{ "schemaVersion": "1.0", "name": "BenchLM models", "description": "Stable model metadata, rankings, benchmark scores, and coverage fields for BenchLM model pages.", "canonicalUrl": "https://benchlm.ai/data/models.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" ], "counts": { "totalModels": 406, "canonicalModels": 302, "rankingEligibleModels": 225 }, "items": [ { "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", "id": 295, "releaseDate": "2026-07-24", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-5", "familyName": "Claude Opus 5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-5", "relatedModelKeys": [ "claude-opus-4-8", "claude-fable-5", "claude-sonnet-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-opus-4-8" }, "scores": { "displayScore": 84, "overallScore": 84, "rawOverallScore": 84, "verifiedDisplayScore": 84, "displayCategoryScores": { "agentic": 84.6, "coding": 83, "reasoning": 83.5, "multimodalGrounded": 86.4, "knowledge": 97, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 84.2, "coding": 83, "reasoning": 83.5, "multimodalGrounded": 86.4, "knowledge": 97, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 3, "categoryRanks": { "agentic": 1, "coding": 5, "multimodalGrounded": 4, "knowledge": 1 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 59, "verifiedBenchmarkCount": 59, "rankableBenchmarkCount": 59, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "frontierBench": 42.7, "browseComp": 90.8, "hleWithTools": 64.7, "deepSearchQa": 95, "draco": 88.6, "multiAgentBrowseCompPrerelease": 93.6, "osWorld2": 70.6, "mcpAtlas": 85.8, "mcpAtlasClaimCoverage": 89.1, "legalAgentBenchAllPass": 23.58, "legalAgentBenchCriterionPass": 93.74, "legalAgentBenchHeldoutAllPass": 11.7, "legalAgentBenchHeldoutCriterionPass": 94.1, "gdpvalAa": 1862, "toolathlonVerified": 80.6, "toolathlonVerifiedPass3": 87, "toolathlonVerifiedPass3All": 73.1, "toolathlonVerifiedAvgTurns": 23.5, "automationBench": 26, "aaAgenticIndex": 59.17, "gdpvalAaNormalized": 66.2, "aaTau3Banking": 42.1, "aaBriefcaseElo": 1720, "aaTerminalBench21": 89.1, "aaEnterpriseOpsGym": 47.5, "aaHarveyLab": 93.5 }, "coding": { "sweVerified": 96, "swePro": 79.2, "sweMultilingual": 89.5, "sweMultimodal": 59.4, "deepSwe": 68.8, "frontierCode": 53.4, "frontierCode11Extended": 63.6, "programBenchEpisode1": 83, "programBench": 93, "cursorBench32": 70, "vulcanBench": 87, "aaCodingIndex": 77.98, "aaSciCode": 55.7, "vulcanCiiV1": 96.4 }, "reasoning": { "arcAgi1": 97.5, "arcAgi2": 90.4, "arcAgi3": 30.16, "lcr": 75.7, "critpt": 29.1 }, "multimodalGrounded": { "chartography": 29.6, "chartographyWithTools": 83, "benchCadVision2Code": 0.366, "benchCadVision2CodeWithTools": 0.821, "gdpPdf": 83.4, "gdpPdfWithTools": 85.5, "officeQa": 78.1, "officeQaPro": 66.9, "aaMmmuPro": 84.7, "designArenaWebsite": 1327 }, "knowledge": { "hle": 64.7, "hleNoTools": 56.3, "healthBench": 67.1, "healthBenchLengthAdjusted": 57.8, "healthBenchProfessional": 59.8, "healthBenchProfessionalRaw": 73.4, "bioMysteryBenchHumanSolvable": 90.1, "bioMysteryBenchHumanDifficult": 49.4, "spatialBenchVerified": 72.5, "singleCellBench": 60.6, "proteinGymHard": 47.7, "proteinDesign": 42.5, "organicChemistryV2": 61.6, "protocolsTroubleshooting": 61.1, "protocolsUnderstanding": 78.4, "artificialAnalysis": 63.05, "aaGpqaDiamond": 93.2, "aaHle": 54.9, "aaOmniscienceIndex": 37.1, "omniscienceAccuracy": 60.9, "omniscienceHallucinationRate": 60.8 }, "multilingual": { "gmmlu": 92.5, "milu": 92.1, "include": 89.8 }, "instructionFollowing": {}, "math": { "imo2026": 42, "riemannBench": 60, "riemannBenchWithTools": 79, "arxivMathJune2026": 90.8, "arxivMathJune2026WithTools": 91.3 } } }, { "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", "id": 282, "releaseDate": "2026-07-16", "market": null, "isRegional": false, "family": { "familyKey": "kimi-3", "familyName": "Kimi K3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-3", "relatedModelKeys": [ "kimi-k2-7-code", "kimi-2-6", "kimi-k2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "kimi-2-6" }, "scores": { "displayScore": 82, "overallScore": 82, "rawOverallScore": 81, "verifiedDisplayScore": 82, "displayCategoryScores": { "agentic": 94.5, "coding": 63, "reasoning": null, "multimodalGrounded": 88.4, "knowledge": 83.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 94.5, "coding": null, "reasoning": null, "multimodalGrounded": 88.4, "knowledge": 83.5, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 5, "categoryRanks": { "agentic": 5, "coding": 4, "multimodalGrounded": 1, "knowledge": 10 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 30, "verifiedBenchmarkCount": 30, "rankableBenchmarkCount": 9, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 88.3, "browseComp": 91.2, "deepSearchQa": 95, "toolathlonVerified": 73.2, "mcpAtlas": 84.2, "automationBench": 30.8, "jobBench": 52.9, "apexAgents": 37.6, "spreadsheetBench2": 34.8, "deckBench": 73.5, "aaAgenticIndex": 54.26, "gdpvalAaNormalized": 58.4, "gdpvalAa": 1668, "aaBriefcaseElo": 1517, "aaAutomationBench": 52.7, "aaEnterpriseOpsGym": 45.3, "aaHarveyLab": 94.6, "aaTau3Banking": 46, "aaTerminalBench21": 85, "apexAgentsAa": 41.3, "aaItbench": 47.7 }, "coding": { "deepSwe": 67.5, "cursorBench32": 60.8, "frontierSwe": 81.2, "programBench": 77.8, "kimiCodeBenchV2": 72.9, "sweMarathon": 42, "postTrainBench": 36.6, "mlsBenchLite": 48.3, "aaCodingIndex": 76.24, "aaSciCode": 58.7, "vulcanBench": 73.7, "openHarmonyBench": 57.3 }, "reasoning": { "lcr": 82.7, "critpt": 23.4 }, "multimodalGrounded": { "officeQaPro": 63.3, "mmmuPro": 81.6, "mmmuProPython": 83.4, "charxivNoTools": 84.8, "charxiv": 91.3, "mathVision": 94.3, "mathVisionPython": 97.8, "babyVisionPython": 85.7, "zeroBench": 23, "zeroBenchPython": 41, "worldVqaForceAnswer": 51, "omniDocBench": 91.1, "perceptionBench": 58.5, "aaMmmuPro": 80.5, "designArenaWebsite": 1363 }, "knowledge": { "gpqa": 93.5, "gpqaDiamond": 93.5, "hle": 56, "hleNoTools": 43.5, "artificialAnalysis": 59.7, "aaGpqaDiamond": 93.5, "aaHle": 46.9, "aaOmniscienceIndex": 19.7, "omniscienceAccuracy": 47.6, "omniscienceHallucinationRate": 53.2, "aaOpennessIndex": 38.9 }, "multilingual": {}, "instructionFollowing": {}, "math": {}, "external": { "exploitBench": 32, "aceCyberRangeSolved": 0, "lastOnesCyberRangeSteps": 17, "lastOnesCyberRangeCompletion": 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": 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", "id": 263, "releaseDate": "2026-07-09", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-6", "familyName": "GPT-5.6", "variantType": "sol", "snapshotLabel": "sol", "baseFamilyModelKey": "gpt-5-6-sol", "relatedModelKeys": [ "gpt-5-6-terra", "gpt-5-6-luna", "gpt-5-6-cyber" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gpt-5-5" }, "scores": { "displayScore": 80, "overallScore": 80, "rawOverallScore": 80, "verifiedDisplayScore": 80, "displayCategoryScores": { "agentic": 94.5, "coding": 55.3, "reasoning": 85.2, "multimodalGrounded": 83.2, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": 97 }, "verifiedDisplayCategoryScores": { "agentic": 94.5, "coding": 53.5, "reasoning": 85.2, "multimodalGrounded": 83.2, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": 97 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 4, "categoryRanks": { "agentic": 10, "coding": 3, "multimodalGrounded": 5, "knowledge": 5 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 23, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "frontierBench": 34.59, "terminalBench2": 91.9, "browseComp": 92.2, "osWorld2": 62.6, "cyberGym": 84.5, "exploitGym": 33.7, "toolathlon": 58, "aaAgenticIndex": 57.78, "tau2Bench": 85.1, "gdpvalAaNormalized": 60.5, "gdpvalAa": 1735, "aaBriefcaseElo": 1494, "aaItbench": 56.2, "aaTau3Banking": 44.3, "aaAutomationBench": 51.2, "aaHarveyLab": 87.2, "terminalBenchHard": 65.9, "aaTerminalBench21": 88, "aaEnterpriseOpsGym": 42.9 }, "coding": { "swePro": 64.6, "terminalBench2": 91.9, "deepSwe": 72.7, "frontierCode11Extended": 60.6, "cursorBench32": 67.2, "vulcanBench": 87, "aaCodingIndex": 77.39, "aaSciCode": 56.1, "vulcanCiiV1": 86.5 }, "reasoning": { "arcAgi2": 92.5, "arcAgi3": 7.78, "geneBenchPro": 28.7, "lcr": 77.7, "critpt": 32.3 }, "multimodalGrounded": { "mmmuPro": 83, "mmmuProPython": 84.6, "aaMmmuPro": 83.4 }, "knowledge": { "gpqa": 94.6, "gpqaDiamond": 94.6, "healthBenchProfessional": 60.5, "healthBenchHard": 33.1, "artificialAnalysis": 58.89, "aaGpqaDiamond": 94.1, "aaHle": 49.5, "aaOmniscienceIndex": 22, "omniscienceAccuracy": 59.4, "omniscienceHallucinationRate": 92.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 72.7 }, "math": { "frontierMath": 89, "frontierMathV2Tiers13": 89, "frontierMathV2Tier4": 83 }, "external": { "exploitBench": 73.5, "secBenchPro": 71.2, "lastOnesCyberRangeCompletion": 70, "advancedCyberCompletionRateStandard": 1.5, "advancedCyberCompletionRateBlue": 2, "frontierCyber": 9.6, "cyScenarioBenchAverageSuccess": 28, "cyScenarioBenchScenariosSolved": 7, "atomicNetworkAttackSimulation": 98, "atomicVulnerabilityResearch": 91, "atomicEvasion": 56 } } }, { "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", "id": 416, "releaseDate": "2026-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-fable", "familyName": "Claude Fable", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-fable-5-1", "relatedModelKeys": [ "claude-fable-5", "claude-mythos-5-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-fable-5" }, "scores": { "displayScore": 79, "overallScore": 79, "rawOverallScore": 79, "verifiedDisplayScore": 79, "displayCategoryScores": { "agentic": 85, "coding": 80.3, "reasoning": 83.1, "multimodalGrounded": null, "knowledge": 97, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 80.3, "reasoning": 83.1, "multimodalGrounded": null, "knowledge": 97, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 1, "categoryRanks": { "agentic": 2, "coding": 2, "knowledge": 2 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench4": 55.8, "terminalBenchScience": 52.6, "osWorld2": 41.7, "automationBench": 31.4, "toolathlonVerified": 77.8, "toolathlonVerifiedPass3": 81.5, "toolathlonVerifiedPass3All": 73.1, "toolathlonVerifiedAvgTurns": 23.7, "aaAgenticIndex": 61.34, "gdpvalAaNormalized": 67.7, "gdpvalAa": 1853, "aaBriefcaseElo": 1694, "aaHarveyLab": 93, "aaTau3Banking": 47.2, "aaTerminalBench21": 91.4 }, "coding": { "swePro": 81.2, "sweMultilingual": 89.1, "sweMultimodal": 54.7, "deepSwe": 67.4, "programBench": 87.6, "cursorBench32": 73.4, "aaCodingIndex": 81.6, "aaSciCode": 62 }, "reasoning": { "arcAgi1": 97.5, "arcAgi2": 90, "lcr": 80, "critpt": 29.7 }, "multimodalGrounded": {}, "knowledge": { "hle": 65, "hleNoTools": 60.9, "artificialAnalysis": 65.65, "aaGpqaDiamond": 93.7, "aaHle": 59.1, "aaOmniscienceIndex": 43.5, "omniscienceAccuracy": 67.2, "omniscienceHallucinationRate": 72.