 192, "url": "https://benchlm.ai/models/ministral-3-8b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b-reasoning.md", "score": 40.94, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 193, "slug": "claude-3-opus", "canonicalModelKey": "claude-3-opus", "model": "Claude 3 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 40.57, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 22.75, "upper": 58.38 }, "rankingEligible": true, "overallRank": 193, "url": "https://benchlm.ai/models/claude-3-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-3-opus.md", "score": 40.57, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 194, "slug": "mistral-7b-v0-3", "canonicalModelKey": "mistral-7b-v0-3", "model": "Mistral 7B v0.3", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 40.45, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.94, "upper": 51.97 }, "rankingEligible": true, "overallRank": 194, "url": "https://benchlm.ai/models/mistral-7b-v0-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-7b-v0-3.md", "score": 40.45, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 195, "slug": "qwen2-5-vl-32b", "canonicalModelKey": "qwen2-5-vl-32b", "model": "Qwen2.5-VL-32B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 40.4, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.89, "upper": 51.92 }, "rankingEligible": true, "overallRank": 195, "url": "https://benchlm.ai/models/qwen2-5-vl-32b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-vl-32b.md", "score": 40.4, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 196, "slug": "llama-4-behemoth", "canonicalModelKey": "llama-4-behemoth", "model": "Llama 4 Behemoth", "creator": "Meta", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 40.36, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.84, "upper": 51.87 }, "rankingEligible": true, "overallRank": 196, "url": "https://benchlm.ai/models/llama-4-behemoth", "markdownUrl": "https://benchlm.ai/md/models/llama-4-behemoth.md", "score": 40.36, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 197, "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", "score": 40.33, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 198, "slug": "ministral-3-3b-reasoning", "canonicalModelKey": "ministral-3-3b-reasoning", "model": "Ministral 3 3B (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 40.07, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.55, "upper": 51.58 }, "rankingEligible": true, "overallRank": 198, "url": "https://benchlm.ai/models/ministral-3-3b-reasoning", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b-reasoning.md", "score": 40.07, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 199, "slug": "mistral-8x7b-v0-2", "canonicalModelKey": "mistral-8x7b-v0-2", "model": "Mistral 8x7B v0.2", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 39.68, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.17, "upper": 51.19 }, "rankingEligible": true, "overallRank": 199, "url": "https://benchlm.ai/models/mistral-8x7b-v0-2", "markdownUrl": "https://benchlm.ai/md/models/mistral-8x7b-v0-2.md", "score": 39.68, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 200, "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", "score": 39.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 201, "slug": "granite-4-0-350m", "canonicalModelKey": "granite-4-0-350m", "model": "Granite-4.0-350M", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 39, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 27.49, "upper": 50.51 }, "rankingEligible": true, "overallRank": 201, "url": "https://benchlm.ai/models/granite-4-0-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-350m.md", "score": 39, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 202, "slug": "granite-4-0-h-350m", "canonicalModelKey": "granite-4-0-h-350m", "model": "Granite-4.0-H-350M", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 39, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 27.49, "upper": 50.51 }, "rankingEligible": true, "overallRank": 202, "url": "https://benchlm.ai/models/granite-4-0-h-350m", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-350m.md", "score": 39, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 203, "slug": "grok-code-fast-1", "canonicalModelKey": "grok-code-fast-1", "model": "Grok Code Fast 1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 37.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 34.7, "upper": 40.75 }, "rankingEligible": true, "overallRank": 203, "url": "https://benchlm.ai/models/grok-code-fast-1", "markdownUrl": "https://benchlm.ai/md/models/grok-code-fast-1.md", "score": 37.73, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 204, "slug": "gpt-4o-mini", "canonicalModelKey": "gpt-4o-mini", "model": "GPT-4o mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 37.43, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.67, "upper": 58.19 }, "rankingEligible": true, "overallRank": 204, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md", "score": 37.43, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 205, "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", "score": 37.33, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 206, "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", "score": 35.27, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 207, "slug": "gemini-1-5-pro", "canonicalModelKey": "gemini-1-5-pro", "model": "Gemini 1.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 35.14, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.08, "upper": 49.2 }, "rankingEligible": true, "overallRank": 207, "url": "https://benchlm.ai/models/gemini-1-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-5-pro.md", "score": 35.14, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 208, "slug": "qwen2-5-coder-32b-instruct", "canonicalModelKey": "qwen2-5-coder-32b-instruct", "model": "Qwen2.5 Coder 32B Instruct", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34.21, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 17.53, "upper": 50.89 }, "rankingEligible": true, "overallRank": 208, "url": "https://benchlm.ai/models/qwen2-5-coder-32b-instruct", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-coder-32b-instruct.md", "score": 34.21, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 209, "slug": "ministral-3-14b", "canonicalModelKey": "ministral-3-14b", "model": "Ministral 3 14B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 23, "upper": 45.01 }, "rankingEligible": true, "overallRank": 209, "url": "https://benchlm.ai/models/ministral-3-14b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b.md", "score": 34, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 210, "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", "score": 31.16, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 10, "scoreConfidence": 2 }, { "rank": 211, "slug": "gpt-4-turbo", "canonicalModelKey": "gpt-4-turbo", "model": "GPT-4 Turbo", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 26.85, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 19.33, "upper": 34.36 }, "rankingEligible": true, "overallRank": 211, "url": "https://benchlm.ai/models/gpt-4-turbo", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-turbo.md", "score": 26.85, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 212, "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", "score": 26.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 213, "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", "score": 26.24, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 214, "slug": "minimax-m1-80k", "canonicalModelKey": "minimax-m1-80k", "model": "MiniMax M1 80k", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "80K", "contextWindowTokens": 80000, "displayScore": 24.21, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 14.31, "upper": 34.12 }, "rankingEligible": true, "overallRank": 214, "url": "https://benchlm.ai/models/minimax-m1-80k", "markdownUrl": "https://benchlm.ai/md/models/minimax-m1-80k.md", "score": 24.21, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 215, "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", "score": 22.76, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 216, "slug": "phi-4", "canonicalModelKey": "phi-4", "model": "Phi-4", "creator": "Microsoft", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "16K", "contextWindowTokens": 16000, "displayScore": 22.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 0, "upper": 45.61 }, "rankingEligible": true, "overallRank": 216, "url": "https://benchlm.ai/models/phi-4", "markdownUrl": "https://benchlm.ai/md/models/phi-4.md", "score": 22.55, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 217, "slug": "gemini-1-0-pro", "canonicalModelKey": "gemini-1-0-pro", "model": "Gemini 1.0 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 21.28, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 13.82, "upper": 28.75 }, "rankingEligible": true, "overallRank": 217, "url": "https://benchlm.ai/models/gemini-1-0-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-0-pro.md", "score": 21.28, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 218, "slug": "claude-3-haiku", "canonicalModelKey": "claude-3-haiku", "model": "Claude 3 Haiku", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 20.86, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 14.72, "upper": 27.01 }, "rankingEligible": true, "overallRank": 218, "url": "https://benchlm.ai/models/claude-3-haiku", "markdownUrl": "https://benchlm.ai/md/models/claude-3-haiku.md", "score": 20.86, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 219, "slug": "ministral-3-8b", "canonicalModelKey": "ministral-3-8b", "model": "Ministral 3 8B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 20.38, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.69, "upper": 24.07 }, "rankingEligible": true, "overallRank": 219, "url": "https://benchlm.ai/models/ministral-3-8b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b.md", "score": 20.38, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 220, "slug": "nova-pro", "canonicalModelKey": "nova-pro", "model": "Nova Pro", "creator": "Amazon", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 19.67, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 16.55, "upper": 22.79 }, "rankingEligible": true, "overallRank": 220, "url": "https://benchlm.ai/models/nova-pro", "markdownUrl": "https://benchlm.ai/md/models/nova-pro.md", "score": 19.67, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 221, "slug": "lfm2-24b-a2b", "canonicalModelKey": "lfm2-24b-a2b", "model": "LFM2-24B-A2B", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 18.29, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 15.23, "upper": 21.35 }, "rankingEligible": true, "overallRank": 221, "url": "https://benchlm.ai/models/lfm2-24b-a2b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-24b-a2b.md", "score": 18.29, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 222, "slug": "ministral-3-3b", "canonicalModelKey": "ministral-3-3b", "model": "Ministral 3 3B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 17.93, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 14, "upper": 21.86 }, "rankingEligible": true, "overallRank": 222, "url": "https://benchlm.ai/models/ministral-3-3b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b.md", "score": 17.93, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 223, "slug": "lfm2-5-1-2b-thinking", "canonicalModelKey": "lfm2-5-1-2b-thinking", "model": "LFM2.5-1.2B-Thinking", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 15.71, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 12.66, "upper": 18.75 }, "rankingEligible": true, "overallRank": 223, "url": "https://benchlm.ai/models/lfm2-5-1-2b-thinking", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-thinking.md", "score": 15.71, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 224, "slug": "lfm2-5-1-2b-instruct", "canonicalModelKey": "lfm2-5-1-2b-instruct", "model": "LFM2.5-1.2B-Instruct", "creator": "LiquidAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 14.99, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 12.08, "upper": 17.9 }, "rankingEligible": true, "overallRank": 224, "url": "https://benchlm.ai/models/lfm2-5-1-2b-instruct", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-instruct.md", "score": 14.99, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 225, "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", "score": 11.08, "rankingMode": "bench-align-v5", "category": null, "categoryLabel": null, "trustedBenchmarkCount": 13, "scoreConfidence": 2 } ], "categories": { "agentic": [ { "rank": 1, "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": 73.54, "upper": 84.36 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md", "score": 78.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 59, "scoreConfidence": 3 }, { "rank": 2, "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": "supported", "scoreInterval90": { "lower": 69.2, "upper": 83.51 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md", "score": 76.36, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 3, "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": 69.08, "upper": 80.22 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md", "score": 74.65, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 4, "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": 63.44, "upper": 81.98 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 72.71, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 5, "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": 66.43, "upper": 78.64 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md", "score": 72.54, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 30, "scoreConfidence": 2 }, { "rank": 6, "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": "supported", "scoreInterval90": { "lower": 61.02, "upper": 78.49 }, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md", "score": 69.