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 257, "releaseDate": "2026-06-09", "market": null, "isRegional": false, "family": { "familyKey": "claude-fable", "familyName": "Claude Fable", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-fable-5", "relatedModelKeys": [ "claude-mythos-5", "claude-fable-5-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 78, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 92.7, "coding": 83, "reasoning": null, "multimodalGrounded": 61.3, "knowledge": 67, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 92.7, "coding": 83, "reasoning": null, "multimodalGrounded": 61.3, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 2, "categoryRanks": { "agentic": 3, "coding": 1, "knowledge": 29 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "frontierBench": 34.05, "terminalBench2": 84.3, "osWorldVerified": 85, "gdpvalAa": 1747, "aaAgenticIndex": 56.59, "tau2Bench": 98.5, "gdpvalAaNormalized": 61.1, "aaBriefcaseElo": 1572, "aaAutomationBench": 48.6, "aaEnterpriseOpsGym": 51.1, "aaHarveyLab": 93.6, "aaTau3Banking": 38.1, "terminalBenchHard": 62.9, "aaTerminalBench21": 84.6 }, "coding": { "sweVerified": 95, "swePro": 80, "frontierCode": 53.5, "terminalBench2": 84.3, "cursorBench31": 70.6, "cursorBench32": 70.5, "vulcanBench": 89.5, "aaCodingIndex": 76.49, "aaSciCode": 60.2 }, "reasoning": { "lcr": 76.7, "critpt": 28.6 }, "multimodalGrounded": { "blueprintBench2": 38.6, "officeQaPro": 57.9, "designArenaWebsite": 1315 }, "knowledge": { "artificialAnalysis": 62.07, "aaGpqaDiamond": 92.6, "aaHle": 55.5, "aaOmniscienceIndex": 43.3, "omniscienceAccuracy": 65.4, "omniscienceHallucinationRate": 63.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 63.5 }, "math": {} } }, { "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", "id": 238, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-8", "familyName": "Claude Opus 4.8", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-8", "relatedModelKeys": [ "claude-opus-4-7-max", "claude-opus-4-7", "claude-opus-4-6" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-opus-4-7-max" }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 76, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 83.1, "coding": 74.9, "reasoning": 68.3, "multimodalGrounded": 88.4, "knowledge": 86.5, "multilingual": null, "instructionFollowing": null, "math": 66.8 }, "verifiedDisplayCategoryScores": { "agentic": 83.1, "coding": 74.9, "reasoning": 68.3, "multimodalGrounded": 88.4, "knowledge": 86.5, "multilingual": null, "instructionFollowing": null, "math": 66.8 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 9, "categoryRanks": { "agentic": 18, "coding": 8, "multimodalGrounded": 2, "knowledge": 4, "math": 2 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": true } }, "coverage": { "trustedBenchmarkCount": 30, "verifiedBenchmarkCount": 30, "rankableBenchmarkCount": 30, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "frontierBench": 21.08, "terminalBench2": 74.6, "browseComp": 84.3, "deepSearchQa": 93.1, "osWorldVerified": 83.4, "financeAgentV2": 53.9, "gdpvalAa": 1593, "mcpAtlas": 82.2, "toolathlon": 59.9, "gertLabs": 72.97, "aaAgenticIndex": 49.37, "tau2Bench": 94.4, "gdpvalAaNormalized": 53.9, "researchClawBench": 21.1, "osWorld2": 20.6 }, "coding": { "sweVerified": 88.6, "swePro": 69.2, "sweMultilingual": 84.4, "sweMultimodal": 38.4, "terminalBench2": 74.6, "cursorBench31": 58.4, "cursorBench32": 62.3, "aaCodingIndex": 74.25, "aaSciCode": 53.5, "frontierCode": 46.5 }, "reasoning": { "arcAgi2": 72.08, "arcAgi3": 1.52, "lcr": 73, "critpt": 20.9 }, "multimodalGrounded": { "officeQaPro": 66.2, "screenSpotPro": 87.9, "charxiv": 89.9, "charxivNoTools": 80.5, "designArenaWebsite": 1271 }, "knowledge": { "gpqa": 93.6, "gpqaDiamond": 93.6, "hle": 57.9, "hleNoTools": 49.8, "artificialAnalysis": 57.33, "aaGpqaDiamond": 92, "aaHle": 48.7, "aaOmniscienceIndex": 28.8, "omniscienceAccuracy": 48.8, "omniscienceHallucinationRate": 39.3 }, "multilingual": { "include": 87.6 }, "instructionFollowing": { "aaIfBench": 62.2 }, "math": { "usamo2026": 96.7, "frontierMathV2Tiers13": 47.241, "frontierMathV2Tier4": 31.25 } } }, { "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", "id": 298, "releaseDate": "2026-08-03", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-8-max", "familyName": "Qwen3.8 Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-8-max", "relatedModelKeys": [ "qwen3-8-max-preview", "qwen3-7-max", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "qwen3-8-max-preview" }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 77, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 86.1, "coding": 59.5, "reasoning": 95.5, "multimodalGrounded": 87.1, "knowledge": 64.6, "multilingual": null, "instructionFollowing": 93.9, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 86.1, "coding": 59.2, "reasoning": 95.5, "multimodalGrounded": 87.1, "knowledge": 63.7, "multilingual": null, "instructionFollowing": 93.9, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 6, "categoryRanks": { "agentic": 4, "coding": 14, "reasoning": 1, "multimodalGrounded": 3, "knowledge": 33, "instructionFollowing": 2 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 42, "verifiedBenchmarkCount": 42, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 86.6, "coworkBench": 74.8, "jobBench": 53.4, "skillsBench": 70.2, "agentsLastExam": 52.4, "automationBench": 27.3, "toolathlonVerified": 72.5, "wideResearch": 81.9, "hleWithTools": 56.2, "osWorldVerified": 86.1, "osWorld2": 19.4, "webArenaVerified": 66.8, "androidWorld": 85.3, "mobileWorld": 77.8 }, "coding": { "terminalBench21": 86.6, "swePro": 67.7, "deepSwe": 56.6, "nl2Repo": 55.9, "frontierSwe": 73.5, "mlsBenchLite": 41, "paperBench": 93, "qwenReactBench": 1724, "vulcanBench": 81.2, "openHarmonyBench": 60.8 }, "reasoning": { "mrcrv2": 92.9, "longBenchV2": 66.3 }, "multimodalGrounded": { "mmmuPro": 82.3, "mathVision": 95.2, "mathVisionPython": 97.7, "babyVision": 82, "babyVisionPython": 91.3, "zeroBench": 24, "zeroBenchPython": 49, "medXpertQaMm": 80.4, "screenSpotPro": 84.5, "vision2Web": 69, "charxivNoTools": 88.4, "charxiv": 93.5, "omniDocBench15": 92.1, "ocrBenchV2": 74.2, "ccOcr": 79.6, "realWorldQa": 88, "erqa": 77.8, "simpleVqa": 75, "perceptionBench": 63.5, "videoMmeWithSub": 90.4, "videoMmmu": 88.7, "mmvu": 82.4, "mlvuAvg": 90.8, "lvBench": 81.8, "designArenaWebsite": 1299 }, "knowledge": { "gpqa": 92.6, "gpqaDiamond": 92.6, "hle": 43.6, "hleNoTools": 43.6 }, "multilingual": {}, "instructionFollowing": { "ifBench": 82.8 }, "math": {} } }, { "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", "id": 15, "releaseDate": "2026-05-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-7-max", "familyName": "Qwen3.7 Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-7-max", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 76, "overallScore": 76, "rawOverallScore": 76, "verifiedDisplayScore": 76, "displayCategoryScores": { "agentic": 64, "coding": 81.7, "reasoning": 78, "multimodalGrounded": null, "knowledge": 70.1, "multilingual": 100, "instructionFollowing": 91, "math": 82.2 }, "verifiedDisplayCategoryScores": { "agentic": 64, "coding": 81.7, "reasoning": 78, "multimodalGrounded": null, "knowledge": 70.1, "multilingual": 100, "instructionFollowing": 91, "math": 82.2 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 18, "categoryRanks": { "agentic": 119, "coding": 48, "knowledge": 23, "multilingual": 1, "instructionFollowing": 13 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 33, "verifiedBenchmarkCount": 33, "rankableBenchmarkCount": 33, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 69.7, "qwenClawBench": 64.3, "qwenWebBench": 1568, "clawEval": 65.2, "bfclV4": 75, "mcpAtlas": 76.4, "vitaBench": 47.9, "hleWithTools": 53.5, "aaAgenticIndex": 30.86, "tau2Bench": 94.7, "gdpvalAaNormalized": 38.2, "gdpvalAa": 1264, "gertLabs": 64.27, "researchClawBench": 18.7 }, "coding": { "sweVerified": 80.4, "swePro": 60.6, "sweMultilingual": 78.3, "nl2Repo": 47.2, "sciCode": 53.5, "liveCodeBench": 91.6, "terminalBench2": 69.7, "aaCodingIndex": 65.97, "aaSciCode": 48.8, "openHarmonyBench": 53.4 }, "reasoning": { "mrcrv2": 90.4, "critpt": 13.4, "lcr": 74.7 }, "multimodalGrounded": { "designArenaWebsite": 1291 }, "knowledge": { "gpqa": 92.4, "gpqaDiamond": 92.4, "hle": 41.4, "mmluPro": 89.6, "mmluRedux": 95, "superGpqa": 73.6, "mmmlu": 90.3, "artificialAnalysis": 46.71, "aaGpqaDiamond": 92.3, "aaHle": 40.5, "aaOmniscienceIndex": 13.5, "omniscienceAccuracy": 31.1, "omniscienceHallucinationRate": 25.6 }, "multilingual": { "mmluProX": 87, "nova63": 59, "include": 86.2, "maxife": 89.2, "polyMath": 86.5 }, "instructionFollowing": { "ifeval": 94.3, "ifBench": 79.1, "aaIfBench": 80.5 }, "math": { "hmmtFeb2026": 97.1, "imoAnswerBench": 90, "apex": 44.5 } } }, { "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", "id": 264, "releaseDate": "2026-07-09", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-6", "familyName": "GPT-5.6", "variantType": "terra", "snapshotLabel": "terra", "baseFamilyModelKey": "gpt-5-6-sol", "relatedModelKeys": [ "gpt-5-6-sol", "gpt-5-6-luna" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 76, "overallScore": 76, "rawOverallScore": 75, "verifiedDisplayScore": 76, "displayCategoryScores": { "agentic": 91.2, "coding": 52.7, "reasoning": 78.1, "multimodalGrounded": 71.9, "knowledge": 84.2, "multilingual": null, "instructionFollowing": null, "math": 97 }, "verifiedDisplayCategoryScores": { "agentic": 91.2, "coding": 51.3, "reasoning": 78.1, "multimodalGrounded": 71.9, "knowledge": 84.2, "multilingual": null, "instructionFollowing": null, "math": 97 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 14, "categoryRanks": { "agentic": 26, "coding": 10, "multimodalGrounded": 11, "knowledge": 7 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 21, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "frontierBench": 20.81, "terminalBench2": 87.4, "browseComp": 87.5, "osWorld2": 50.2, "cyberGym": 81.8, "exploitGym": 23.2, "toolathlon": 53.1, "aaAgenticIndex": 50.2, "tau2Bench": 86.3, "gdpvalAaNormalized": 53.3, "gdpvalAa": 1583, "aaHarveyLab": 85.2, "aaItbench": 51, "aaTau3Banking": 40.2, "aaAutomationBench": 45.6, "terminalBenchHard": 57.6, "aaTerminalBench21": 88, "apexAgentsAa": 38.9, "aaBriefcaseElo": 1344, "aaEnterpriseOpsGym": 38.5 }, "coding": { "swePro": 63.4, "terminalBench2": 87.4, "deepSwe": 69.6, "frontierCode11Extended": 55.8, "cursorBench32": 64.9, "aaCodingIndex": 76.66, "aaSciCode": 53.9, "vulcanBench": 87 }, "reasoning": { "arcAgi2": 83.9, "arcAgi3": 0.8, "lcr": 79.7, "critpt": 30 }, "multimodalGrounded": { "mmmuPro": 80.7, "mmmuProPython": 82, "aaMmmuPro": 80.7 }, "knowledge": { "gpqa": 92.9, "gpqaDiamond": 92.9, "healthBenchProfessional": 57.7, "healthBenchHard": 32.7, "artificialAnalysis": 54.95, "aaGpqaDiamond": 92.5, "aaHle": 42.9, "aaOmniscienceIndex": 0.1, "omniscienceAccuracy": 46.8, "omniscienceHallucinationRate": 87.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.2 }, "math": { "frontierMath": 84.9, "frontierMathV2Tiers13": 84.9, "frontierMathV2Tier4": 68.3 }, "external": { "exploitBench": 52.9 } } }, { "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": "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", "id": 262, "releaseDate": "2026-06-30", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-5", "familyName": "Claude Sonnet 5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-sonnet-5", "relatedModelKeys": [ "claude-sonnet-4-6", "claude-opus-4-8" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-sonnet-4-6" }, "scores": { "displayScore": 75, "overallScore": 75, "rawOverallScore": 73, "verifiedDisplayScore": 75, "displayCategoryScores": { "agentic": 86.2, "coding": 66.2, "reasoning": null, "multimodalGrounded": 76.5, "knowledge": 84.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 86.2, "coding": 66.2, "reasoning": null, "multimodalGrounded": 76.5, "knowledge": 84.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 39, "categoryRanks": { "agentic": 11, "coding": 9, "knowledge": 6 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 15, "verifiedBenchmarkCount": 15, "rankableBenchmarkCount": 15, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "frontierBench": 14.59, "terminalBench2": 80.4, "browseComp": 84.7, "hleWithTools": 57.4, "osWorldVerified": 81.2, "gdpvalAa": 1603, "aaAgenticIndex": 49.72, "gdpvalAaNormalized": 54.2 }, "coding": { "sweVerified": 85.2, "swePro": 63.2, "sweMultilingual": 78.3, "sweMultimodal": 28.1, "terminalBench2": 80.4, "frontierCode": 42.7, "cursorBench32": 61.5, "aaCodingIndex": 71.55, "aaSciCode": 53.6 }, "reasoning": { "lcr": 77, "critpt": 16.9 }, "multimodalGrounded": { "charxiv": 88.3, "charxivNoTools": 77, "aaMmmuPro": 77.3, "designArenaWebsite": 1294 }, "knowledge": { "hle": 57.4, "hleNoTools": 43.2, "artificialAnalysis": 55.26, "aaGpqaDiamond": 91.1, "aaHle": 41.3, "aaOmniscienceIndex": 16.5, "omniscienceAccuracy": 40.1, "omniscienceHallucinationRate": 39.4 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 249, "releaseDate": "2026-06-03", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-7-plus", "familyName": "Qwen3.7 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-7-plus", "relatedModelKeys": [ "qwen3-7-max", "qwen3-6-plus", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "qwen3-6-plus" }, "scores": { "displayScore": 72, "overallScore": 72, "rawOverallScore": 71, "verifiedDisplayScore": 72, "displayCategoryScores": { "agentic": 66.4, "coding": 70.1, "reasoning": 79.7, "multimodalGrounded": 67.7, "knowledge": 61.3, "multilingual": 78.9, "instructionFollowing": 91.4, "math": 78.4 }, "verifiedDisplayCategoryScores": { "agentic": 66.4, "coding": 70.1, "reasoning": 79.7, "multimodalGrounded": 67.7, "knowledge": 61.3, "multilingual": 78.9, "instructionFollowing": 91.4, "math": 78.4 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 36, "categoryRanks": { "agentic": 115, "coding": 40, "multimodalGrounded": 14, "knowledge": 39, "multilingual": 3, "instructionFollowing": 8 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 50, "verifiedBenchmarkCount": 50, "rankableBenchmarkCount": 50, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 70.3, "qwenClawBench": 61.8, "qwenWebBench": 1536, "clawEval": 62.7, "bfclV4": 72.9, "mcpAtlas": 73.2, "vitaBench": 45.6, "deepPlanning": 62.3, "osWorldVerified": 73.3, "androidWorld": 81, "aaAgenticIndex": 20.69, "apexAgentsAa": 22.4, "tau2Bench": 93, "gdpvalAaNormalized": 22.4, "gdpvalAa": 947, "osWorld2": 2.8 }, "coding": { "terminalBench2": 70.3, "sweVerified": 77.7, "swePro": 57.6, "sweMultilingual": 75.8, "nl2Repo": 41.1, "sciCode": 51.3, "liveCodeBench": 89.6, "aaCodingIndex": 55.86, "aaSciCode": 45.5 }, "reasoning": { "critpt": 9.1, "mrcrv2": 91.7, "lcr": 69 }, "multimodalGrounded": { "mmmuPro": 79, "mathVision": 90.3, "charxiv": 85.9, "erqa": 69.8, "medXpertQaMm": 71, "screenSpotPro": 79, "simpleVqa": 81.7, "mmSearchPlus": 41.4, "realWorldQa": 86.9, "omniDocBench15": 91.4, "ocrBenchV2": 70.7, "odinw13": 51.1, "videoMmeWithSub": 88, "videoMmmu": 85.4, "mlvuAvg": 87.4, "aaMmmuPro": 80.5, "designArenaWebsite": 1288 }, "knowledge": { "gpqa": 90.3, "gpqaDiamond": 90.3, "hle": 34.7, "mmluPro": 88.5, "mmluRedux": 94.5, "superGpqa": 71.4, "mmmlu": 89, "artificialAnalysis": 39.37, "aaGpqaDiamond": 90, "aaHle": 35.6, "aaOmniscienceIndex": 1.1, "omniscienceAccuracy": 22.5, "omniscienceHallucinationRate": 27.7 }, "multilingual": { "mmluProX": 85.4, "nova63": 58.8, "include": 83, "maxife": 88.8, "polyMath": 84 }, "instructionFollowing": { "ifeval": 94.6, "ifBench": 79.1, "aaIfBench": 78 }, "math": { "hmmtFeb2026": 92.9, "imoAnswerBench": 86, "apex": 22.7 } } }, { "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", "id": 281, "releaseDate": "2026-07-09", "market": null, "isRegional": false, "family": { "familyKey": "muse-spark", "familyName": "Muse Spark", "variantType": "1.1", "snapshotLabel": "1.1", "baseFamilyModelKey": "muse-spark-1-2", "relatedModelKeys": [ "muse-spark-1-2", "muse-spark" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "muse-spark" }, "scores": { "displayScore": 71, "overallScore": 71, "rawOverallScore": 70, "verifiedDisplayScore": 71, "displayCategoryScores": { "agentic": 84, "coding": 49.8, "reasoning": null, "multimodalGrounded": 76.8, "knowledge": 92.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 84, "coding": 47.8, "reasoning": null, "multimodalGrounded": 76.8, "knowledge": 92.5, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 8, "categoryRanks": { "agentic": 25, "coding": 16, "knowledge": 3 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 19, "verifiedBenchmarkCount": 19, "rankableBenchmarkCount": 19, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 80, "mcpAtlas": 88.1, "toolathlon": 75.6, "osWorldVerified": 80.8, "webArenaVerified": 69, "deepSearchQa": 84.9, "cyberGym": 59, "financeAgentV2": 57.2, "deepSwe": 53.3, "osWorld2": 14.2, "jobBench": 54.7, "cybench": 92.9, "exploitGym": 0.8, "aaAgenticIndex": 39.74, "gdpvalAaNormalized": 43.6, "gdpvalAa": 1375 }, "coding": { "terminalBench2": 80, "swePro": 61.5, "aaCodingIndex": 71.34, "aaSciCode": 58.2 }, "reasoning": { "mrcr1m": 54.1, "lcr": 81.3, "critpt": 15.1 }, "multimodalGrounded": { "charxiv": 88.4, "babyVision": 76.3, "designArenaWebsite": 1286 }, "knowledge": { "hle": 62.1, "hleNoTools": 52.2, "healthBenchProfessional": 59.3, "artificialAnalysis": 53.2, "aaGpqaDiamond": 89.8, "aaHle": 46.2, "aaOmniscienceIndex": 28.1, "omniscienceAccuracy": 52.1, "omniscienceHallucinationRate": 50 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 392, "releaseDate": "2026-08-13", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-7-flash", "familyName": "Gemini 3.7 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-7-flash", "relatedModelKeys": [ "gemini-3-6-flash", "gemini-3-5-flash", "gemini-3-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gemini-3-6-flash" }, "scores": { "displayScore": 71, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 84.3, "coding": 58.5, "reasoning": null, "multimodalGrounded": 70.1, "knowledge": 66.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 63, "categoryRanks": { "agentic": 42, "coding": 15, "multimodalGrounded": 12, "knowledge": 31 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 45.1, "gdpvalAaNormalized": 50.8, "gdpvalAa": 1516, "aaBriefcaseElo": 1134, "aaAutomationBench": 62.7, "aaHarveyLab": 90.7, "aaTau3Banking": 32.8, "aaTerminalBench21": 85.8 }, "coding": { "aaCodingIndex": 76.12, "aaSciCode": 56.8 }, "reasoning": { "lcr": 80, "critpt": 14.3 }, "multimodalGrounded": { "aaMmmuPro": 85.5, "designArenaWebsite": 1321 }, "knowledge": { "artificialAnalysis": 56.03, "aaGpqaDiamond": 94.5, "aaHle": 47.9, "aaOmniscienceIndex": 26.5, "omniscienceAccuracy": 55.3, "omniscienceHallucinationRate": 64.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 32, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-5", "familyName": "GPT-5.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-5", "relatedModelKeys": [ "gpt-5-5-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gpt-5-4" }, "scores": { "displayScore": 70, "overallScore": 69, "rawOverallScore": 69, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 85, "coding": 44.5, "reasoning": 79, "multimodalGrounded": 65.8, "knowledge": 77.5, "multilingual": null, "instructionFollowing": null, "math": 71.1 }, "verifiedDisplayCategoryScores": { "agentic": 85, "coding": 42.5, "reasoning": 79, "multimodalGrounded": 65.8, "knowledge": 77.5, "multilingual": null, "instructionFollowing": null, "math": 71.1 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 13, "categoryRanks": { "agentic": 14, "coding": 7, "multimodalGrounded": 15, "knowledge": 18 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 29, "verifiedBenchmarkCount": 29, "rankableBenchmarkCount": 29, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 82, "cyberGym": 81.8, "browseComp": 84.4, "osWorldVerified": 78.7, "mcpAtlas": 75.3, "toolathlon": 55.6, "tau2Bench": 98, "aaAgenticIndex": 47.41, "apexAgentsAa": 37.7, "gdpvalAaNormalized": 49.1, "gdpvalAa": 1482, "gertLabs": 72.93, "researchClawBench": 17, "osWorld2": 13, "jobBench": 42.7, "exploitGym": 13.4, "aaItbench": 45.8 }, "coding": { "swePro": 58.6, "terminalBench2": 82, "vibeCodeBench": 69.847, "reactNativeEvals": 84.7, "cursorBench31": 59.2, "cursorBench32": 58.4, "aaCodingIndex": 74.89, "aaSciCode": 56.1, "frontierCode": 43 }, "reasoning": { "mrcrv2_64_128": 83.1, "mrcrv2_128_256": 87.5, "arcAgi2": 85, "arcAgi3": 0.43, "lcr": 79, "critpt": 27.1 }, "multimodalGrounded": { "mmmuPro": 81.2, "mmmuProPython": 83.2, "officeQaPro": 54.1, "aaMmmuPro": 79.9, "designArenaWebsite": 1274 }, "knowledge": { "gpqa": 93.6, "gpqaDiamond": 93.6, "hle": 52.2, "hleNoTools": 41.4, "artificialAnalysis": 56.31, "aaGpqaDiamond": 93.5, "aaHle": 45.8, "aaOmniscienceIndex": 20.5, "omniscienceAccuracy": 58, "omniscienceHallucinationRate": 89 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": { "frontierMath": 51.7, "frontierMathV2Tiers13": 51.7, "frontierMathV2Tier4": 35.4 }, "external": { "secBenchPro": 45.8, "atomicNetworkAttackSimulation": 100, "atomicVulnerabilityResearch": 92, "atomicEvasion": 54 } } }, { "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", "id": 265, "releaseDate": "2026-07-09", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-6", "familyName": "GPT-5.6", "variantType": "luna", "snapshotLabel": "luna", "baseFamilyModelKey": "gpt-5-6-sol", "relatedModelKeys": [ "gpt-5-6-sol", "gpt-5-6-terra" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 69, "overallScore": 69, "rawOverallScore": 68, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 84.7, "coding": 52, "reasoning": 57.9, "multimodalGrounded": 60.7, "knowledge": 83.6, "multilingual": null, "instructionFollowing": null, "math": 97 }, "verifiedDisplayCategoryScores": { "agentic": 84.7, "coding": 50, "reasoning": 57.9, "multimodalGrounded": 60.7, "knowledge": 83.6, "multilingual": null, "instructionFollowing": null, "math": 97 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 28, "categoryRanks": { "agentic": 58, "coding": 6, "multimodalGrounded": 21, "knowledge": 9 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 21, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "frontierBench": 14.32, "terminalBench2": 84.7, "browseComp": 83.3, "osWorld2": 45.6, "cyberGym": 77.9, "exploitGym": 12.4, "toolathlon": 53.4, "aaAgenticIndex": 46.9, "gdpvalAaNormalized": 53.5, "gdpvalAa": 1582, "aaHarveyLab": 87.9, "aaItbench": 40.3, "aaTau3Banking": 31.1, "aaAutomationBench": 42.2, "aaTerminalBench21": 80.9, "apexAgentsAa": 35.8, "aaBriefcaseElo": 1354, "aaEnterpriseOpsGym": 40.8 }, "coding": { "swePro": 62.7, "terminalBench2": 84.7, "deepSwe": 67.2, "frontierCode11Extended": 55.1, "cursorBench32": 61.1, "aaCodingIndex": 71.45, "aaSciCode": 52.5, "vulcanBench": 85.5 }, "reasoning": { "arcAgi2": 59.54, "arcAgi3": 0.18, "lcr": 78.3, "critpt": 20.6 }, "multimodalGrounded": { "mmmuPro": 78.4, "mmmuProPython": 79.5, "aaMmmuPro": 78.6 }, "knowledge": { "gpqa": 92.3, "gpqaDiamond": 92.3, "healthBenchProfessional": 55.7, "healthBenchHard": 32, "artificialAnalysis": 51.24, "aaGpqaDiamond": 91.1, "aaHle": 39.5, "aaOmniscienceIndex": -10.3, "omniscienceAccuracy": 42.7, "omniscienceHallucinationRate": 92.6 }, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMath": 78.6, "frontierMathV2Tiers13": 78.6, "frontierMathV2Tier4": 58.5 }, "external": { "exploitBench": 33.2 } } }, { "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", "id": 259, "releaseDate": "2026-06-16", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "flagship", "snapshotLabel": "5.2", "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5-1", "glm-5", "glm-5-reasoning", "glm-5-turbo", "glm-5-3" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "glm-5-1" }, "scores": { "displayScore": 68, "overallScore": 68, "rawOverallScore": 68, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 80.8, "coding": 50.