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 7, "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": 55.66, "upper": 83.48 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md", "score": 69.57, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 8, "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": "supported", "scoreInterval90": { "lower": 61.43, "upper": 76.66 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md", "score": 69.05, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 9, "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": 61.04, "upper": 76.57 }, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md", "score": 68.8, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 10, "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": 58.56, "upper": 78.45 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md", "score": 68.5, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 23, "scoreConfidence": 3 }, { "rank": 11, "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": "supported", "scoreInterval90": { "lower": 59.96, "upper": 72.98 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md", "score": 66.47, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 12, "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": "supported", "scoreInterval90": { "lower": 52.95, "upper": 78.38 }, "rankingEligible": true, "overallRank": 47, "url": "https://benchlm.ai/models/grok-4-6", "markdownUrl": "https://benchlm.ai/md/models/grok-4-6.md", "score": 65.66, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 13, "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": "estimated", "scoreInterval90": { "lower": 51.43, "upper": 78.71 }, "rankingEligible": true, "overallRank": 19, "url": "https://benchlm.ai/models/muse-spark", "markdownUrl": "https://benchlm.ai/md/models/muse-spark.md", "score": 65.07, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 14, "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": "supported", "scoreInterval90": { "lower": 58.63, "upper": 70.85 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md", "score": 64.74, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 15, "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": "supported", "scoreInterval90": { "lower": 55.59, "upper": 71.73 }, "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", "score": 63.66, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 16, "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": 55.92, "upper": 70.08 }, "rankingEligible": true, "overallRank": 11, "url": "https://benchlm.ai/models/grok-4-5", "markdownUrl": "https://benchlm.ai/md/models/grok-4-5.md", "score": 63, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 17, "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": 47.25, "upper": 76.58 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md", "score": 61.92, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 18, "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": 50.8, "upper": 72.66 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "score": 61.73, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 19, "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": 44.32, "upper": 78.03 }, "rankingEligible": true, "overallRank": 21, "url": "https://benchlm.ai/models/dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/models/dots3-note-preview.md", "score": 61.17, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 26, "scoreConfidence": 3 }, { "rank": 20, "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": 48, "upper": 74.31 }, "rankingEligible": true, "overallRank": 42, "url": "https://benchlm.ai/models/gpt-5-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5-pro.md", "score": 61.15, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 21, "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": "estimated", "scoreInterval90": { "lower": 47.88, "upper": 74.2 }, "rankingEligible": true, "overallRank": 34, "url": "https://benchlm.ai/models/gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex.md", "score": 61.04, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 22, "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": "supported", "scoreInterval90": { "lower": 50.27, "upper": 68.69 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md", "score": 59.48, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 23, "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": 45.83, "upper": 72.15 }, "rankingEligible": true, "overallRank": 54, "url": "https://benchlm.ai/models/gpt-5-4-pro", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-pro.md", "score": 58.99, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 24, "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": "estimated", "scoreInterval90": { "lower": 46.37, "upper": 71.33 }, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md", "score": 58.85, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 25, "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": 46.21, "upper": 71.31 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md", "score": 58.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 19, "scoreConfidence": 2 }, { "rank": 26, "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": "supported", "scoreInterval90": { "lower": 49.41, "upper": 67.87 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md", "score": 58.64, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 27, "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": 42.31, "upper": 74.83 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md", "score": 58.57, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 28, "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": "estimated", "scoreInterval90": { "lower": 44.21, "upper": 71.77 }, "rankingEligible": true, "overallRank": 69, "url": "https://benchlm.ai/models/qwen3-6-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-max-preview.md", "score": 57.99, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 29, "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": 45.61, "upper": 68.64 }, "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", "score": 57.13, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 30, "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": "supported", "scoreInterval90": { "lower": 48.39, "upper": 65.86 }, "rankingEligible": true, "overallRank": 57, "url": "https://benchlm.ai/models/deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-0813.md", "score": 57.13, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 31, "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": 51.32, "upper": 62.73 }, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md", "score": 57.03, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 32, "scoreConfidence": 3 }, { "rank": 32, "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": 41.88, "upper": 72.02 }, "rankingEligible": true, "overallRank": 58, "url": "https://benchlm.ai/models/agents-a1", "markdownUrl": "https://benchlm.ai/md/models/agents-a1.md", "score": 56.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 33, "slug": "agents-a1-f16-gguf", "canonicalModelKey": "agents-a1-f16-gguf", "model": "Agents-A1-F16-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.88, "upper": 72.02 }, "rankingEligible": true, "overallRank": 59, "url": "https://benchlm.ai/models/agents-a1-f16-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-f16-gguf.md", "score": 56.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 34, "slug": "agents-a1-fp8", "canonicalModelKey": "agents-a1-fp8", "model": "Agents-A1-FP8", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.88, "upper": 72.02 }, "rankingEligible": true, "overallRank": 60, "url": "https://benchlm.ai/models/agents-a1-fp8", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-fp8.md", "score": 56.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 35, "slug": "agents-a1-q4-k-m-gguf", "canonicalModelKey": "agents-a1-q4-k-m-gguf", "model": "Agents-A1-Q4_K_M-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.88, "upper": 72.02 }, "rankingEligible": true, "overallRank": 61, "url": "https://benchlm.ai/models/agents-a1-q4-k-m-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-q4-k-m-gguf.md", "score": 56.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 36, "slug": "agents-a1-q8-0-gguf", "canonicalModelKey": "agents-a1-q8-0-gguf", "model": "Agents-A1-Q8_0-GGUF", "creator": "InternScience", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": 61.2, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.88, "upper": 72.02 }, "rankingEligible": true, "overallRank": 62, "url": "https://benchlm.ai/models/agents-a1-q8-0-gguf", "markdownUrl": "https://benchlm.ai/md/models/agents-a1-q8-0-gguf.md", "score": 56.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 37, "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": 47.83, "upper": 65.93 }, "rankingEligible": true, "overallRank": 23, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md", "score": 56.88, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 38, "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": 44.8, "upper": 67.83 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md", "score": 56.31, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 39, "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": "supported", "scoreInterval90": { "lower": 44.62, "upper": 67.68 }, "rankingEligible": true, "overallRank": 55, "url": "https://benchlm.ai/models/muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-2.md", "score": 56.15, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 40, "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": "estimated", "scoreInterval90": { "lower": 42, "upper": 68.58 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/swe-1-7", "markdownUrl": "https://benchlm.ai/md/models/swe-1-7.md", "score": 55.29, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 41, "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": "estimated", "scoreInterval90": { "lower": 41.98, "upper": 68.3 }, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 55.14, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 42, "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": "supported", "scoreInterval90": { "lower": 43.53, "upper": 66.12 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md", "score": 54.82, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 43, "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": "estimated", "scoreInterval90": { "lower": 26.86, "upper": 82.66 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-35b-a3b.md", "score": 54.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 44, "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": 39.5, "upper": 70.02 }, "rankingEligible": true, "overallRank": 78, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md", "score": 54.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 45, "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": "estimated", "scoreInterval90": { "lower": 41.33, "upper": 67.89 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md", "score": 54.61, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 46, "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": "estimated", "scoreInterval90": { "lower": 22.53, "upper": 84.99 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/holo3-122b-a10b.md", "score": 53.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 47, "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": "estimated", "scoreInterval90": { "lower": 39.6, "upper": 67.43 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-s-2-1.md", "score": 53.51, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 48, "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": "estimated", "scoreInterval90": { "lower": 39.39, "upper": 67.39 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md", "score": 53.39, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 49, "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": 41.81, "upper": 64.84 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md", "score": 53.33, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 50, "slug": "gpt-5-2-codex", "canonicalModelKey": "gpt-5-2-codex", "model": "GPT-5.2-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 57.86, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.79, "upper": 64.81 }, "rankingEligible": true, "overallRank": 88, "url": "https://benchlm.ai/models/gpt-5-2-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-codex.md", "score": 53.3, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 51, "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": "estimated", "scoreInterval90": { "lower": 36.51, "upper": 70.07 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/btl-4", "markdownUrl": "https://benchlm.ai/md/models/btl-4.md", "score": 53.29, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 52, "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": "estimated", "scoreInterval90": { "lower": 38.82, "upper": 66.29 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-35b.md", "score": 52.55, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 53, "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": "estimated", "scoreInterval90": { "lower": 36.18, "upper": 68.68 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pokee-isaac-28b", "markdownUrl": "https://benchlm.ai/md/models/pokee-isaac-28b.md", "score": 52.43, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 54, "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": "estimated", "scoreInterval90": { "lower": 38.39, "upper": 66.07 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md", "score": 52.23, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 55, "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": "estimated", "scoreInterval90": { "lower": 29.93, "upper": 74.23 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-glimmer-30b", "markdownUrl": "https://benchlm.ai/md/models/muse-glimmer-30b.md", "score": 52.08, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 56, "slug": "gpt-5-1-codex", "canonicalModelKey": "gpt-5-1-codex", "model": "GPT-5.1-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 52.63, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.48, "upper": 64.8 }, "rankingEligible": true, "overallRank": 119, "url": "https://benchlm.ai/models/gpt-5-1-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex.md", "score": 51.64, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 57, "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": 38.38, "upper": 64.7 }, "rankingEligible": true, "overallRank": 91, "url": "https://benchlm.ai/models/claude-haiku-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5.md", "score": 51.54, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 58, "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": "supported", "scoreInterval90": { "lower": 39.61, "upper": 62.99 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md", "score": 51.3, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 59, "slug": "gpt-5-high", "canonicalModelKey": "gpt-5-high", "model": "GPT-5 (high)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 59.4, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 38.05, "upper": 64.37 }, "rankingEligible": true, "overallRank": 80, "url": "https://benchlm.ai/models/gpt-5-high", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-high.md", "score": 51.21, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 60, "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": "estimated", "scoreInterval90": { "lower": 39.64, "upper": 62.67 }, "rankingEligible": true, "overallRank": 66, "url": "https://benchlm.ai/models/glm-4-7", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7.md", "score": 51.15, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 61, "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": 35.5, "upper": 66.35 }, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md", "score": 50.92, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 62, "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": 34.07, "upper": 66.83 }, "rankingEligible": true, "overallRank": 135, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md", "score": 50.45, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 63, "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": 37.11, "upper": 63.43 }, "rankingEligible": true, "overallRank": 70, "url": "https://benchlm.ai/models/kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5-reasoning.md", "score": 50.27, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 64, "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": "estimated", "scoreInterval90": { "lower": 36.67, "upper": 62.99 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md", "score": 49.83, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 65, "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": "estimated", "scoreInterval90": { "lower": 36.18, "upper": 62.5 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-9b.md", "score": 49.34, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 66, "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": 35.91, "upper": 62.23 }, "rankingEligible": true, "overallRank": 150, "url": "https://benchlm.ai/models/qwen3-5-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-plus.md", "score": 49.07, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 67, "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": "estimated", "scoreInterval90": { "lower": 37.56, "upper": 60.58 }, "rankingEligible": true, "overallRank": 93, "url": "https://benchlm.ai/models/gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-26b-a4b.md", "score": 49.07, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 68, "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": 37.55, "upper": 60.58 }, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md", "score": 49.07, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 69, "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": 37.38, "upper": 60.41 }, "rankingEligible": true, "overallRank": 114, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md", "score": 48.89, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 