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 81, "multilingual": null, "instructionFollowing": null, "math": 80.7 }, "verifiedDisplayCategoryScores": { "agentic": 80.8, "coding": 48.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 81, "multilingual": null, "instructionFollowing": null, "math": 80.7 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 48, "categoryRanks": { "agentic": 22, "coding": 21, "knowledge": 13 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 15, "verifiedBenchmarkCount": 15, "rankableBenchmarkCount": 15, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "frontierBench": 4.59, "terminalBench2": 81, "mcpAtlas": 76.8, "toolathlon": 48.2, "aaAgenticIndex": 45.67, "tau2Bench": 99.1, "gdpvalAaNormalized": 49.9, "gdpvalAa": 1498, "apexAgentsAa": 33.7, "researchClawBench": 20.7 }, "coding": { "swePro": 62.1, "nl2Repo": 48.9, "terminalBench2": 81, "programBench": 63.7, "cursorBench32": 55, "aaCodingIndex": 68.76, "aaSciCode": 50.5, "openHarmonyBench": 58.4 }, "reasoning": { "critpt": 20.9, "lcr": 76.7 }, "multimodalGrounded": { "designArenaWebsite": 1320 }, "knowledge": { "gpqa": 91.2, "gpqaDiamond": 91.2, "hle": 54.7, "hleNoTools": 40.5, "artificialAnalysis": 52.64, "aaGpqaDiamond": 89.5, "aaHle": 41.1, "aaOmniscienceIndex": 4.4, "omniscienceAccuracy": 24.3, "omniscienceHallucinationRate": 26.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.3 }, "math": { "aime2026": 99.2, "hmmtNov2025": 94.4, "hmmtFeb2026": 92.5, "mmAnswerBench": 91 } } }, { "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", "id": 33, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-7", "familyName": "Claude Opus 4.7", "variantType": "reasoning", "snapshotLabel": "adaptive", "baseFamilyModelKey": "claude-opus-4-7", "relatedModelKeys": [ "claude-opus-4-7", "claude-opus-4-6", "claude-opus-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "claude-opus-4-6" }, "scores": { "displayScore": 68, "overallScore": 68, "rawOverallScore": 67, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 70.4, "coding": 69.8, "reasoning": 71.4, "multimodalGrounded": 49.1, "knowledge": 81.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 70.4, "coding": 69.8, "reasoning": 71.4, "multimodalGrounded": 49.1, "knowledge": 81.6, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 16, "categoryRanks": { "agentic": 15, "coding": 19, "multimodalGrounded": 24, "knowledge": 12 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 20, "verifiedBenchmarkCount": 20, "rankableBenchmarkCount": 20, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 69.4, "browseComp": 79.3, "mcpAtlas": 77.3, "osWorldVerified": 78, "cyberGym": 73.1, "aaAgenticIndex": 46.31, "tau2Bench": 88.6, "gdpvalAaNormalized": 49.1, "gdpvalAa": 1483, "osWorld2": 18.2, "jobBench": 45.9, "aaItbench": 46.7 }, "coding": { "sweVerified": 87.6, "swePro": 64.3, "terminalBench2": 69.4, "aaCodingIndex": 73.6, "aaSciCode": 54.5 }, "reasoning": { "mrcrv2_128_256": 59.2, "arcAgi2": 75.8, "arcAgi3": 0.18, "lcr": 75.3, "critpt": 12 }, "multimodalGrounded": { "officeQaPro": 43.6, "charxiv": 91, "charxivNoTools": 82.1, "aaMmmuPro": 78.8, "designArenaWebsite": 1313 }, "knowledge": { "gpqa": 94.2, "gpqaDiamond": 94.2, "hle": 54.7, "hleNoTools": 46.9, "artificialAnalysis": 54.96, "aaGpqaDiamond": 91.4, "aaHle": 42.3, "aaOmniscienceIndex": 27.3, "omniscienceAccuracy": 48.9, "omniscienceHallucinationRate": 42.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 58.6 }, "math": { "frontierMath": 43.8 } } }, { "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", "id": 14, "releaseDate": "2026-02-19", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-1-pro", "familyName": "Gemini 3.1 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-1-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 68, "rawOverallScore": 67, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 67.8, "coding": 59.2, "reasoning": 72.4, "multimodalGrounded": 78.2, "knowledge": 66.4, "multilingual": null, "instructionFollowing": null, "math": 55.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 72.4, "multimodalGrounded": 78.2, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 55.1 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 98, "categoryRanks": { "agentic": 128, "coding": 85, "multimodalGrounded": 9, "knowledge": 32 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 20, "verifiedBenchmarkCount": 20, "rankableBenchmarkCount": 20, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "clawEval": 57.8, "deepSearchQa": 69.7, "tau2Bench": 95.6, "aaAgenticIndex": 23.05, "apexAgentsAa": 32, "gdpvalAaNormalized": 23.2, "gdpvalAa": 965, "gertLabs": 56.87, "researchClawBench": 13.3 }, "coding": { "liveCodeBenchPro": 82.9, "reactNativeEvals": 78.9, "vibeCodeBench": 32.034, "aaCodingIndex": 68.83, "aaSciCode": 58.9 }, "reasoning": { "arcAgi2": 77.08, "arcAgi3": 0.42, "lcr": 79, "critpt": 17.7 }, "multimodalGrounded": { "mmmuPro": 83.9, "charxiv": 80.2, "erqa": 69.4, "simpleVqa": 72.4, "screenSpotPro": 84.4, "zeroBench": 29, "medXpertQaMm": 81.3, "aaMmmuPro": 82.4, "designArenaWebsite": 1271 }, "knowledge": { "gpqaDiamond": 94.3, "hleNoTools": 45.4, "healthBenchHard": 20.6, "medXpertQaText": 71.5, "artificialAnalysis": 47.74, "aaGpqaDiamond": 94.1, "aaHle": 47, "aaOmniscienceIndex": 31.9, "omniscienceAccuracy": 54.9, "omniscienceHallucinationRate": 50.9 }, "multilingual": { "aaGlobalMmluLite": 93.2 }, "instructionFollowing": { "aaIfBench": 77.1 }, "math": { "frontierMathV2Tiers13": 36.9, "frontierMathV2Tier4": 16.7 } } }, { "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", "id": 385, "releaseDate": "2026-08-05", "market": null, "isRegional": false, "family": { "familyKey": "muse-spark", "familyName": "Muse Spark", "variantType": "1.2", "snapshotLabel": "1.2", "baseFamilyModelKey": "muse-spark-1-2", "relatedModelKeys": [ "muse-spark-1-1", "muse-spark" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "muse-spark-1-1" }, "scores": { "displayScore": 67, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 76, "coding": 59.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 60.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 55, "categoryRanks": { "agentic": 39, "coding": 27, "knowledge": 41 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench21": 82.9, "gdpvalAa": 1631, "aaAgenticIndex": 49.31, "gdpvalAaNormalized": 55.8, "aaBriefcaseElo": 1361, "aaTau3Banking": 34.8, "aaTerminalBench21": 80.1, "aaEnterpriseOpsGym": 47.3 }, "coding": { "terminalBench21": 82.9, "deepSwe": 59.3, "aaCodingIndex": 72.22, "aaSciCode": 56.4 }, "reasoning": { "lcr": 83.3, "critpt": 17.7 }, "multimodalGrounded": { "designArenaWebsite": 1332 }, "knowledge": { "artificialAnalysis": 56.76, "aaGpqaDiamond": 90.4, "aaHle": 45.5, "aaOmniscienceIndex": 27.2, "omniscienceAccuracy": 45.4, "omniscienceHallucinationRate": 33.3 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 38, "releaseDate": "2026-05-19", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-5-flash", "familyName": "Gemini 3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-5-flash", "relatedModelKeys": [ "gemini-3-flash", "gemini-3-1-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gemini-3-flash" }, "scores": { "displayScore": 67, "overallScore": 66, "rawOverallScore": 66, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 77.7, "coding": 55, "reasoning": 62.6, "multimodalGrounded": 82.4, "knowledge": 60.2, "multilingual": null, "instructionFollowing": 82.4, "math": 55.9 }, "verifiedDisplayCategoryScores": { "agentic": 77.7, "coding": 54, "reasoning": 62.6, "multimodalGrounded": 82.4, "knowledge": 58.2, "multilingual": null, "instructionFollowing": 82.4, "math": 55.9 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 43, "categoryRanks": { "agentic": 89, "coding": 29, "reasoning": 2, "multimodalGrounded": 6, "knowledge": 42, "instructionFollowing": 24 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": true, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 23, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 76.2, "mcpAtlas": 83.6, "toolathlon": 56.5, "osWorldVerified": 78.4, "financeAgentV2": 57.861, "gdpvalAa": 1345, "tau2Bench": 95.3, "gdpvalAaNormalized": 42.2, "aaAgenticIndex": 39.71, "apexAgentsAa": 47.1, "gertLabs": 61.85, "researchClawBench": 18, "aaEnterpriseOpsGym": 50.1 }, "coding": { "terminalBench2": 76.2, "swePro": 55.1, "sciCode": 53.1, "vibeCodeBench": 48.683, "cursorBench31": 49.8, "cursorBench32": 48.8, "aaCodingIndex": 70.14, "aaSciCode": 53.1 }, "reasoning": { "mrcrv2": 77.3, "mrcr1m": 26.6, "arcAgi2": 72.1, "lcr": 69.3, "critpt": 13.1 }, "multimodalGrounded": { "charxiv": 84.2, "mmmuPro": 83.6, "blueprintBench2": 33.6, "aaMmmuPro": 84.3, "designArenaWebsite": 1280 }, "knowledge": { "artificialAnalysis": 50.2, "gpqa": 92.2, "gpqaDiamond": 92.676, "hle": 40.2, "omniscienceAccuracy": 51.9, "omniscienceHallucinationRate": 60.7, "aaGpqaDiamond": 92.2, "aaHle": 42.7, "aaOmniscienceIndex": 21.2 }, "multilingual": {}, "instructionFollowing": { "ifBench": 76.3, "aaIfBench": 76.3 }, "math": { "frontierMathV2Tiers13": 38.966, "frontierMathV2Tier4": 14.583 } } }, { "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", "id": 18, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-6", "familyName": "Claude Opus 4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 66, "overallScore": 66, "rawOverallScore": 65, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 65.5, "coding": 66.3, "reasoning": null, "multimodalGrounded": 55.3, "knowledge": 82.2, "multilingual": null, "instructionFollowing": null, "math": 59.6 }, "verifiedDisplayCategoryScores": { "agentic": 65.5, "coding": 66.3, "reasoning": null, "multimodalGrounded": 55.3, "knowledge": 82.2, "multilingual": null, "instructionFollowing": null, "math": 59.6 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 23, "categoryRanks": { "agentic": 37, "coding": 31, "knowledge": 11 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 30, "verifiedBenchmarkCount": 30, "rankableBenchmarkCount": 30, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 65.4, "browseComp": 83.7, "osWorldVerified": 72.7, "tau2Bench": 84.8, "clawEval": 70.4, "deepSearchQa": 73.7, "cyberGym": 66.6, "gertLabs": 61.85, "researchClawBench": 19.9, "jobBench": 36.7 }, "coding": { "sweVerified": 80.84, "sweVerifiedArcee": 75.6, "liveCodeBenchPro": 70.7, "swePro": 53.4, "sweRebench": 65.3, "reactNativeEvals": 84.1, "vibeCodeBench": 57.573, "aaSciCode": 45.7, "frontierCode": 26.9 }, "reasoning": { "lcr": 62.3, "critpt": 2.8 }, "multimodalGrounded": { "mmmuPro": 77.3, "erqa": 51.6, "screenSpotPro": 83.1, "medXpertQaMm": 64.8, "aaMmmuPro": 72.5, "designArenaWebsite": 1309 }, "knowledge": { "gpqa": 91.3, "gpqaDiamond": 89.2, "superGpqa": 95, "mmluPro": 82, "mmluProArcee": 89.1, "hle": 53, "hleNoTools": 40, "healthBenchHard": 14.8, "medXpertQaText": 52.1, "artificialAnalysis": 38.77, "aaGpqaDiamond": 84, "aaHle": 19.1, "aaOmniscienceIndex": 2.4, "omniscienceAccuracy": 45.8, "omniscienceHallucinationRate": 80.