70, "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": "estimated", "scoreInterval90": { "lower": 37.27, "upper": 60.29 }, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "score": 48.78, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 71, "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": "estimated", "scoreInterval90": { "lower": 34.05, "upper": 63.48 }, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": 48.77, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 72, "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": 41, "upper": 56.03 }, "rankingEligible": true, "overallRank": 41, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md", "score": 48.51, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 73, "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": 33.32, "upper": 63.58 }, "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", "score": 48.45, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 74, "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": "estimated", "scoreInterval90": { "lower": 35.06, "upper": 61.38 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md", "score": 48.22, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 75, "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": "estimated", "scoreInterval90": { "lower": 34.62, "upper": 61.42 }, "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", "score": 48.02, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 76, "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": "estimated", "scoreInterval90": { "lower": 36.44, "upper": 59.47 }, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md", "score": 47.95, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 77, "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": 34.56, "upper": 60.88 }, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 47.72, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 78, "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": "estimated", "scoreInterval90": { "lower": 34.22, "upper": 60.54 }, "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", "score": 47.38, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 79, "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": 33.98, "upper": 60.3 }, "rankingEligible": true, "overallRank": 176, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md", "score": 47.14, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 80, "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": 33.48, "upper": 59.8 }, "rankingEligible": true, "overallRank": 106, "url": "https://benchlm.ai/models/claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5.md", "score": 46.64, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 81, "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": 30.21, "upper": 62.84 }, "rankingEligible": true, "overallRank": 188, "url": "https://benchlm.ai/models/lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-8b-a1b.md", "score": 46.52, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 82, "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": "estimated", "scoreInterval90": { "lower": 31.22, "upper": 60.3 }, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": 45.76, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 83, "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": "estimated", "scoreInterval90": { "lower": 34.21, "upper": 57.24 }, "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", "score": 45.72, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 84, "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": 33.98, "upper": 57.01 }, "rankingEligible": true, "overallRank": 127, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md", "score": 45.5, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 10, "scoreConfidence": 1 }, { "rank": 85, "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": "estimated", "scoreInterval90": { "lower": 32.24, "upper": 58.56 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-230m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-230m.md", "score": 45.4, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 86, "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": "estimated", "scoreInterval90": { "lower": 32.23, "upper": 58.55 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m.md", "score": 45.39, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 87, "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": "estimated", "scoreInterval90": { "lower": 32.19, "upper": 58.51 }, "rankingEligible": true, "overallRank": 170, "url": "https://benchlm.ai/models/claude-4-1-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus.md", "score": 45.35, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 88, "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": 33.61, "upper": 56.64 }, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md", "score": 45.12, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 39, "scoreConfidence": 3 }, { "rank": 89, "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": "supported", "scoreInterval90": { "lower": 34.79, "upper": 54.6 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 44.69, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 90, "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": 34.56, "upper": 54.38 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md", "score": 44.47, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 91, "slug": "gpt-oss-120b", "canonicalModelKey": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.22, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 32.89, "upper": 55.91 }, "rankingEligible": true, "overallRank": 141, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md", "score": 44.4, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 92, "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": 32.83, "upper": 55.85 }, "rankingEligible": true, "overallRank": 151, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md", "score": 44.34, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 93, "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": 32.5, "upper": 55.53 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md", "score": 44.01, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 94, "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": 32.95, "upper": 54.94 }, "rankingEligible": true, "overallRank": 24, "url": "https://benchlm.ai/models/hy3", "markdownUrl": "https://benchlm.ai/md/models/hy3.md", "score": 43.94, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 95, "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": "supported", "scoreInterval90": { "lower": 36.25, "upper": 51.01 }, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "score": 43.63, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 96, "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": "supported", "scoreInterval90": { "lower": 32.04, "upper": 54.93 }, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md", "score": 43.49, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 97, "slug": "minimax-m2-5", "canonicalModelKey": "minimax-m2-5", "model": "MiniMax M2.5", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.49, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.73, "upper": 54.76 }, "rankingEligible": true, "overallRank": 85, "url": "https://benchlm.ai/models/minimax-m2-5", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-5.md", "score": 43.25, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 98, "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": 33.42, "upper": 52.76 }, "rankingEligible": true, "overallRank": 32, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md", "score": 43.09, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 99, "slug": "mistral-small-4", "canonicalModelKey": "mistral-small-4", "model": "Mistral Small 4", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 46.35, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.42, "upper": 54.45 }, "rankingEligible": true, "overallRank": 160, "url": "https://benchlm.ai/models/mistral-small-4", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4.md", "score": 42.94, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 100, "slug": "mistral-large-3", "canonicalModelKey": "mistral-large-3", "model": "Mistral Large 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.6, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.28, "upper": 54.31 }, "rankingEligible": true, "overallRank": 139, "url": "https://benchlm.ai/models/mistral-large-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-3.md", "score": 42.8, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 101, "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": "estimated", "scoreInterval90": { "lower": 31.23, "upper": 54.26 }, "rankingEligible": true, "overallRank": 147, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md", "score": 42.74, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 102, "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": "estimated", "scoreInterval90": { "lower": 29.46, "upper": 55.78 }, "rankingEligible": true, "overallRank": 187, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md", "score": 42.62, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 103, "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": 30.28, "upper": 53.31 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md", "score": 41.8, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 104, "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": 30.24, "upper": 53.27 }, "rankingEligible": true, "overallRank": 173, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md", "score": 41.75, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 105, "slug": "gpt-5-mini", "canonicalModelKey": "gpt-5-mini", "model": "GPT-5 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.97, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.23, "upper": 53.25 }, "rankingEligible": true, "overallRank": 180, "url": "https://benchlm.ai/models/gpt-5-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-mini.md", "score": 41.74, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 106, "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": 30.03, "upper": 53.06 }, "rankingEligible": true, "overallRank": 181, "url": "https://benchlm.ai/models/lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-2-6b.md", "score": 41.54, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 107, "slug": "trinity-large-thinking", "canonicalModelKey": "trinity-large-thinking", "model": "Trinity-Large-Thinking", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 47.92, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 29.76, "upper": 52.78 }, "rankingEligible": true, "overallRank": 148, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md", "score": 41.27, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 108, "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": 28.67, "upper": 53.77 }, "rankingEligible": true, "overallRank": 20, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md", "score": 41.22, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 109, "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": 29.54, "upper": 52.57 }, "rankingEligible": true, "overallRank": 183, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md", "score": 41.06, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 110, "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": 26.39, "upper": 55.34 }, "rankingEligible": true, "overallRank": 205, "url": "https://benchlm.ai/models/ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-9b.md", "score": 40.86, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 111, "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": "supported", "scoreInterval90": { "lower": 31.78, "upper": 49.52 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md", "score": 40.65, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 112, "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": 25.27, "upper": 55.75 }, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.md", "score": 40.51, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 113, "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": 23.35, "upper": 56.28 }, "rankingEligible": true, "overallRank": 210, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md", "score": 39.81, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 10, "scoreConfidence": 2 }, { "rank": 114, "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": 26.92, "upper": 52.32 }, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md", "score": 39.62, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 115, "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": 32.01, "upper": 47.13 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 39.57, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 116, "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": 26.57, "upper": 52.25 }, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md", "score": 39.41, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 117, "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": 30.07, "upper": 48.52 }, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 39.29, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 118, "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": 24.73, "upper": 53.79 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md", "score": 39.26, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 119, "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": 28.87, "upper": 48.37 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "score": 38.62, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 120, "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": "estimated", "scoreInterval90": { "lower": 26.91, "upper": 49.94 }, "rankingEligible": true, "overallRank": 174, "url": "https://benchlm.ai/models/deepseek-v3", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3.md", "score": 38.43, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 121, "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": "supported", "scoreInterval90": { "lower": 22.65, "upper": 53.59 }, "rankingEligible": true, "overallRank": 96, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md", "score": 38.12, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 12, "scoreConfidence": 3 }, { "rank": 122, "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": 22.89, "upper": 52.69 }, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 37.79, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 123, "slug": "gpt-oss-20b", "canonicalModelKey": "gpt-oss-20b", "model": "GPT-OSS 20B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 25.85, "upper": 48.88 }, "rankingEligible": true, "overallRank": 185, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md", "score": 37.37, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 124, "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": 28.81, "upper": 44.84 }, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 36.82, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 125, "slug": "gemma-3-27b", "canonicalModelKey": "gemma-3-27b", "model": "Gemma 3 27B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 41.26, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 24.55, "upper": 47.57 }, "rankingEligible": true, "overallRank": 189, "url": "https://benchlm.ai/models/gemma-3-27b", "markdownUrl": "https://benchlm.ai/md/models/gemma-3-27b.md", "score": 36.06, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 126, "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": 21.24, "upper": 49.68 }, "rankingEligible": true, "overallRank": 49, "url": "https://benchlm.ai/models/minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-7.md", "score": 35.46, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 16, "scoreConfidence": 1 }, { "rank": 127, "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": "estimated", "scoreInterval90": { "lower": 23.6, "upper": 46.63 }, "rankingEligible": true, "overallRank": 200, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md", "score": 35.12, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 128, "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": "supported", "scoreInterval90": { "lower": 25.31, "upper": 42.88 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md", "score": 34.09, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 129, "slug": "gpt-4o-mini", "canonicalModelKey": "gpt-4o-mini", "model": "GPT-4o mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 37.43, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 22.17, "upper": 45.2 }, "rankingEligible": true, "overallRank": 204, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md", "score": 33.68, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 130, "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": "supported", "scoreInterval90": { "lower": 16.22, "upper": 49.41 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md", "score": 32.81, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 36, "scoreConfidence": 3 }, { "rank": 131, "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": 18.75, "upper": 45.07 }, "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", "score": 31.91, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 132, "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": 20.33, "upper": 43.45 }, "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", "score": 31.89, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 133, "slug": "ministral-3-14b", "canonicalModelKey": "ministral-3-14b", "model": "Ministral 3 14B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 20.18, "upper": 43.21 }, "rankingEligible": true, "overallRank": 209, "url": "https://benchlm.ai/models/ministral-3-14b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b.md", "score": 31.69, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 134, "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": 15.58, "upper": 41.89 }, "rankingEligible": true, "overallRank": 225, "url": "https://benchlm.ai/models/minicpm5-1b", "markdownUrl": "https://benchlm.ai/md/models/minicpm5-1b.md", "score": 28.73, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 135, "slug": "grok-build-0-1", "canonicalModelKey": "grok-build-0-1", "model": "Grok Build 0.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 14.72, "upper": 40.16 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-build-0-1", "markdownUrl": "https://benchlm.ai/md/models/grok-build-0-1.md", "score": 27.44, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 136, "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": 13.28, "upper": 37.87 }, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md", "score": 25.58, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 137, "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": "estimated", "scoreInterval90": { "lower": 12.5, "upper": 35.53 }, "rankingEligible": true, "overallRank": 215, "url": "https://benchlm.ai/models/llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/models/llama-4-maverick.md", "score": 24.01, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 138, "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": 16.35, "upper": 30.88 }, "rankingEligible": true, "overallRank": 73, "url": "https://benchlm.ai/models/gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-flash.md", "score": 23.61, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 139, "slug": "ministral-3-8b", "canonicalModelKey": "ministral-3-8b", "model": "Ministral 3 8B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 20.38, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 10.92, "upper": 33.95 }, "rankingEligible": true, "overallRank": 219, "url": "https://benchlm.ai/models/ministral-3-8b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b.md", "score": 22.44, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 140, "slug": "ministral-3-3b", "canonicalModelKey": "ministral-3-3b", "model": "Ministral 3 3B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 17.93, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 9.38, "upper": 32.41 }, "rankingEligible": true, "overallRank": 222, "url": "https://benchlm.ai/models/ministral-3-3b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b.md", "score": 20.89, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 141, "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": "supported", "scoreInterval90": { "lower": 0, "upper": 36.8 }, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "score": 12.19, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 142, "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": 0, "upper": 26.21 }, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md", "score": 6.22, "rankingMode": "bench-align-v5", "category": "agentic", "categoryLabel": "Agentic", "trustedBenchmarkCount": 6, "scoreConfidence": 1 } ], "coding": [ { "rank": 1, "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": 76.32, "upper": 85.85 }, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md", "score": 81.08, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 2, "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": "supported", "scoreInterval90": { "lower": 73.15, "upper": 85.72 }, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md", "score": 79.44, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 3, "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": 73.8, "upper": 83.81 }, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md", "score": 78.81, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 3 }, { "rank": 4, "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": 70.87, "upper": 86.54 }, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md", "score": 78.71, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 30, "scoreConfidence": 2 }, { "rank": 5, "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": 68.97, "upper": 87.36 }, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md", "score": 78.16, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 59, "scoreConfidence": 3 }, { "rank": 6, "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": "supported", "scoreInterval90": { "lower": 67.28, "upper": 79 }, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md", "score": 73.14, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 7, "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": "supported", "scoreInterval90": { "lower": 65.05, "upper": 79.27 }, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md", "score": 72.16, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 8, "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": 65.8, "upper": 78.38 }, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "score": 72.09, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 9, "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": "supported", "scoreInterval90": { "lower": 62.86, "upper": 78.28 }, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md", "score": 70.57, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 10, "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": "supported", "scoreInterval90": { "lower": 57.68, "upper": 81.06 }, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md", "score": 69.37, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 11, "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": 57.34, "upper": 80.36 }, "rankingEligible": true, "overallRank": 7, "url": "https://benchlm.ai/models/hy4-preview", "markdownUrl": "https://benchlm.ai/md/models/hy4-preview.md", "score": 68.85, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 12, "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": 62.54, "upper": 74.56 }, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md", "score": 68.55, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 13, "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": "supported", "scoreInterval90": { "lower": 58.03, "upper": 78.45 }, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md", "score": 68.24, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 14, "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": 49.97, "upper": 83.26 }, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 66.62, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 15, "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": "supported", "scoreInterval90": { "lower": 51.33, "upper": 81.41 }, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md", "score": 66.37, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 16, "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": 57.2, "upper": 75.23 }, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md", "score": 66.22, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 19, "scoreConfidence": 2 }, { "rank": 17, "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": 55.5, "upper": 75.47 }, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md", "score": 65.49, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 18, "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": 51.31, "upper": 79.32 }, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md", "score": 65.32, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 19, "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": 50.07, "upper": 80.55 }, "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", "score": 65.31, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 20, "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": "supported", "scoreInterval90": { "lower": 51.74, "upper": 78.39 }, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md", "score": 65.07, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 21, "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": "supported", "scoreInterval90": { "lower": 56.76, "upper": 73.04 }, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md", "score": 64.9, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 22, "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": 56.73, "upper": 71.64 }, "rankingEligible": true, "overallRank": 19, "url": "https://benchlm.ai/models/muse-spark", "markdownUrl": "https://benchlm.ai/md/models/muse-spark.md", "score": 64.19, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 23, "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": 56.65, "upper": 71.48 }, "rankingEligible": true, "overallRank": 24, "url": "https://benchlm.ai/models/hy3", "markdownUrl": "https://benchlm.ai/md/models/hy3.md", "score": 64.06, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 24, "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": "supported", "scoreInterval90": { "lower": 44.27, "upper": 83.23 }, "rankingEligible": true, "overallRank": 47, "url": "https://benchlm.ai/models/grok-4-6", "markdownUrl": "https://benchlm.ai/md/models/grok-4-6.md", "score": 63.75, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 25, "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": "estimated", "scoreInterval90": { "lower": 46.49, "upper": 80.62 }, "rankingEligible": true, "overallRank": 34, "url": "https://benchlm.ai/models/gpt-5-3-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-3-codex.md", "score": 63.56, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 26, "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": "supported", "scoreInterval90": { "lower": 43.16, "upper": 83.46 }, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md", "score": 63.31, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 27, "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": "supported", "scoreInterval90": { "lower": 47.08, "upper": 78.81 }, "rankingEligible": true, "overallRank": 55, "url": "https://benchlm.ai/models/muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-2.md", "score": 62.94, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 28, "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": 55.25, "upper": 69.86 }, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md", "score": 62.56, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 29, "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": "supported", "scoreInterval90": { "lower": 52.11, "upper": 72.78 }, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 62.44, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 30, "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": "estimated", "scoreInterval90": { "lower": 50.64, "upper": 73.66 }, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md", "score": 62.15, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 31, "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": 52.23, "upper": 71.63 }, "rankingEligible": true, "overallRank": 23, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md", "score": 61.93, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 32, "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": 44.08, "upper": 79.36 }, "rankingEligible": true, "overallRank": 21, "url": "https://benchlm.ai/models/dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/models/dots3-note-preview.md", "score": 61.72, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 26, "scoreConfidence": 3 }, { "rank": 33, "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": "estimated", "scoreInterval90": { "lower": 50.08, "upper": 73.11 }, "rankingEligible": true, "overallRank": 30, "url": "https://benchlm.ai/models/mimo-v2-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-pro.md", "score": 61.6, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 34, "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": "estimated", "scoreInterval90": { "lower": 49.94, "upper": 72.97 }, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 61.46, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 35, "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": 49.93, "upper": 72.96 }, "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", "score": 61.44, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 36, "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": 43.58, "upper": 78.71 }, "rankingEligible": true, "overallRank": 25, "url": "https://benchlm.ai/models/ornith-1-5-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-397b.md", "score": 61.15, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 37, "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": "estimated", "scoreInterval90": { "lower": 49.41, "upper": 72.44 }, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 60.92, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 38, "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": 45.15, "upper": 73.04 }, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md", "score": 59.1, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 32, "scoreConfidence": 3 }, { "rank": 39, "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": 39.35, "upper": 78.59 }, "rankingEligible": true, "overallRank": 11, "url": "https://benchlm.ai/models/grok-4-5", "markdownUrl": "https://benchlm.ai/md/models/grok-4-5.md", "score": 58.97, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 40, "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": "estimated", "scoreInterval90": { "lower": 47.08, "upper": 70.56 }, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 58.82, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 41, "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": "estimated", "scoreInterval90": { "lower": 47.04, "upper": 70.07 }, "rankingEligible": true, "overallRank": 69, "url": "https://benchlm.ai/models/qwen3-6-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-max-preview.md", "score": 58.56, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 42, "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": 50.56, "upper": 66.5 }, "rankingEligible": true, "overallRank": 41, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md", "score": 58.53, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 43, "slug": "glm-5v-turbo", "canonicalModelKey": "glm-5v-turbo", "model": "GLM-5V-Turbo", "creator": "Z.AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 62.09, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 45.96, "upper": 68.98 }, "rankingEligible": true, "overallRank": 53, "url": "https://benchlm.ai/models/glm-5v-turbo", "markdownUrl": "https://benchlm.ai/md/models/glm-5v-turbo.md", "score": 57.47, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 44, "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": "estimated", "scoreInterval90": { "lower": 45.3, "upper": 68.33 }, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 56.82, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 45, "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": 45.15, "upper": 68.18 }, "rankingEligible": true, "overallRank": 99, "url": "https://benchlm.ai/models/apodex-1-1", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1.md", "score": 56.