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.6 }, "math": { "aime2025Arcee": 99.8, "frontierMathV2Tiers13": 40.7, "frontierMathV2Tier4": 22.9 } } }, { "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", "id": 29, "releaseDate": "2026-08-13", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4-pro", "familyName": "DeepSeek V4 Pro", "variantType": "pro-reasoning", "snapshotLabel": "0813", "baseFamilyModelKey": "deepseek-v4-pro-max", "relatedModelKeys": [ "deepseek-v4-pro-base", "deepseek-v4-pro", "deepseek-v4-pro-high" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "deepseek-v4-pro" }, "scores": { "displayScore": 64, "overallScore": 64, "rawOverallScore": 63, "verifiedDisplayScore": 64, "displayCategoryScores": { "agentic": 67.5, "coding": 55.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 70, "multilingual": null, "instructionFollowing": null, "math": 80.5 }, "verifiedDisplayCategoryScores": { "agentic": 67.5, "coding": 54.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 70, "multilingual": null, "instructionFollowing": null, "math": 80.5 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 57, "categoryRanks": { "agentic": 30, "coding": 78, "knowledge": 24 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 23, "verifiedBenchmarkCount": 23, "rankableBenchmarkCount": 23, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 67.9, "terminalBench21": 87.9, "browseComp": 83.4, "hleWithTools": 60, "mcpAtlas": 73.6, "gdpvalAa": 1306, "toolathlon": 51.8, "aaAgenticIndex": 49.56, "apexAgentsAa": 24.3, "tau2Bench": 96.2, "gdpvalAaNormalized": 54.5, "cyberGym": 83.3, "toolathlonVerified": 74.1, "agentsLastExam": 25.7, "automationBench": 31.8, "aaTau3Banking": 39.6, "aaTerminalBench21": 78.7, "aaBriefcaseElo": 1286, "aaEnterpriseOpsGym": 49.6 }, "coding": { "liveCodeBenchPass1Cot": 93.5, "codeforces": 3206, "sweVerified": 80.6, "swePro": 55.4, "sweMultilingual": 76.2, "terminalBench2": 67.9, "vibeCodeBench": 49.931, "aaCodingIndex": 68.83, "aaSciCode": 49.2, "terminalBench21": 87.9, "nl2Repo": 61.5, "deepSwe": 62.7, "dsBenchFullStack": 71.1, "dsBenchHard": 67.2 }, "reasoning": { "mrcr1m": 83.5, "corpusQa1m": 62, "lcr": 75.3, "critpt": 18 }, "multimodalGrounded": { "designArenaWebsite": 1258 }, "knowledge": { "mmluPro": 87.5, "simpleQa": 57.9, "chineseSimpleQa": 84.4, "gpqa": 90.1, "gpqaDiamond": 90.1, "hle": 42.7, "artificialAnalysis": 53.2, "aaGpqaDiamond": 92.8, "aaHle": 41, "aaOmniscienceIndex": 0.8, "omniscienceAccuracy": 49.1, "omniscienceHallucinationRate": 94.1, "aaOpennessIndex": 44.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.5 }, "math": { "hmmtFeb2026": 95.2, "imoAnswerBench": 89.8, "apex": 38.3, "apexShortlist": 90.2 } } }, { "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", "id": 11, "releaseDate": "2026-03-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4-pro", "gpt-5-4-mini", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 64, "overallScore": 64, "rawOverallScore": 64, "verifiedDisplayScore": 64, "displayCategoryScores": { "agentic": 74.8, "coding": 42.9, "reasoning": 69.8, "multimodalGrounded": 64.8, "knowledge": 75.1, "multilingual": null, "instructionFollowing": null, "math": 65.7 }, "verifiedDisplayCategoryScores": { "agentic": 74.8, "coding": 40.9, "reasoning": 69.8, "multimodalGrounded": 64.8, "knowledge": 75.1, "multilingual": null, "instructionFollowing": null, "math": 65.7 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 12, "categoryRanks": { "agentic": 31, "coding": 38, "multimodalGrounded": 16, "knowledge": 21 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 32, "verifiedBenchmarkCount": 32, "rankableBenchmarkCount": 32, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 75.1, "cyberGym": 79, "browseComp": 82.7, "osWorldVerified": 75, "mcpAtlas": 70.6, "toolathlon": 54.6, "tau2Bench": 98.9, "clawEval": 60.3, "deepSearchQa": 73.6, "aaAgenticIndex": 44.17, "apexAgentsAa": 33.3, "gdpvalAaNormalized": 44.2, "gdpvalAa": 1385, "gertLabs": 64.89, "researchClawBench": 15.3, "jobBench": 38.9, "exploitGym": 6 }, "coding": { "liveCodeBenchPro": 87.5, "swePro": 57.7, "reactNativeEvals": 85.3, "vibeCodeBench": 67.421, "aaCodingIndex": 71.05, "aaSciCode": 56.6 }, "reasoning": { "arcAgi2": 73.95, "arcAgi3": 0.21, "lcr": 77.7, "critpt": 23.4 }, "multimodalGrounded": { "mmmuPro": 81.2, "officeQaPro": 53.2, "mmmuProPython": 82.1, "charxiv": 82.8, "erqa": 65.4, "simpleVqa": 61.1, "screenSpotPro": 85.4, "zeroBench": 41, "medXpertQaMm": 77.1, "aaMmmuPro": 78.4, "designArenaWebsite": 1238 }, "knowledge": { "gpqa": 92.8, "hle": 52.1, "hleNoTools": 39.8, "gpqaDiamond": 92.8, "healthBenchHard": 40.1, "medXpertQaText": 59.6, "artificialAnalysis": 53.12, "aaGpqaDiamond": 92, "aaHle": 43.7, "aaOmniscienceIndex": 5.8, "omniscienceAccuracy": 50.8, "omniscienceHallucinationRate": 91.7, "healthBenchProfessional": 48.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.9 }, "math": { "frontierMathV2Tiers13": 47.6, "frontierMathV2Tier4": 27.1 }, "korean": {} } }, { "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", "id": 44, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "kimi-2-6", "familyName": "Kimi K2.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-2-6", "relatedModelKeys": [ "kimi-k2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "kimi-k2-5" }, "scores": { "displayScore": 62, "overallScore": 62, "rawOverallScore": 61, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": 66.6, "coding": 60, "reasoning": null, "multimodalGrounded": 61.9, "knowledge": 51.2, "multilingual": null, "instructionFollowing": null, "math": 71.7 }, "verifiedDisplayCategoryScores": { "agentic": 66.6, "coding": 60, "reasoning": null, "multimodalGrounded": 61.9, "knowledge": 49.2, "multilingual": null, "instructionFollowing": null, "math": 71.7 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 81, "categoryRanks": { "agentic": 95, "coding": 76, "multimodalGrounded": 18, "knowledge": 52, "math": 1 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": true } }, "coverage": { "trustedBenchmarkCount": 29, "verifiedBenchmarkCount": 29, "rankableBenchmarkCount": 29, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 66.7, "browseComp": 83.2, "osWorldVerified": 73.1, "toolathlon": 50, "mcpAtlas": 55.9, "clawEval": 62.3, "deepSearchQa": 92.5, "wideResearch": 80.8, "aaAgenticIndex": 31.16, "tau2Bench": 95.9, "gdpvalAaNormalized": 34.5, "gdpvalAa": 1189, "apexAgentsAa": 28.5, "gertLabs": 56.82, "researchClawBench": 18, "osWorld2": 4.6 }, "coding": { "sweVerified": 80.2, "liveCodeBenchV6": 89.6, "swePro": 58.6, "sweMultilingual": 76.7, "sciCode": 52.2, "terminalBench2": 66.7, "vibeCodeBench": 37.891, "cursorBench31": 47.6, "aaCodingIndex": 61.77, "aaSciCode": 53.5 }, "reasoning": { "lcr": 76.7, "critpt": 8 }, "multimodalGrounded": { "mmmuPro": 79.4, "mmmuProPython": 80.1, "charxiv": 80.4, "mathVision": 87.4, "vStar": 96.9, "aaMmmuPro": 79.4, "designArenaWebsite": 1289 }, "knowledge": { "gpqa": 90.5, "gpqaDiamond": 90.5, "hle": 34.7, "artificialAnalysis": 45.14, "aaGpqaDiamond": 91.1, "aaHle": 37.5, "aaOmniscienceIndex": 5.3, "omniscienceAccuracy": 32.6, "omniscienceHallucinationRate": 40.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76 }, "math": { "aime2026": 96.4, "hmmtFeb2026": 92.7, "mmAnswerBench": 86, "frontierMathV2Tiers13": 38.966, "frontierMathV2Tier4": 14.58 } } }, { "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", "id": 43, "releaseDate": "2026-04-07", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "snapshot", "snapshotLabel": "5.1", "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning", "glm-5-turbo" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "glm-5" }, "scores": { "displayScore": 61, "overallScore": 61, "rawOverallScore": 61, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 49.1, "coding": 63.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.4, "multilingual": null, "instructionFollowing": null, "math": 64.5 }, "verifiedDisplayCategoryScores": { "agentic": 49.1, "coding": 63.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.4, "multilingual": null, "instructionFollowing": null, "math": 64.5 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 29, "categoryRanks": { "agentic": 90, "coding": 28, "math": 3 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": true } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 63.5, "browseComp": 68, "tau3Bench": 70.6, "mcpAtlas": 71.8, "cyberGym": 68.7, "clawEval": 62.3, "aaAgenticIndex": 30.56, "tau2Bench": 97.7, "gdpvalAaNormalized": 37.7, "gertLabs": 60.11, "gdpvalAa": 1254, "researchClawBench": 18.2 }, "coding": { "swePro": 58.4, "nl2Repo": 42.7, "sweRebench": 62.7, "vibeCodeBench": 31.456, "aaCodingIndex": 55.78, "aaSciCode": 43.8, "openHarmonyBench": 52.3 }, "reasoning": { "lcr": 68, "critpt": 4.6 }, "multimodalGrounded": { "designArenaWebsite": 1290 }, "knowledge": { "gpqaDiamond": 86.2, "hle": 52.3, "artificialAnalysis": 40.97, "aaGpqaDiamond": 86.8, "aaHle": 30.1, "aaOmniscienceIndex": 0.9, "omniscienceAccuracy": 23.7, "omniscienceHallucinationRate": 29.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.3 }, "math": { "aime2026": 95.3, "hmmtNov2025": 94, "hmmtFeb2026": 82.6, "mmAnswerBench": 83.8, "frontierMathV2Tiers13": 33.448, "frontierMathV2Tier4": 12.5 } } }, { "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", "id": 27, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-6", "familyName": "Claude Sonnet 4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-sonnet-4-6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 60, "overallScore": 60, "rawOverallScore": 59, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": 54.5, "coding": 66.7, "reasoning": null, "multimodalGrounded": 46.7, "knowledge": 76, "multilingual": null, "instructionFollowing": null, "math": 49.4 }, "verifiedDisplayCategoryScores": { "agentic": 54.2, "coding": 66.7, "reasoning": null, "multimodalGrounded": 46.7, "knowledge": 76, "multilingual": null, "instructionFollowing": null, "math": 49.4 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 41, "categoryRanks": { "agentic": 72, "coding": 42, "knowledge": 20 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 18, "verifiedBenchmarkCount": 18, "rankableBenchmarkCount": 18, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 59.1, "osWorldVerified": 72.1, "clawEval": 67.8, "cyberGym": 65.2, "tau2Bench": 79.5, "gertLabs": 62.92, "osWorld2": 8.3, "jobBench": 36.9 }, "coding": { "sweVerified": 79.6, "sweRebench": 60.7, "reactNativeEvals": 80.6, "vibeCodeBench": 51.476, "cursorBench31": 48.8, "aaSciCode": 46.9, "frontierCode": 24.3 }, "reasoning": { "lcr": 62.3, "critpt": 0.9 }, "multimodalGrounded": { "charxiv": 77.4, "aaMmmuPro": 70.6, "designArenaWebsite": 1303 }, "knowledge": { "gpqa": 89.9, "superGpqa": 95, "mmluPro": 79.2, "hle": 49, "artificialAnalysis": 36.8, "aaGpqaDiamond": 79.9, "aaHle": 13.3, "aaOmniscienceIndex": -3.5, "omniscienceAccuracy": 38.6, "omniscienceHallucinationRate": 68.