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 46, "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": 45.32, "upper": 67.41 }, "rankingEligible": true, "overallRank": 20, "url": "https://benchlm.ai/models/mimo-v2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5-pro.md", "score": 56.36, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 47, "slug": "gpt-5-2-codex", "canonicalModelKey": "gpt-5-2-codex", "model": "GPT-5.2-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 57.86, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 33.19, "upper": 79.44 }, "rankingEligible": true, "overallRank": 88, "url": "https://benchlm.ai/models/gpt-5-2-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2-codex.md", "score": 56.31, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 48, "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": 41.84, "upper": 69.26 }, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "score": 55.55, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 49, "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": "estimated", "scoreInterval90": { "lower": 36.35, "upper": 73.69 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md", "score": 55.02, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 50, "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": 44.22, "upper": 65.22 }, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.md", "score": 54.72, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 51, "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": 37.88, "upper": 71.43 }, "rankingEligible": true, "overallRank": 70, "url": "https://benchlm.ai/models/kimi-k2-5-reasoning", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5-reasoning.md", "score": 54.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 52, "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": "estimated", "scoreInterval90": { "lower": 43.06, "upper": 66.09 }, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": 54.57, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 53, "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": 42.63, "upper": 65.66 }, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md", "score": 54.15, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 54, "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": "estimated", "scoreInterval90": { "lower": 33.6, "upper": 74.59 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-s-2-1.md", "score": 54.09, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 55, "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": "supported", "scoreInterval90": { "lower": 41.65, "upper": 66.45 }, "rankingEligible": true, "overallRank": 110, "url": "https://benchlm.ai/models/kimi-k2-7-code", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-7-code.md", "score": 54.05, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 56, "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": 42.44, "upper": 65.47 }, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md", "score": 53.95, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 57, "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": 36.51, "upper": 71.29 }, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 53.9, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 58, "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": "estimated", "scoreInterval90": { "lower": 32.99, "upper": 74.8 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/btl-4", "markdownUrl": "https://benchlm.ai/md/models/btl-4.md", "score": 53.9, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 59, "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": "estimated", "scoreInterval90": { "lower": 42.37, "upper": 65.4 }, "rankingEligible": true, "overallRank": 115, "url": "https://benchlm.ai/models/mimo-v2-flash", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-flash.md", "score": 53.89, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 60, "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": 42.14, "upper": 65.17 }, "rankingEligible": true, "overallRank": 114, "url": "https://benchlm.ai/models/gpt-5-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1.md", "score": 53.65, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 61, "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": "estimated", "scoreInterval90": { "lower": 33.69, "upper": 72.69 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-35b.md", "score": 53.19, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 62, "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": 46, "upper": 60.31 }, "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", "score": 53.16, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 63, "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": "estimated", "scoreInterval90": { "lower": 32.73, "upper": 73.26 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-glimmer-30b", "markdownUrl": "https://benchlm.ai/md/models/muse-glimmer-30b.md", "score": 52.99, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 64, "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": "estimated", "scoreInterval90": { "lower": 32.95, "upper": 73.02 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md", "score": 52.99, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 65, "slug": "gpt-5-medium", "canonicalModelKey": "gpt-5-medium", "model": "GPT-5 (medium)", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 54.06, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.26, "upper": 64.29 }, "rankingEligible": true, "overallRank": 109, "url": "https://benchlm.ai/models/gpt-5-medium", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-medium.md", "score": 52.77, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 66, "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": 43.32, "upper": 62.05 }, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 52.69, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 67, "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": 45.28, "upper": 60.05 }, "rankingEligible": true, "overallRank": 66, "url": "https://benchlm.ai/models/glm-4-7", "markdownUrl": "https://benchlm.ai/md/models/glm-4-7.md", "score": 52.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 68, "slug": "minimax-m2-5", "canonicalModelKey": "minimax-m2-5", "model": "MiniMax M2.5", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.49, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 41.04, "upper": 64.07 }, "rankingEligible": true, "overallRank": 85, "url": "https://benchlm.ai/models/minimax-m2-5", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-5.md", "score": 52.56, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 69, "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": "estimated", "scoreInterval90": { "lower": 33.85, "upper": 71.22 }, "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", "score": 52.54, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 70, "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": 35.7, "upper": 68.2 }, "rankingEligible": true, "overallRank": 106, "url": "https://benchlm.ai/models/claude-sonnet-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5.md", "score": 51.95, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 9, "scoreConfidence": 2 }, { "rank": 71, "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": 32.86, "upper": 70.58 }, "rankingEligible": true, "overallRank": 135, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md", "score": 51.72, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 72, "slug": "deepseek-v3-2-thinking", "canonicalModelKey": "deepseek-v3-2-thinking", "model": "DeepSeek V3.2 (Thinking)", "creator": "DeepSeek", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 58.89, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 40.14, "upper": 63.17 }, "rankingEligible": true, "overallRank": 82, "url": "https://benchlm.ai/models/deepseek-v3-2-thinking", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2-thinking.md", "score": 51.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 73, "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": 39.5, "upper": 62.53 }, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md", "score": 51.02, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 39, "scoreConfidence": 3 }, { "rank": 74, "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": 39.49, "upper": 62.52 }, "rankingEligible": true, "overallRank": 127, "url": "https://benchlm.ai/models/step-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/step-3-7-flash.md", "score": 51.01, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 10, "scoreConfidence": 1 }, { "rank": 75, "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": "supported", "scoreInterval90": { "lower": 43.12, "upper": 58.77 }, "rankingEligible": true, "overallRank": 78, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md", "score": 50.94, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 76, "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": "supported", "scoreInterval90": { "lower": 39.8, "upper": 61.55 }, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "score": 50.68, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 77, "slug": "grok-4-1-fast-reasoning", "canonicalModelKey": "grok-4-1-fast-reasoning", "model": "Grok 4.1 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 59.55, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 39, "upper": 62.03 }, "rankingEligible": true, "overallRank": 76, "url": "https://benchlm.ai/models/grok-4-1-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-1-fast-reasoning.md", "score": 50.52, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 78, "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": "supported", "scoreInterval90": { "lower": 42.51, "upper": 58.34 }, "rankingEligible": true, "overallRank": 57, "url": "https://benchlm.ai/models/deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-0813.md", "score": 50.43, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 79, "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": "estimated", "scoreInterval90": { "lower": 31.28, "upper": 69.49 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-9b.md", "score": 50.38, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 80, "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": "estimated", "scoreInterval90": { "lower": 38.86, "upper": 61.89 }, "rankingEligible": true, "overallRank": 107, "url": "https://benchlm.ai/models/glm-4-6", "markdownUrl": "https://benchlm.ai/md/models/glm-4-6.md", "score": 50.38, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 81, "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": 38.79, "upper": 61.81 }, "rankingEligible": true, "overallRank": 146, "url": "https://benchlm.ai/models/o1", "markdownUrl": "https://benchlm.ai/md/models/o1.md", "score": 50.3, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 82, "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": 31.86, "upper": 68.73 }, "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", "score": 50.29, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 83, "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": "estimated", "scoreInterval90": { "lower": 38.59, "upper": 61.62 }, "rankingEligible": true, "overallRank": 105, "url": "https://benchlm.ai/models/deepseek-v3-2", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3-2.md", "score": 50.11, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 84, "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": "estimated", "scoreInterval90": { "lower": 30.65, "upper": 69.28 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/models/zaya1-74b-preview.md", "score": 49.96, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 85, "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": "supported", "scoreInterval90": { "lower": 41.77, "upper": 56.87 }, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md", "score": 49.32, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 86, "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": "estimated", "scoreInterval90": { "lower": 37.77, "upper": 60.8 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md", "score": 49.28, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 87, "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": "estimated", "scoreInterval90": { "lower": 31.83, "upper": 66.48 }, "rankingEligible": true, "overallRank": 128, "url": "https://benchlm.ai/models/gpt-4-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1.md", "score": 49.16, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 88, "slug": "gpt-5-1-codex", "canonicalModelKey": "gpt-5-1-codex", "model": "GPT-5.1-Codex", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "400K", "contextWindowTokens": 400000, "displayScore": 52.63, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 37.61, "upper": 60.64 }, "rankingEligible": true, "overallRank": 119, "url": "https://benchlm.ai/models/gpt-5-1-codex", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-1-codex.md", "score": 49.13, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 89, "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": "estimated", "scoreInterval90": { "lower": 37.24, "upper": 60.26 }, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": 48.75, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 90, "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": 38.08, "upper": 59.24 }, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "score": 48.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 91, "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": 32.38, "upper": 64.78 }, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md", "score": 48.58, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 92, "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": 36.81, "upper": 59.84 }, "rankingEligible": true, "overallRank": 154, "url": "https://benchlm.ai/models/gemma-4-12b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-12b.md", "score": 48.32, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 93, "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": 38.7, "upper": 57.58 }, "rankingEligible": true, "overallRank": 71, "url": "https://benchlm.ai/models/gemma-4-31b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-31b.md", "score": 48.14, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 94, "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": 36.26, "upper": 59.28 }, "rankingEligible": true, "overallRank": 151, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md", "score": 47.77, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 95, "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": 36.18, "upper": 59.21 }, "rankingEligible": true, "overallRank": 91, "url": "https://benchlm.ai/models/claude-haiku-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5.md", "score": 47.7, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 96, "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": "estimated", "scoreInterval90": { "lower": 28.19, "upper": 67.11 }, "rankingEligible": true, "overallRank": 158, "url": "https://benchlm.ai/models/o3-mini", "markdownUrl": "https://benchlm.ai/md/models/o3-mini.md", "score": 47.65, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 97, "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": "estimated", "scoreInterval90": { "lower": 36.09, "upper": 59.11 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md", "score": 47.6, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 98, "slug": "o1-preview", "canonicalModelKey": "o1-preview", "model": "o1-preview", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 48.48, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 36.07, "upper": 59.09 }, "rankingEligible": true, "overallRank": 143, "url": "https://benchlm.ai/models/o1-preview", "markdownUrl": "https://benchlm.ai/md/models/o1-preview.md", "score": 47.58, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 99, "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": 32.53, "upper": 62.53 }, "rankingEligible": true, "overallRank": 176, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md", "score": 47.53, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 100, "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": "supported", "scoreInterval90": { "lower": 33.58, "upper": 61.26 }, "rankingEligible": true, "overallRank": 96, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md", "score": 47.42, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 12, "scoreConfidence": 3 }, { "rank": 101, "slug": "gpt-oss-120b", "canonicalModelKey": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.22, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 35.84, "upper": 58.87 }, "rankingEligible": true, "overallRank": 141, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md", "score": 47.36, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 102, "slug": "mistral-small-4", "canonicalModelKey": "mistral-small-4", "model": "Mistral Small 4", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 46.35, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 35.68, "upper": 58.71 }, "rankingEligible": true, "overallRank": 160, "url": "https://benchlm.ai/models/mistral-small-4", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4.md", "score": 47.2, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 103, "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": "supported", "scoreInterval90": { "lower": 29.07, "upper": 64.95 }, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md", "score": 47.01, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 36, "scoreConfidence": 3 }, { "rank": 104, "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": 34.88, "upper": 57.91 }, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md", "score": 46.4, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 105, "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": 34.84, "upper": 57.87 }, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md", "score": 46.35, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 106, "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": 34.81, "upper": 57.84 }, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md", "score": 46.33, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 107, "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": "estimated", "scoreInterval90": { "lower": 26.9, "upper": 65.68 }, "rankingEligible": true, "overallRank": 170, "url": "https://benchlm.ai/models/claude-4-1-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-4-1-opus.md", "score": 46.29, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 108, "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": 37.73, "upper": 54.58 }, "rankingEligible": true, "overallRank": 93, "url": "https://benchlm.ai/models/gemma-4-26b-a4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-26b-a4b.md", "score": 46.16, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 109, "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": 32.93, "upper": 58.67 }, "rankingEligible": true, "overallRank": 73, "url": "https://benchlm.ai/models/gemini-3-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-flash.md", "score": 45.8, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 110, "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": 31.44, "upper": 59.45 }, "rankingEligible": true, "overallRank": 49, "url": "https://benchlm.ai/models/minimax-m2-7", "markdownUrl": "https://benchlm.ai/md/models/minimax-m2-7.md", "score": 45.45, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 1 }, { "rank": 111, "slug": "grok-4-fast-reasoning", "canonicalModelKey": "grok-4-fast-reasoning", "model": "Grok 4 Fast (Reasoning)", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 55.76, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 33.91, "upper": 56.94 }, "rankingEligible": true, "overallRank": 101, "url": "https://benchlm.ai/models/grok-4-fast-reasoning", "markdownUrl": "https://benchlm.ai/md/models/grok-4-fast-reasoning.md", "score": 45.42, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 112, "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": 33.86, "upper": 56.89 }, "rankingEligible": true, "overallRank": 173, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md", "score": 45.38, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 113, "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": "estimated", "scoreInterval90": { "lower": 33.43, "upper": 56.45 }, "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", "score": 44.94, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 114, "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": 26.2, "upper": 62.53 }, "rankingEligible": true, "overallRank": 205, "url": "https://benchlm.ai/models/ornith-1-5-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-5-9b.md", "score": 44.36, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 12, "scoreConfidence": 2 }, { "rank": 115, "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": 32.61, "upper": 55.64 }, "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", "score": 44.12, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 116, "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": "estimated", "scoreInterval90": { "lower": 24.33, "upper": 62.92 }, "rankingEligible": true, "overallRank": 187, "url": "https://benchlm.ai/models/claude-4-sonnet", "markdownUrl": "https://benchlm.ai/md/models/claude-4-sonnet.md", "score": 43.62, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 117, "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": 31.47, "upper": 54.72 }, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md", "score": 43.1, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 118, "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": 31.51, "upper": 54.54 }, "rankingEligible": true, "overallRank": 183, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md", "score": 43.03, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 119, "slug": "gemma-4-e4b", "canonicalModelKey": "gemma-4-e4b", "model": "Gemma 4 E4B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 43.37, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.44, "upper": 54.46 }, "rankingEligible": true, "overallRank": 178, "url": "https://benchlm.ai/models/gemma-4-e4b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e4b.md", "score": 42.95, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 120, "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": "estimated", "scoreInterval90": { "lower": 31.29, "upper": 54.32 }, "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", "score": 42.81, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 121, "slug": "grok-build-0-1", "canonicalModelKey": "grok-build-0-1", "model": "Grok Build 0.1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 31.19, "upper": 54.22 }, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-build-0-1", "markdownUrl": "https://benchlm.ai/md/models/grok-build-0-1.md", "score": 42.7, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 122, "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": "estimated", "scoreInterval90": { "lower": 31.16, "upper": 54.18 }, "rankingEligible": true, "overallRank": 174, "url": "https://benchlm.ai/models/deepseek-v3", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v3.md", "score": 42.67, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 123, "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": 30.98, "upper": 54.01 }, "rankingEligible": true, "overallRank": 181, "url": "https://benchlm.ai/models/lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-2-6b.md", "score": 42.49, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 124, "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": "estimated", "scoreInterval90": { "lower": 30.98, "upper": 54.01 }, "rankingEligible": true, "overallRank": 152, "url": "https://benchlm.ai/models/qwen3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-flash.md", "score": 42.49, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 125, "slug": "gemma-4-e2b", "canonicalModelKey": "gemma-4-e2b", "model": "Gemma 4 E2B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.33, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 30.72, "upper": 53.75 }, "rankingEligible": true, "overallRank": 184, "url": "https://benchlm.ai/models/gemma-4-e2b", "markdownUrl": "https://benchlm.ai/md/models/gemma-4-e2b.md", "score": 42.24, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 126, "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": 26.18, "upper": 58.1 }, "rankingEligible": true, "overallRank": 32, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md", "score": 42.14, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 127, "slug": "gpt-oss-20b", "canonicalModelKey": "gpt-oss-20b", "model": "GPT-OSS 20B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 29.28, "upper": 52.31 }, "rankingEligible": true, "overallRank": 185, "url": "https://benchlm.ai/models/gpt-oss-20b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-20b.md", "score": 40.8, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 128, "slug": "gpt-5-mini", "canonicalModelKey": "gpt-5-mini", "model": "GPT-5 mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 42.97, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 28.74, "upper": 51.76 }, "rankingEligible": true, "overallRank": 180, "url": "https://benchlm.ai/models/gpt-5-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-mini.md", "score": 40.25, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 129, "slug": "claude-3-opus", "canonicalModelKey": "claude-3-opus", "model": "Claude 3 Opus", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 40.57, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 27.93, "upper": 50.96 }, "rankingEligible": true, "overallRank": 193, "url": "https://benchlm.ai/models/claude-3-opus", "markdownUrl": "https://benchlm.ai/md/models/claude-3-opus.md", "score": 39.45, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 130, "slug": "gemma-3-27b", "canonicalModelKey": "gemma-3-27b", "model": "Gemma 3 27B", "creator": "Google", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": 41.26, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 26.5, "upper": 49.53 }, "rankingEligible": true, "overallRank": 189, "url": "https://benchlm.ai/models/gemma-3-27b", "markdownUrl": "https://benchlm.ai/md/models/gemma-3-27b.md", "score": 38.02, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 131, "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": 27.73, "upper": 47.37 }, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md", "score": 37.55, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 132, "slug": "gemini-1-5-pro", "canonicalModelKey": "gemini-1-5-pro", "model": "Gemini 1.5 Pro", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": 35.14, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 25.15, "upper": 48.18 }, "rankingEligible": true, "overallRank": 207, "url": "https://benchlm.ai/models/gemini-1-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-1-5-pro.md", "score": 36.66, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 133, "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": "estimated", "scoreInterval90": { "lower": 24.99, "upper": 48.02 }, "rankingEligible": true, "overallRank": 200, "url": "https://benchlm.ai/models/llama-4-scout", "markdownUrl": "https://benchlm.ai/md/models/llama-4-scout.md", "score": 36.51, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 134, "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": 19.64, "upper": 52.83 }, "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", "score": 36.24, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 135, "slug": "gpt-4o-mini", "canonicalModelKey": "gpt-4o-mini", "model": "GPT-4o mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 37.43, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 24.23, "upper": 47.26 }, "rankingEligible": true, "overallRank": 204, "url": "https://benchlm.ai/models/gpt-4o-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini.md", "score": 35.75, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 136, "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": 21.27, "upper": 49.79 }, "rankingEligible": true, "overallRank": 94, "url": "https://benchlm.ai/models/gemini-2-5-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro.md", "score": 35.53, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 137, "slug": "ministral-3-14b", "canonicalModelKey": "ministral-3-14b", "model": "Ministral 3 14B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 34, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 22.55, "upper": 45.58 }, "rankingEligible": true, "overallRank": 209, "url": "https://benchlm.ai/models/ministral-3-14b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-14b.md", "score": 34.07, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 138, "slug": "grok-code-fast-1", "canonicalModelKey": "grok-code-fast-1", "model": "Grok Code Fast 1", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": 37.73, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 22.04, "upper": 45.07 }, "rankingEligible": true, "overallRank": 203, "url": "https://benchlm.ai/models/grok-code-fast-1", "markdownUrl": "https://benchlm.ai/md/models/grok-code-fast-1.md", "score": 33.56, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 139, "slug": "trinity-large-thinking", "canonicalModelKey": "trinity-large-thinking", "model": "Trinity-Large-Thinking", "creator": "Arcee AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "512K", "contextWindowTokens": 512000, "displayScore": 47.92, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.9, "upper": 42.45 }, "rankingEligible": true, "overallRank": 148, "url": "https://benchlm.ai/models/trinity-large-thinking", "markdownUrl": "https://benchlm.ai/md/models/trinity-large-thinking.md", "score": 32.17, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 140, "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": "supported", "scoreInterval90": { "lower": 23.94, "upper": 37.92 }, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "score": 30.93, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 141, "slug": "gpt-4-turbo", "canonicalModelKey": "gpt-4-turbo", "model": "GPT-4 Turbo", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 26.85, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 19.23, "upper": 42.25 }, "rankingEligible": true, "overallRank": 211, "url": "https://benchlm.ai/models/gpt-4-turbo", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-turbo.md", "score": 30.74, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 142, "slug": "mistral-large-3", "canonicalModelKey": "mistral-large-3", "model": "Mistral Large 3", "creator": "Mistral", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.6, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "supported", "scoreInterval90": { "lower": 21.24, "upper": 38.58 }, "rankingEligible": true, "overallRank": 139, "url": "https://benchlm.ai/models/mistral-large-3", "markdownUrl": "https://benchlm.ai/md/models/mistral-large-3.md", "score": 29.91, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 143, "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": 11.5, "upper": 47.17 }, "rankingEligible": true, "overallRank": 147, "url": "https://benchlm.ai/models/mercury-2", "markdownUrl": "https://benchlm.ai/md/models/mercury-2.md", "score": 29.33, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 144, "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": "estimated", "scoreInterval90": { "lower": 15.47, "upper": 38.5 }, "rankingEligible": true, "overallRank": 215, "url": "https://benchlm.ai/models/llama-4-maverick", "markdownUrl": "https://benchlm.ai/md/models/llama-4-maverick.md", "score": 26.99, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 145, "slug": "ministral-3-8b", "canonicalModelKey": "ministral-3-8b", "model": "Ministral 3 8B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 20.38, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 12.59, "upper": 35.61 }, "rankingEligible": true, "overallRank": 219, "url": "https://benchlm.ai/models/ministral-3-8b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-8b.md", "score": 24.1, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 146, "slug": "ministral-3-3b", "canonicalModelKey": "ministral-3-3b", "model": "Ministral 3 3B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 17.93, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": "estimated", "scoreInterval90": { "lower": 9.99, "upper": 33.02 }, "rankingEligible": true, "overallRank": 222, "url": "https://benchlm.ai/models/ministral-3-3b", "markdownUrl": "https://benchlm.ai/md/models/ministral-3-3b.md", "score": 21.5, "rankingMode": "bench-align-v5", "category": "coding", "categoryLabel": "Coding", "trustedBenchmarkCount": 0, "scoreConfidence": 1 } ], "reasoning": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 95.5, "rankingMode": "provisional", "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 62.6, "rankingMode": "provisional", "category": "reasoning", "categoryLabel": "Reasoning", "trustedBenchmarkCount": 23, "scoreConfidence": 4 } ], "multimodalGrounded": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md", "score": 88.4, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 30, "scoreConfidence": 2 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "score": 88.4, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 3, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 87.