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.2 }, "math": { "frontierMathV2Tiers13": 32.4, "frontierMathV2Tier4": 8.3 }, "korean": {} } }, { "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", "id": 284, "releaseDate": "2026-07-15", "market": null, "isRegional": false, "family": { "familyKey": "inkling", "familyName": "Inkling", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "inkling", "relatedModelKeys": [ "inkling-small" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 58, "overallScore": 58, "rawOverallScore": 57, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 57.6, "coding": 51.2, "reasoning": null, "multimodalGrounded": 42.9, "knowledge": 66.6, "multilingual": null, "instructionFollowing": 88.6, "math": 79 }, "verifiedDisplayCategoryScores": { "agentic": 57.6, "coding": 50.4, "reasoning": null, "multimodalGrounded": 42.2, "knowledge": 66.6, "multilingual": null, "instructionFollowing": 88.6, "math": 79 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 31, "categoryRanks": { "agentic": 116, "coding": 117, "multimodalGrounded": 28, "knowledge": 30, "instructionFollowing": 15 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 63.8, "browseComp": 77.1, "mcpAtlas": 74.1, "designArenaAgenticWebDev": 1257, "aaAgenticIndex": 34.13, "gdpvalAaNormalized": 36.7, "gdpvalAa": 1234, "aaBriefcaseElo": 844, "aaTau3Banking": 29.1, "aaEnterpriseOpsGym": 38, "aaTerminalBench21": 55.1 }, "coding": { "sweVerified": 77.6, "swePro": 54.3, "terminalBench2": 63.8, "aaCodingIndex": 52.06, "aaSciCode": 46.1 }, "reasoning": { "lcr": 73.3, "critpt": 5.4 }, "multimodalGrounded": { "mmmuPro": 73.5, "charxiv": 82, "charxivNoTools": 78.1, "aaMmmuPro": 73.5, "designArenaWebsite": 1229 }, "knowledge": { "gpqa": 87.9, "gpqaDiamond": 87.9, "hle": 46, "hleNoTools": 30, "artificialAnalysis": 42.29, "aaGpqaDiamond": 87.2, "aaHle": 31.9, "aaOmniscienceIndex": 2, "omniscienceAccuracy": 41.6, "omniscienceHallucinationRate": 67.7, "aaOpennessIndex": 38.9 }, "multilingual": {}, "instructionFollowing": { "ifBench": 79.8 }, "math": { "aime2026": 97.1 } } }, { "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", "id": 241, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m3", "familyName": "MiniMax M3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m3", "relatedModelKeys": [ "minimax-m2-7", "minimax-m2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "minimax-m2-7" }, "scores": { "displayScore": 58, "overallScore": 58, "rawOverallScore": 57, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 63.5, "coding": 57.6, "reasoning": null, "multimodalGrounded": 42.6, "knowledge": 63.9, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 63.5, "coding": 57.5, "reasoning": null, "multimodalGrounded": 41.3, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 22, "categoryRanks": { "agentic": 114, "coding": 91, "multimodalGrounded": 29, "knowledge": 34 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 66, "browseComp": 83.52, "osWorldVerified": 70.06, "mcpAtlas": 74.2, "clawEval": 74.5, "aaAgenticIndex": 36.12, "tau2Bench": 88.9, "gdpvalAaNormalized": 44, "gdpvalAa": 1380, "gdpvalRubrics": 74.7, "bankerToolBench": 76.1, "researchClawBench": 19.8, "osWorld2": 4.6, "aaBriefcaseElo": 1107, "aaEnterpriseOpsGym": 32.1, "aaHarveyLab": 88.4, "terminalBenchHard": 42.4, "aaTerminalBench21": 65.2, "aaAutomationBench": 15.9, "aaTau3Banking": 15.3 }, "coding": { "sweVerified": 80.5, "swePro": 59, "terminalBench2": 66, "nl2Repo": 42.13, "aaCodingIndex": 58.57, "aaSciCode": 45.4, "vibeV2": 50.1, "svgBench": 63.7, "kernelBenchHard": 28.8, "openHarmonyBench": 48.4 }, "reasoning": { "lcr": 80.3, "critpt": 3.7 }, "multimodalGrounded": { "officeQaPro": 45.1, "omniDocBench15": 91.6, "mmmuPro": 78.1, "videoMmmu": 84.6, "videoMmeWithSub": 85.4, "designArenaWebsite": 1277, "aaMmmuPro": 78.6 }, "knowledge": { "artificialAnalysis": 45.4, "aaGpqaDiamond": 92.9, "aaHle": 39, "aaOmniscienceIndex": 1.4, "omniscienceAccuracy": 16.7, "omniscienceHallucinationRate": 18.4, "aaOpennessIndex": 33.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 82.9 }, "math": { "usamo2026": 85.71 } } }, { "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", "id": 55, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-plus", "familyName": "Qwen3.6 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-plus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 58, "overallScore": 58, "rawOverallScore": 57, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 52.5, "coding": 54.5, "reasoning": 54.4, "multimodalGrounded": 61.1, "knowledge": 55.8, "multilingual": 69.7, "instructionFollowing": 86.4, "math": 62.6 }, "verifiedDisplayCategoryScores": { "agentic": 51.9, "coding": 53.6, "reasoning": 54.4, "multimodalGrounded": 61.1, "knowledge": 54.4, "multilingual": 69.7, "instructionFollowing": 86.4, "math": 62.6 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 40, "categoryRanks": { "agentic": 122, "coding": 66, "multimodalGrounded": 19, "knowledge": 47, "multilingual": 4, "instructionFollowing": 20, "math": 4 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 39, "verifiedBenchmarkCount": 39, "rankableBenchmarkCount": 39, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 61.6, "clawEval": 58.8, "qwenClawBench": 57.2, "tau3Bench": 70.7, "vitaBench": 44.3, "deepPlanning": 41.5, "toolathlon": 39.8, "mcpAtlas": 48.2, "mcpTasks": 74.1, "wideResearch": 74.3, "aaAgenticIndex": 29, "tau2Bench": 97.7, "gdpvalAaNormalized": 31.8, "gdpvalAa": 1137, "gertLabs": 50.6, "researchClawBench": 18 }, "coding": { "sweVerified": 78.8, "swePro": 56.6, "sweMultilingual": 73.8, "liveCodeBenchV6": 87.1, "vibeCodeBench": 25.564, "aaCodingIndex": 54.53, "aaSciCode": 40.7 }, "reasoning": { "aiNeedle": 68.3, "longBenchV2": 62, "lcr": 72.3, "critpt": 2.9 }, "multimodalGrounded": { "mmmu": 86, "mmmuPro": 78.8, "mathVision": 88, "videoMmmu": 84, "screenSpotPro": 68.2, "charxiv": 81.5, "vStar": 96.9, "aaMmmuPro": 78, "designArenaWebsite": 1258 }, "knowledge": { "gpqa": 90.4, "superGpqa": 71.6, "mmluPro": 88.5, "mmluRedux": 94.5, "cEval": 93.3, "hle": 28.8, "artificialAnalysis": 40.49, "aaGpqaDiamond": 88.2, "aaHle": 27.8, "aaOmniscienceIndex": 0.9, "omniscienceAccuracy": 26.4, "omniscienceHallucinationRate": 34.6 }, "multilingual": { "mmluProX": 84.7, "nova63": 57.9 }, "instructionFollowing": { "ifeval": 94.3, "ifBench": 75.8, "aaIfBench": 75.2 }, "math": { "aime2026": 95.3, "hmmtFeb2025": 96.7, "hmmtNov2025": 94.6, "hmmtFeb2026": 87.8, "mmAnswerBench": 83.8, "frontierMathV2Tiers13": 26.207, "frontierMathV2Tier4": 8.333 } } }, { "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", "id": 297, "releaseDate": "2026-07-30", "market": null, "isRegional": false, "family": { "familyKey": "inkling", "familyName": "Inkling", "variantType": "small", "snapshotLabel": "Small", "baseFamilyModelKey": "inkling", "relatedModelKeys": [ "inkling" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 56, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 58.8, "coding": 55.1, "reasoning": 41.7, "multimodalGrounded": 43.1, "knowledge": 69.7, "multilingual": null, "instructionFollowing": 92.8, "math": 77 }, "verifiedDisplayCategoryScores": { "agentic": 58.8, "coding": 55.1, "reasoning": 41.7, "multimodalGrounded": 43.1, "knowledge": 69.7, "multilingual": null, "instructionFollowing": 92.8, "math": 77 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 45, "categoryRanks": { "agentic": 112, "coding": 50, "multimodalGrounded": 27, "instructionFollowing": 5 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 18, "verifiedBenchmarkCount": 18, "rankableBenchmarkCount": 18, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 64.7, "browseComp": 77.4, "mcpAtlas": 79.6, "toolathlonVerified": 54.4, "aaAgenticIndex": 31.88, "gdpvalAaNormalized": 38.4, "gdpvalAa": 1268 }, "coding": { "sweVerified": 80.2, "swePro": 55.9, "terminalBench2": 64.7, "sciCode": 48.7, "aaCodingIndex": 52.95, "aaSciCode": 48.7 }, "reasoning": { "arcAgi2": 40.1, "critpt": 8.3, "lcr": 69.3 }, "multimodalGrounded": { "mmmuPro": 74, "charxiv": 81.3, "charxivNoTools": 77.4, "aaMmmuPro": 74 }, "knowledge": { "gpqa": 89.5, "gpqaDiamond": 89.5, "hle": 47.8, "hleNoTools": 31.6, "artificialAnalysis": 41.18, "aaGpqaDiamond": 89.5, "aaHle": 33.3, "aaOmniscienceIndex": -8.9, "omniscienceAccuracy": 33.2, "omniscienceHallucinationRate": 63 }, "multilingual": {}, "instructionFollowing": { "ifBench": 82.2 }, "math": { "aime2026": 95.5, "hmmtFeb2026": 90.2 } } }, { "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", "id": 51, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 56, "overallScore": 56, "rawOverallScore": 56, "verifiedDisplayScore": 56, "displayCategoryScores": { "agentic": 43.9, "coding": 61.6, "reasoning": 43, "multimodalGrounded": null, "knowledge": 77.1, "multilingual": 48.7, "instructionFollowing": 87.4, "math": 56.9 }, "verifiedDisplayCategoryScores": { "agentic": 43.9, "coding": 61.6, "reasoning": 43, "multimodalGrounded": null, "knowledge": 77.1, "multilingual": 48.7, "instructionFollowing": 87.4, "math": 56.9 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 35, "categoryRanks": { "agentic": 41, "coding": 37, "knowledge": 19, "multilingual": 6, "instructionFollowing": 18, "math": 7 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 34, "verifiedBenchmarkCount": 34, "rankableBenchmarkCount": 34, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 56.2, "clawEval": 57.7, "qwenClawBench": 54.1, "tau3Bench": 65.6, "deepPlanning": 14.6, "toolathlon": 38, "mcpAtlas": 31.1, "mcpTasks": 60.8, "wideResearch": 69.8, "tau2Bench": 98.2, "cyberGym": 43.2, "apexAgentsAa": 14.5, "gertLabs": 50.99 }, "coding": { "sweVerified": 77.8, "sweVerifiedArcee": 72.8, "swePro": 55.1, "sweMultilingual": 73.3, "sweRebench": 62.8, "reactNativeEvals": 74.8, "aaSciCode": 46.2 }, "reasoning": { "longBenchV2": 60.8, "aiNeedle": 63.3, "lcr": 70.7, "critpt": 2 }, "multimodalGrounded": { "designArenaWebsite": 1266 }, "knowledge": { "gpqa": 86, "gpqaDiamond": 86, "superGpqa": 66.8, "mmluPro": 85.7, "mmluProArcee": 85.8, "hle": 50.4, "artificialAnalysis": 40.55, "aaGpqaDiamond": 82, "aaHle": 29.3, "aaOmniscienceIndex": 0.3, "omniscienceAccuracy": 26.3, "omniscienceHallucinationRate": 35.3 }, "multilingual": { "mmluProX": 83.1, "nova63": 55.1 }, "instructionFollowing": { "ifeval": 92.6, "aaIfBench": 72.3 }, "math": { "aime2026": 95.8, "aime2025Arcee": 93.3, "hmmtFeb2025": 97.5, "hmmtNov2025": 96.9, "hmmtFeb2026": 86.4, "mmAnswerBench": 82.5, "frontierMathV2Tiers13": 16.434, "frontierMathV2Tier4": 2.1 } } }, { "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", "id": 81, "releaseDate": "2026-03-17", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-pro", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-5-mini" }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 55.1, "coding": 52.6, "reasoning": null, "multimodalGrounded": 51.8, "knowledge": 57, "multilingual": null, "instructionFollowing": null, "math": 44.6 }, "verifiedDisplayCategoryScores": { "agentic": 55.1, "coding": null, "reasoning": null, "multimodalGrounded": 51.8, "knowledge": 56.7, "multilingual": null, "instructionFollowing": null, "math": 44.6 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 96, "categoryRanks": { "agentic": 121, "coding": 100, "knowledge": 46 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 12, "verifiedBenchmarkCount": 12, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 60, "osWorldVerified": 72.1, "mcpAtlas": 57.7, "toolathlon": 42.9, "tau2Bench": 93.4, "aaAgenticIndex": 31.54, "apexAgentsAa": 28.2, "gdpvalAaNormalized": 33.3, "gdpvalAa": 1167 }, "coding": { "vibeCodeBench": 47.969, "aaCodingIndex": 56.08, "aaSciCode": 49.9, "frontierCode": 27 }, "reasoning": { "lcr": 73, "critpt": 10 }, "multimodalGrounded": { "mmmuPro": 76.6, "mmmuProPython": 78, "aaMmmuPro": 73.3 }, "knowledge": { "gpqa": 88, "hle": 41.5, "hleNoTools": 28.2, "artificialAnalysis": 40.94, "aaGpqaDiamond": 87.5, "aaHle": 28.1, "aaOmniscienceIndex": -18.9, "omniscienceAccuracy": 37.5, "omniscienceHallucinationRate": 90.