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 4, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md", "score": 86.4, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 59, "scoreConfidence": 3 }, { "rank": 5, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md", "score": 83.2, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 23, "scoreConfidence": 3 }, { "rank": 6, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 82.4, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 7, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md", "score": 81.8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 8, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md", "score": 80.7, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 9, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md", "score": 78.2, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 10, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 19, "url": "https://benchlm.ai/models/muse-spark", "markdownUrl": "https://benchlm.ai/md/models/muse-spark.md", "score": 73.5, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 22, "scoreConfidence": 3 }, { "rank": 11, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md", "score": 71.9, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 12, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md", "score": 70.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 13, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md", "score": 69.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 14, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 67.7, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 15, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md", "score": 65.8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 16, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md", "score": 64.8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 32, "scoreConfidence": 3 }, { "rank": 17, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md", "score": 64.5, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 18, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "score": 61.9, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 19, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 61.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 20, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 60.9, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 21, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md", "score": 60.7, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 22, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 78, "url": "https://benchlm.ai/models/mimo-v2-5", "markdownUrl": "https://benchlm.ai/md/models/mimo-v2-5.md", "score": 57.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 23, "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": null, "scoreInterval90": null, "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", "score": 53.8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 24, "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": null, "scoreInterval90": null, "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", "score": 49.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 25, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md", "score": 45.9, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 36, "scoreConfidence": 3 }, { "rank": 26, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md", "score": 43.5, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 39, "scoreConfidence": 3 }, { "rank": 27, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.md", "score": 43.1, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 28, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md", "score": 42.9, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 29, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md", "score": 42.6, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 30, "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", "score": 39.8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 31, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 102, "url": "https://benchlm.ai/models/grok-4-20-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-beta.md", "score": 30.5, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 32, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 13.5, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 33, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 151, "url": "https://benchlm.ai/models/command-a-plus", "markdownUrl": "https://benchlm.ai/md/models/command-a-plus.md", "score": 8, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 34, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": null, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 35, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": null, "rankingMode": "provisional", "category": "multimodalGrounded", "categoryLabel": "Multimodal & Grounded", "trustedBenchmarkCount": 13, "scoreConfidence": 3 } ], "knowledge": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 3, "url": "https://benchlm.ai/models/claude-opus-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-5.md", "score": 97, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 59, "scoreConfidence": 3 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 1, "url": "https://benchlm.ai/models/claude-fable-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-fable-5-1.md", "score": 97, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 3, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 8, "url": "https://benchlm.ai/models/muse-spark-1-1", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-1.md", "score": 92.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 19, "scoreConfidence": 2 }, { "rank": 4, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "score": 86.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 5, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 4, "url": "https://benchlm.ai/models/gpt-5-6-sol", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-sol.md", "score": 85.9, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 3 }, { "rank": 6, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 39, "url": "https://benchlm.ai/models/claude-sonnet-5", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-5.md", "score": 84.3, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 7, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 14, "url": "https://benchlm.ai/models/gpt-5-6-terra", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-terra.md", "score": 84.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 8, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 87, "url": "https://benchlm.ai/models/gpt-5-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-2.md", "score": 83.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 14, "scoreConfidence": 3 }, { "rank": 9, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 28, "url": "https://benchlm.ai/models/gpt-5-6-luna", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-luna.md", "score": 83.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 10, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 5, "url": "https://benchlm.ai/models/kimi-k3", "markdownUrl": "https://benchlm.ai/md/models/kimi-k3.md", "score": 83.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 30, "scoreConfidence": 2 }, { "rank": 11, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 23, "url": "https://benchlm.ai/models/claude-opus-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-6.md", "score": 82.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 12, "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": null, "scoreInterval90": null, "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", "score": 81.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 13, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 48, "url": "https://benchlm.ai/models/glm-5-2", "markdownUrl": "https://benchlm.ai/md/models/glm-5-2.md", "score": 81, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 15, "scoreConfidence": 2 }, { "rank": 14, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 135, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md", "score": 80.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 15, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "score": 79.9, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 16, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": 79, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 17, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": 77.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 18, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 13, "url": "https://benchlm.ai/models/gpt-5-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-5.md", "score": 77.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 19, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 77.1, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 20, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 41, "url": "https://benchlm.ai/models/claude-sonnet-4-6", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-6.md", "score": 76, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 21, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 12, "url": "https://benchlm.ai/models/gpt-5-4", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4.md", "score": 75.1, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 32, "scoreConfidence": 3 }, { "rank": 22, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 95, "url": "https://benchlm.ai/models/qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507.md", "score": 74.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 23, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "score": 70.1, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 24, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 57, "url": "https://benchlm.ai/models/deepseek-v4-pro-0813", "markdownUrl": "https://benchlm.ai/md/models/deepseek-v4-pro-0813.md", "score": 70, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 2 }, { "rank": 25, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 10, "url": "https://benchlm.ai/models/gemini-3-6-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-6-flash.md", "score": 68.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 2, "scoreConfidence": 1 }, { "rank": 26, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 11, "url": "https://benchlm.ai/models/grok-4-5", "markdownUrl": "https://benchlm.ai/md/models/grok-4-5.md", "score": 68.4, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 27, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 26, "url": "https://benchlm.ai/models/gemini-3-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-pro.md", "score": 68.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 28, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 47, "url": "https://benchlm.ai/models/grok-4-6", "markdownUrl": "https://benchlm.ai/md/models/grok-4-6.md", "score": 68.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 29, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 2, "url": "https://benchlm.ai/models/claude-fable", "markdownUrl": "https://benchlm.ai/md/models/claude-fable.md", "score": 67, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 30, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md", "score": 66.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 31, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 63, "url": "https://benchlm.ai/models/gemini-3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-7-flash.md", "score": 66.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 32, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 98, "url": "https://benchlm.ai/models/gemini-3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-pro.md", "score": 66.4, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 20, "scoreConfidence": 3 }, { "rank": 33, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 64.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 34, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 22, "url": "https://benchlm.ai/models/minimax-m3", "markdownUrl": "https://benchlm.ai/md/models/minimax-m3.md", "score": 63.9, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 16, "scoreConfidence": 2 }, { "rank": 35, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 15, "url": "https://benchlm.ai/models/claude-opus-4-7", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-7.md", "score": 63.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 36, "slug": "claude-opus-4-5-thinking", "canonicalModelKey": "claude-opus-4-5-thinking", "model": "Claude Opus 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": 57.25, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 92, "url": "https://benchlm.ai/models/claude-opus-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5-thinking.md", "score": 63.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 37, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 50, "url": "https://benchlm.ai/models/glm-5-3", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3.md", "score": 63.3, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 8, "scoreConfidence": 1 }, { "rank": 38, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 56, "url": "https://benchlm.ai/models/glm-5-3-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-5-3-flash.md", "score": 62.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 39, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 61.3, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 40, "slug": "gpt-oss-120b", "canonicalModelKey": "gpt-oss-120b", "model": "GPT-OSS 120B", "creator": "OpenAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": 49.22, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 141, "url": "https://benchlm.ai/models/gpt-oss-120b", "markdownUrl": "https://benchlm.ai/md/models/gpt-oss-120b.md", "score": 60.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 1, "scoreConfidence": 1 }, { "rank": 41, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 55, "url": "https://benchlm.ai/models/muse-spark-1-2", "markdownUrl": "https://benchlm.ai/md/models/muse-spark-1-2.md", "score": 60.