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.3 }, "math": { "frontierMathV2Tiers13": 28.28, "frontierMathV2Tier4": 2.08 } } }, { "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", "id": 36, "releaseDate": "2025-11-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-5", "familyName": "Claude Opus 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 54, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 48.1, "coding": 57, "reasoning": 77, "multimodalGrounded": 13.5, "knowledge": 58, "multilingual": 82.9, "instructionFollowing": 56.4, "math": 58.4 }, "verifiedDisplayCategoryScores": { "agentic": 48.1, "coding": 56.4, "reasoning": 77, "multimodalGrounded": 13.5, "knowledge": 56.6, "multilingual": 82.9, "instructionFollowing": 56.4, "math": 58.4 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 46, "categoryRanks": { "agentic": 124, "coding": 34, "multimodalGrounded": 32, "knowledge": 44, "multilingual": 2, "instructionFollowing": 33, "math": 6 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 41, "verifiedBenchmarkCount": 41, "rankableBenchmarkCount": 41, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 59.3, "osWorldVerified": 66.3, "osWorld": 66.3, "clawEval": 59.6, "qwenClawBench": 52.3, "tau3Bench": 70.2, "vitaBench": 23.3, "deepPlanning": 26.4, "toolathlon": 43.5, "mcpAtlas": 42.3, "mcpTasks": 71.8, "wideResearch": 76.4, "cyberGym": 50.6, "tau2Bench": 86.3, "gertLabs": 64.23, "jobBench": 32.3 }, "coding": { "sweVerified": 80.9, "liveCodeBenchV6": 84.8, "swePro": 57.1, "sweMultilingual": 77.5, "nl2Repo": 43.2, "aaSciCode": 47 }, "reasoning": { "longBenchV2": 64.4, "aiNeedle": 74, "lcr": 67.3, "critpt": 0.3 }, "multimodalGrounded": { "mmmuPro": 70.6, "mathVision": 74.3, "charxiv": 68.5, "videoMmmu": 84.4, "screenSpotPro": 45.7, "vStar": 67, "aaMmmuPro": 71.2, "designArenaWebsite": 1265 }, "knowledge": { "gpqa": 87, "superGpqa": 70.6, "mmluPro": 89.5, "mmluRedux": 96.6, "cEval": 92.2, "hle": 30.8, "artificialAnalysis": 35.57, "aaGpqaDiamond": 81, "aaHle": 13.2, "aaOmniscienceIndex": -4.1, "omniscienceAccuracy": 40.9, "omniscienceHallucinationRate": 76.2, "aaMmluPro": 88.9 }, "multilingual": { "mmluProX": 85.7, "nova63": 56.7 }, "instructionFollowing": { "ifeval": 90.9, "ifBench": 58, "aaIfBench": 43 }, "math": { "aime2026": 95.1, "hmmtFeb2025": 92.9, "hmmtNov2025": 93.3, "hmmtFeb2026": 85.3, "mmAnswerBench": 84, "frontierMathV2Tiers13": 20.69, "frontierMathV2Tier4": 4.167 } } }, { "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", "id": 57, "releaseDate": "2026-02-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-397b", "familyName": "Qwen3.5 397B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-397b", "relatedModelKeys": [ "qwen3-5-397b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 53, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": 32.4, "coding": 46, "reasoning": 65.7, "multimodalGrounded": 60.9, "knowledge": 53.5, "multilingual": 69.7, "instructionFollowing": 87.4, "math": 74.3 }, "verifiedDisplayCategoryScores": { "agentic": 32.4, "coding": 46, "reasoning": 65.7, "multimodalGrounded": 60.9, "knowledge": 53.5, "multilingual": 69.7, "instructionFollowing": 87.4, "math": 74.3 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 89, "categoryRanks": { "agentic": 77, "coding": 57, "multimodalGrounded": 20, "knowledge": 49, "multilingual": 5, "instructionFollowing": 19 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 35, "verifiedBenchmarkCount": 35, "rankableBenchmarkCount": 35, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 52.5, "browseComp": 62, "clawEval": 56.8, "qwenClawBench": 51.8, "tau3Bench": 68.4, "vitaBench": 43.7, "deepPlanning": 37.6, "toolathlon": 36.3, "mcpAtlas": 46.1, "mcpTasks": 74.2, "wideResearch": 74, "tau2Bench": 95.6, "gertLabs": 46.76, "researchClawBench": 14.2, "aaAgenticIndex": 19.85, "apexAgentsAa": 15.3, "gdpvalAaNormalized": 23.3, "gdpvalAa": 966 }, "coding": { "sweVerified": 76.2, "liveCodeBenchV6": 83.6, "swePro": 50.9, "aaSciCode": 42, "aaCodingIndex": 48.21 }, "reasoning": { "longBenchV2": 63.2, "aiNeedle": 68.7, "lcr": 72.7, "critpt": 1.7 }, "multimodalGrounded": { "mmmuPro": 79, "mathVision": 88.6, "charxiv": 80.8, "videoMmmu": 84.7, "screenSpotPro": 65.6, "vStar": 95.8, "aaMmmuPro": 77.3 }, "knowledge": { "gpqa": 88.4, "superGpqa": 70.4, "mmluPro": 87.8, "mmluRedux": 94.9, "cEval": 93, "hle": 28.7, "artificialAnalysis": 34.26, "aaGpqaDiamond": 89.3, "aaHle": 29, "aaOmniscienceIndex": -30.7, "omniscienceAccuracy": 30.8, "omniscienceHallucinationRate": 88.9 }, "multilingual": { "mmluProX": 84.7, "nova63": 59.1 }, "instructionFollowing": { "ifeval": 92.6, "aaIfBench": 78.8 }, "math": { "aime2026": 93.3, "hmmtFeb2025": 94.8, "hmmtNov2025": 92.7, "hmmtFeb2026": 87.9, "mmAnswerBench": 80.9 } } }, { "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", "id": 402, "releaseDate": "2026-08-10", "market": null, "isRegional": false, "family": { "familyKey": "muse-glimmer", "familyName": "Muse Glimmer", "variantType": "30b", "snapshotLabel": "30B", "baseFamilyModelKey": "muse-glimmer-30b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 53, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": 52.1, "coding": 44.2, "reasoning": null, "multimodalGrounded": 39.8, "knowledge": null, "multilingual": null, "instructionFollowing": 83.6, "math": 76.4 }, "verifiedDisplayCategoryScores": { "agentic": 52.1, "coding": 44.2, "reasoning": null, "multimodalGrounded": 39.8, "knowledge": null, "multilingual": null, "instructionFollowing": 83.6, "math": 76.4 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": null, "categoryRanks": { "agentic": 55, "coding": 63, "multimodalGrounded": 30, "instructionFollowing": 23 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "mcpAtlas": 75.5, "deepSearchQa": 74.6, "skillsBench": 44.3, "osWorldVerified": 65.9, "aaAgenticIndex": 22.94, "gdpvalAaNormalized": 22.8, "gdpvalAa": 955, "aaTau3Banking": 23.5, "aaEnterpriseOpsGym": 34.7 }, "coding": { "swePro": 51.2, "sweVerified": 76, "terminalBench21": 51.7, "sciCode": 43.6, "aaCodingIndex": 49, "aaSciCode": 43.6 }, "reasoning": { "lcr": 80, "critpt": 2.6 }, "multimodalGrounded": { "charxiv": 78.8, "screenSpotPro": 75.4, "omniDocBench15": 75.8, "mmmuPro": 74, "aaMmmuPro": 74.3 }, "knowledge": { "artificialAnalysis": 35.06, "aaGpqaDiamond": 83.5, "aaHle": 22, "aaOmniscienceIndex": -32.8, "omniscienceAccuracy": 27, "omniscienceHallucinationRate": 81.9, "aaOpennessIndex": 44.4 }, "multilingual": {}, "instructionFollowing": { "ifBench": 77 }, "math": { "aime2026": 94.7 } } }, { "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", "id": 250, "releaseDate": "2026-06-02", "market": null, "isRegional": false, "family": { "familyKey": "mai-thinking", "familyName": "MAI-Thinking", "variantType": "1", "snapshotLabel": null, "baseFamilyModelKey": "mai-thinking-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 53, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": 28.7, "coding": 44.5, "reasoning": null, "multimodalGrounded": null, "knowledge": 80.6, "multilingual": null, "instructionFollowing": 97.8, "math": 73.5 }, "verifiedDisplayCategoryScores": { "agentic": 28.7, "coding": 44.5, "reasoning": null, "multimodalGrounded": null, "knowledge": 80.6, "multilingual": null, "instructionFollowing": 97.8, "math": 73.5 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 135, "categoryRanks": { "agentic": 62, "coding": 71, "knowledge": 14, "instructionFollowing": 1 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 46 }, "coding": { "liveCodeBenchV6": 87.7, "sweVerified": 73.5, "swePro": 52.8, "terminalBench2": 46 }, "reasoning": { "graphwalksBfs128k": 90 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 84.2, "gpqaDiamond": 84.2, "mmluPro": 85, "simpleQa": 31 }, "multilingual": {}, "instructionFollowing": { "ifBench": 85 }, "math": { "aime2025": 97, "aime2026": 94.5, "hmmtFeb2026": 84.9 } } }, { "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", "id": 34, "releaseDate": "2025-11-18", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-pro", "familyName": "Gemini 3 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-pro", "relatedModelKeys": [ "gemini-3-pro-deep-think" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 53, "overallScore": 53, "rawOverallScore": 52, "verifiedDisplayScore": 53, "displayCategoryScores": { "agentic": null, "coding": 59.9, "reasoning": 34.2, "multimodalGrounded": 69.1, "knowledge": 68.2, "multilingual": null, "instructionFollowing": null, "math": 56.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 34.2, "multimodalGrounded": 69.1, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 56.2 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 26, "categoryRanks": { "agentic": 24, "coding": 30, "multimodalGrounded": 13, "knowledge": 27 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "tau2Bench": 87.1, "gertLabs": 63.23, "jobBench": 11.4 }, "coding": { "vibeCodeBench": 14.3, "aaSciCode": 56.1, "aaLiveCodeBench": 91.7 }, "reasoning": { "arcAgi2": 31.1, "lcr": 73, "critpt": 9.1 }, "multimodalGrounded": { "mmmuPro": 81, "mathVision": 86.6, "videoMmmu": 87.6, "screenSpotPro": 72.7, "charxiv": 81.4, "vStar": 88, "aaMmmuPro": 80.2 }, "knowledge": { "artificialAnalysis": 40.61, "aaGpqaDiamond": 90.8, "aaHle": 39.7, "aaOmniscienceIndex": 15.3, "omniscienceAccuracy": 55.8, "omniscienceHallucinationRate": 91.5, "aaMmluPro": 89.8 }, "multilingual": { "aaGlobalMmluLite": 92.2 }, "instructionFollowing": { "aaIfBench": 70.4 }, "math": { "frontierMathV2Tiers13": 37.6, "frontierMathV2Tier4": 18.75 } } }, { "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", "id": 26, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2-instant", "gpt-5-2-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 52, "overallScore": 52, "rawOverallScore": 51, "verifiedDisplayScore": 52, "displayCategoryScores": { "agentic": 22.2, "coding": 55.1, "reasoning": 52.3, "multimodalGrounded": 64.5, "knowledge": 83.7, "multilingual": null, "instructionFollowing": null, "math": 58.4 }, "verifiedDisplayCategoryScores": { "agentic": 22.2, "coding": 54.1, "reasoning": 52.3, "multimodalGrounded": 64.5, "knowledge": 83.7, "multilingual": null, "instructionFollowing": null, "math": 58.4 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 87, "categoryRanks": { "agentic": 96, "coding": 53, "multimodalGrounded": 17, "knowledge": 8 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "browseComp": 65.8, "osWorldVerified": 47.3, "tau2Bench": 84.8, "gertLabs": 46.54, "jobBench": 34.3 }, "coding": { "sweVerified": 80, "swePro": 55.6, "vibeCodeBench": 53.499, "aaSciCode": 52.1 }, "reasoning": { "arcAgi2": 52.9, "lcr": 79.3, "critpt": 11.6 }, "multimodalGrounded": { "mmmuPro": 79.5, "mathVision": 83, "charxiv": 82.1, "vStar": 75.9, "designArenaWebsite": 1213 }, "knowledge": { "gpqa": 92.4, "artificialAnalysis": 43.34, "aaGpqaDiamond": 90.3, "aaHle": 37.7, "aaOmniscienceIndex": -0.9, "omniscienceAccuracy": 44.3, "omniscienceHallucinationRate": 81.