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 0, "scoreConfidence": 1 }, { "rank": 42, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 60.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 43, "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", "score": 60.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 24, "scoreConfidence": 2 }, { "rank": 44, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 58, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 45, "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": null, "scoreInterval90": null, "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", "score": 57.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 46, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 96, "url": "https://benchlm.ai/models/gpt-5-4-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-mini.md", "score": 57, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 12, "scoreConfidence": 3 }, { "rank": 47, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 55.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 48, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 54.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 49, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 53.5, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 50, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 32, "url": "https://benchlm.ai/models/gpt-5-4-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-4-nano.md", "score": 51.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 51, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md", "score": 51.6, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 52, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "score": 51.2, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 53, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "score": 50.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 54, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 113, "url": "https://benchlm.ai/models/qwen3-6-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-27b.md", "score": 46.7, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 36, "scoreConfidence": 3 }, { "rank": 55, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md", "score": 44.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 56, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 123, "url": "https://benchlm.ai/models/qwen3-6-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-35b-a3b.md", "score": 42.8, "rankingMode": "provisional", "category": "knowledge", "categoryLabel": "Knowledge", "trustedBenchmarkCount": 39, "scoreConfidence": 3 } ], "multilingual": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "score": 100, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 82.9, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 3, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 78.9, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 4, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 69.7, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 5, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 69.7, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 6, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 48.7, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 7, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "score": 47.4, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 8, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 38.2, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 9, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": 36.8, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 10, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "score": 36.8, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 11, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": 21.1, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 12, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 95, "url": "https://benchlm.ai/models/qwen3-235b-2507", "markdownUrl": "https://benchlm.ai/md/models/qwen3-235b-2507.md", "score": 1, "rankingMode": "provisional", "category": "multilingual", "categoryLabel": "Multilingual", "trustedBenchmarkCount": 4, "scoreConfidence": 1 } ], "instructionFollowing": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 135, "url": "https://benchlm.ai/models/mai-thinking-1", "markdownUrl": "https://benchlm.ai/md/models/mai-thinking-1.md", "score": 97.8, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 6, "url": "https://benchlm.ai/models/qwen3-8-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max.md", "score": 93.9, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 42, "scoreConfidence": 2 }, { "rank": 3, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 74, "url": "https://benchlm.ai/models/qwen3-5-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-27b.md", "score": 93.9, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 4, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 58, "url": "https://benchlm.ai/models/agents-a1", "markdownUrl": "https://benchlm.ai/md/models/agents-a1.md", "score": 93.9, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 5, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 45, "url": "https://benchlm.ai/models/inkling-small", "markdownUrl": "https://benchlm.ai/md/models/inkling-small.md", "score": 92.8, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 18, "scoreConfidence": 3 }, { "rank": 6, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 21, "url": "https://benchlm.ai/models/dots3-note-preview", "markdownUrl": "https://benchlm.ai/md/models/dots3-note-preview.md", "score": 92.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 26, "scoreConfidence": 3 }, { "rank": 7, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 164, "url": "https://benchlm.ai/models/nemotron-3-ultra", "markdownUrl": "https://benchlm.ai/md/models/nemotron-3-ultra.md", "score": 91.9, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 3 }, { "rank": 8, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 36, "url": "https://benchlm.ai/models/qwen3-7-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-plus.md", "score": 91.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 50, "scoreConfidence": 4 }, { "rank": 9, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 91.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 10, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 64, "url": "https://benchlm.ai/models/qwen3-8-flash-next", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-flash-next.md", "score": 91.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 11, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 44, "url": "https://benchlm.ai/models/grok-4-3", "markdownUrl": "https://benchlm.ai/md/models/grok-4-3.md", "score": 91.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 12, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 158, "url": "https://benchlm.ai/models/o3-mini", "markdownUrl": "https://benchlm.ai/md/models/o3-mini.md", "score": 91.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 13, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 18, "url": "https://benchlm.ai/models/qwen3-7-max", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-max.md", "score": 91, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 33, "scoreConfidence": 4 }, { "rank": 14, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 77, "url": "https://benchlm.ai/models/qwen3-5-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-122b-a10b.md", "score": 89.8, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 15, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 31, "url": "https://benchlm.ai/models/inkling", "markdownUrl": "https://benchlm.ai/md/models/inkling.md", "score": 88.6, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 16, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 17, "url": "https://benchlm.ai/models/qwen3-8-27b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-27b.md", "score": 88.1, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 21, "scoreConfidence": 3 }, { "rank": 17, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 161, "url": "https://benchlm.ai/models/granite-4-2-8b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-2-8b.md", "score": 87.8, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 11, "scoreConfidence": 2 }, { "rank": 18, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 87.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 34, "scoreConfidence": 4 }, { "rank": 19, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 89, "url": "https://benchlm.ai/models/qwen3-5-397b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-397b.md", "score": 87.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 35, "scoreConfidence": 4 }, { "rank": 20, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 86.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 21, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 146, "url": "https://benchlm.ai/models/o1", "markdownUrl": "https://benchlm.ai/md/models/o1.md", "score": 86.3, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 22, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 100, "url": "https://benchlm.ai/models/qwen3-5-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/qwen3-5-35b-a3b.md", "score": 85.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 3 }, { "rank": 23, "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", "score": 83.6, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 24, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 43, "url": "https://benchlm.ai/models/gemini-3-5-flash", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash.md", "score": 82.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 23, "scoreConfidence": 4 }, { "rank": 25, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 112, "url": "https://benchlm.ai/models/ling-3-0-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash.md", "score": 79.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 16, "scoreConfidence": 3 }, { "rank": 26, "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": null, "scoreInterval90": null, "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", "score": 78.7, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 14, "scoreConfidence": 2 }, { "rank": 27, "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", "score": 77.3, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 28, "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": null, "scoreInterval90": null, "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", "score": 76.3, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 29, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 173, "url": "https://benchlm.ai/models/gpt-4-1-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-mini.md", "score": 75.5, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 30, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 128, "url": "https://benchlm.ai/models/gpt-4-1", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1.md", "score": 72.3, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 31, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 183, "url": "https://benchlm.ai/models/gpt-4-1-nano", "markdownUrl": "https://benchlm.ai/md/models/gpt-4-1-nano.md", "score": 60, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 32, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 176, "url": "https://benchlm.ai/models/hy3-preview", "markdownUrl": "https://benchlm.ai/md/models/hy3-preview.md", "score": 59, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 8, "scoreConfidence": 2 }, { "rank": 33, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 56.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 34, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 188, "url": "https://benchlm.ai/models/lfm2-5-8b-a1b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-8b-a1b.md", "score": 55.7, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 35, "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", "score": 53, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 4, "scoreConfidence": 1 }, { "rank": 36, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 181, "url": "https://benchlm.ai/models/lfm2-5-2-6b", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-2-6b.md", "score": 52.1, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 }, { "rank": 37, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 175, "url": "https://benchlm.ai/models/ling-2-6-flash", "markdownUrl": "https://benchlm.ai/md/models/ling-2-6-flash.md", "score": 48.2, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 3, "scoreConfidence": 1 }, { "rank": 38, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 210, "url": "https://benchlm.ai/models/zaya1-8b", "markdownUrl": "https://benchlm.ai/md/models/zaya1-8b.md", "score": 40.8, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 10, "scoreConfidence": 2 }, { "rank": 39, "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", "score": 40.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 40, "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", "score": 38.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 5, "scoreConfidence": 1 }, { "rank": 41, "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", "score": 26.4, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 7, "scoreConfidence": 1 }, { "rank": 42, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 225, "url": "https://benchlm.ai/models/minicpm5-1b", "markdownUrl": "https://benchlm.ai/md/models/minicpm5-1b.md", "score": 24.7, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 13, "scoreConfidence": 2 }, { "rank": 43, "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", "score": 1, "rankingMode": "provisional", "category": "instructionFollowing", "categoryLabel": "Instruction Following", "trustedBenchmarkCount": 6, "scoreConfidence": 1 } ], "math": [ { "rank": 1, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 81, "url": "https://benchlm.ai/models/kimi-2-6", "markdownUrl": "https://benchlm.ai/md/models/kimi-2-6.md", "score": 71.7, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 29, "scoreConfidence": 3 }, { "rank": 2, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 9, "url": "https://benchlm.ai/models/claude-opus-4-8", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-8.md", "score": 66.8, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 30, "scoreConfidence": 3 }, { "rank": 3, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 29, "url": "https://benchlm.ai/models/glm-5-1", "markdownUrl": "https://benchlm.ai/md/models/glm-5-1.md", "score": 64.5, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 17, "scoreConfidence": 2 }, { "rank": 4, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 40, "url": "https://benchlm.ai/models/qwen3-6-plus", "markdownUrl": "https://benchlm.ai/md/models/qwen3-6-plus.md", "score": 62.6, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 39, "scoreConfidence": 4 }, { "rank": 5, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 84, "url": "https://benchlm.ai/models/kimi-k2-5", "markdownUrl": "https://benchlm.ai/md/models/kimi-k2-5.md", "score": 62.5, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 40, "scoreConfidence": 4 }, { "rank": 6, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 46, "url": "https://benchlm.ai/models/claude-opus-4-5", "markdownUrl": "https://benchlm.ai/md/models/claude-opus-4-5.md", "score": 58.4, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 41, "scoreConfidence": 4 }, { "rank": 7, "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": null, "scoreInterval90": null, "rankingEligible": true, "overallRank": 35, "url": "https://benchlm.ai/models/glm-5", "markdownUrl": "https://benchlm.ai/md/models/glm-5.md", "score": 56.9, "rankingMode": "provisional", "category": "math", "categoryLabel": "Mathematics", "trustedBenchmarkCount": 34, "scoreConfidence": 4 } ] } }