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.4 }, "math": { "aaAime2025": 99, "frontierMathV2Tiers13": 40.7, "frontierMathV2Tier4": 18.8 }, "korean": {} } }, { "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", "id": 63, "releaseDate": "2026-04-21", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-27b", "familyName": "Qwen3.6-27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-27b", "relatedModelKeys": [ "qwen3-6-35b-a3b", "qwen3-5-27b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": 48.5, "coding": 44.9, "reasoning": null, "multimodalGrounded": 45.9, "knowledge": 46.7, "multilingual": null, "instructionFollowing": null, "math": 72.9 }, "verifiedDisplayCategoryScores": { "agentic": 48.5, "coding": 43.1, "reasoning": null, "multimodalGrounded": 45.9, "knowledge": 46.7, "multilingual": null, "instructionFollowing": null, "math": 72.9 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 113, "categoryRanks": { "agentic": 130, "coding": 103, "multimodalGrounded": 25, "knowledge": 54 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 36, "verifiedBenchmarkCount": 36, "rankableBenchmarkCount": 36, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 59.3, "clawEval": 72.4, "qwenClawBench": 53.4, "qwenWebBench": 1487, "androidWorld": 70.3, "aaAgenticIndex": 27.51, "tau2Bench": 94.2, "gdpvalAaNormalized": 31.9, "gdpvalAa": 1138, "gertLabs": 54.84 }, "coding": { "sweVerified": 77.2, "sweMultilingual": 71.3, "swePro": 53.5, "terminalBench2": 59.3, "liveCodeBench": 83.9, "nl2Repo": 36.2, "aaCodingIndex": 53.72, "aaSciCode": 39.8 }, "reasoning": { "lcr": 73.3, "critpt": 1.1 }, "multimodalGrounded": { "mmmu": 82.9, "mmmuPro": 75.8, "realWorldQa": 84.1, "dynaMath": 85.6, "mStar": 81.4, "simpleVqa": 56.1, "charxiv": 78.4, "ccOcr": 81.2, "countBench": 97.8, "refcocoAvg": 92.5, "erqa": 62.5, "videoMmeWithSub": 87.7, "videoMmmu": 84.4, "mlvuAvg": 86.6, "vStar": 94.7, "aaMmmuPro": 74.6 }, "knowledge": { "mmluPro": 86.2, "mmluRedux": 93.5, "superGpqa": 66, "cEval": 91.4, "gpqa": 87.8, "hle": 24, "artificialAnalysis": 37.7, "aaGpqaDiamond": 84.2, "aaHle": 23.1, "aaOmniscienceIndex": -20, "omniscienceAccuracy": 19.6, "omniscienceHallucinationRate": 49.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.6 }, "math": { "hmmtFeb2025": 93.8, "hmmtNov2025": 90.7, "hmmtFeb2026": 84.3, "mmAnswerBench": 80.8, "aime2026": 94.1 } } }, { "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", "id": 294, "releaseDate": "2026-07-23", "market": null, "isRegional": false, "family": { "familyKey": "ling-3-0", "familyName": "Ling 3.0", "variantType": "flash", "snapshotLabel": null, "baseFamilyModelKey": "ling-3-0-flash", "relatedModelKeys": [ "ling-3-0-flash-fin", "ling-3-0-flash-fp8", "ling-2-6-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "ling-2-6-flash" }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": 53.9, "coding": 38.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 29.1, "multilingual": null, "instructionFollowing": 79.2, "math": 73.8 }, "verifiedDisplayCategoryScores": { "agentic": 53.9, "coding": 38.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 29.1, "multilingual": null, "instructionFollowing": 79.2, "math": 73.8 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 112, "categoryRanks": { "agentic": 68, "coding": 56, "instructionFollowing": 25 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench21": 57, "aaTau3Banking": 28, "mcpAtlas": 65.5, "skillsBench": 44.8, "bfclV4": 73, "gdpvalAa": 1107, "wideResearch": 73.6, "browseComp": 72.2, "draco": 70.4, "aaAgenticIndex": 29.31, "gdpvalAaNormalized": 30.3 }, "coding": { "swePro": 56.6, "sweMultilingual": 72.4, "terminalBench21": 57, "liveCodeBenchV5": 82.8, "sciCode": 41.24, "aaCodingIndex": 50.65, "aaSciCode": 41.1 }, "reasoning": { "lcr": 67, "critpt": 1.7 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 84.97, "gpqaDiamond": 84.97, "hle": 22.7, "artificialAnalysis": 37.82, "aaGpqaDiamond": 85.5, "aaHle": 23.7, "aaOmniscienceIndex": -17.9, "omniscienceAccuracy": 18.2, "omniscienceHallucinationRate": 44.1 }, "multilingual": {}, "instructionFollowing": { "ifBench": 74.5 }, "math": { "aime2026": 93.2, "hmmtFeb2026": 87, "imoAnswerBench": 83.7 } } }, { "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", "id": 53, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-5", "familyName": "Kimi K2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-5", "relatedModelKeys": [ "kimi-k2-5-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 48, "verifiedDisplayScore": 49, "displayCategoryScores": { "agentic": 29.4, "coding": 53, "reasoning": 44.9, "multimodalGrounded": 61.2, "knowledge": 54.6, "multilingual": 38.2, "instructionFollowing": 91.2, "math": 62.5 }, "verifiedDisplayCategoryScores": { "agentic": 29.4, "coding": 53, "reasoning": 44.9, "multimodalGrounded": 61.2, "knowledge": 54.6, "multilingual": 38.2, "instructionFollowing": 91.2, "math": 62.5 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 84, "categoryRanks": { "agentic": 117, "coding": 44, "knowledge": 48, "multilingual": 8, "instructionFollowing": 9, "math": 5 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": true } }, "coverage": { "trustedBenchmarkCount": 40, "verifiedBenchmarkCount": 40, "rankableBenchmarkCount": 40, "generatedBenchmarkCount": 0, "scoreConfidence": 4 }, "benchmarks": { "agentic": { "terminalBench2": 50.8, "browseComp": 60.6, "clawEval": 52.3, "qwenClawBench": 54.3, "tau3Bench": 65.7, "deepSearchQa": 77.1, "deepPlanning": 14.4, "toolathlon": 27.8, "mcpAtlas": 29.5, "mcpTasks": 59.1, "wideResearch": 72.7, "tau2Bench": 95.9, "apexAgentsAa": 11.5, "gertLabs": 45.88, "researchClawBench": 14, "jobBench": 8.73, "aaAgenticIndex": 21.69, "gdpvalAaNormalized": 25.3, "gdpvalAa": 1006 }, "coding": { "sweVerified": 76.8, "sweVerifiedArcee": 70.8, "liveCodeBenchV6": 85, "swePro": 50.7, "sweMultilingual": 73, "sweRebench": 58.5, "reactNativeEvals": 77.2, "sciCode": 48.7, "aaSciCode": 49, "aaCodingIndex": 46.78 }, "reasoning": { "longBenchV2": 61, "lcr": 73, "critpt": 3.1 }, "multimodalGrounded": { "mmmuPro": 78.5, "videoMme": 87.4, "mmvu": 80.4, "videoMmmu": 86.6, "aaMmmuPro": 75.4, "designArenaWebsite": 1267 }, "knowledge": { "gpqa": 87.6, "gpqaDiamond": 87.6, "superGpqa": 69.2, "mmluPro": 87.1, "mmluProArcee": 87.1, "hle": 30.1, "artificialAnalysis": 36.02, "aaGpqaDiamond": 87.9, "aaHle": 30.7, "aaOmniscienceIndex": -7.3, "omniscienceAccuracy": 35.2, "omniscienceHallucinationRate": 65.7 }, "multilingual": { "mmluProX": 82.3, "nova63": 56 }, "instructionFollowing": { "ifeval": 93.9, "aaIfBench": 70.2 }, "math": { "aime2025": 96.1, "aime2026": 95.8, "aime2025Arcee": 96.3, "hmmtFeb2025": 95.4, "hmmtNov2025": 91.1, "hmmtFeb2026": 87.1, "mmAnswerBench": 81.8, "frontierMathV2Tiers13": 27.9, "frontierMathV2Tier4": 4.2 } } }, { "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", "id": 71, "releaseDate": "2026-06-04", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-ultra-500b", "familyName": "Nemotron 3 Ultra", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-ultra-500b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 48, "rawOverallScore": 47, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": 29.4, "coding": 49.4, "reasoning": 53.4, "multimodalGrounded": null, "knowledge": 50.7, "multilingual": 47.4, "instructionFollowing": 91.9, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 27.4, "coding": 47.7, "reasoning": 53.4, "multimodalGrounded": null, "knowledge": 49.7, "multilingual": 47.4, "instructionFollowing": 91.9, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 164, "categoryRanks": { "agentic": 141, "coding": 140, "knowledge": 53, "multilingual": 7, "instructionFollowing": 7 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 56.4, "pinchBench": 90, "browseComp": 44.4, "tau3Bench": 70.9, "gdpvalAaNormalized": 33.1, "hleWithTools": 37.4, "aaAgenticIndex": 27.5, "tau2Bench": 83.3, "gdpvalAa": 1162, "aaBriefcaseElo": 879, "aaEnterpriseOpsGym": 28.9, "aaHarveyLab": 81.7, "terminalBenchHard": 36.4, "aaAutomationBench": 5.7 }, "coding": { "sweVerified": 71.9, "sweMultilingual": 67.7, "liveCodeBenchV6": 89, "sciCode": 44.6, "terminalBench2": 56.4, "aaCodingIndex": 49.27, "aaSciCode": 39.9 }, "reasoning": { "lcr": 67, "critpt": 3.1, "longBenchV2": 61.9 }, "multimodalGrounded": { "designArenaWebsite": 1146 }, "knowledge": { "gpqa": 87, "gpqaDiamond": 87, "hle": 26.7, "hleNoTools": 26.7, "mmluPro": 86.8, "omniscienceAccuracy": 21.6, "artificialAnalysis": 38.32, "aaGpqaDiamond": 86.7, "aaHle": 28.4, "aaOmniscienceIndex": -0.4, "omniscienceHallucinationRate": 29.7, "aaOpennessIndex": 83.3 }, "multilingual": { "mmluProX": 83 }, "instructionFollowing": { "ifBench": 81.7, "aaIfBench": 81.4 }, "math": {} } }, { "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", "id": 47, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-27b", "familyName": "Qwen3.5-27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-27b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 48, "rawOverallScore": 47, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": 14.9, "coding": 57.4, "reasoning": 41.1, "multimodalGrounded": null, "knowledge": 79, "multilingual": 36.8, "instructionFollowing": 93.9, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 14.9, "coding": 57.4, "reasoning": 41.1, "multimodalGrounded": null, "knowledge": 79, "multilingual": 36.8, "instructionFollowing": 93.9, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 74, "categoryRanks": { "agentic": 71, "coding": 52, "multimodalGrounded": 34, "knowledge": 16, "multilingual": 9, "instructionFollowing": 3 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 41.6, "browseComp": 61, "osWorldVerified": 56.2, "tau2Bench": 93.9, "gertLabs": 39.41 }, "coding": { "sweVerified": 72.4, "sweRebench": 58.9, "aaSciCode": 39.5 }, "reasoning": { "longBenchV2": 60.6, "lcr": 72.3, "critpt": 0.9 }, "multimodalGrounded": { "mmmu": 82.3, "mmvu": 73.3, "mathVision": 86, "vStar": 93.7, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 86.1, "superGpqa": 65.6, "gpqa": 85.5, "artificialAnalysis": 34.6, "aaGpqaDiamond": 85.8, "aaHle": 23.9, "aaOmniscienceIndex": -44, "omniscienceAccuracy": 20.7, "omniscienceHallucinationRate": 81.5 }, "multilingual": { "mmluProX": 82.2 }, "instructionFollowing": { "ifeval": 95, "aaIfBench": 75.6 }, "math": {} } }, { "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", "id": 37, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-122b-a10b", "familyName": "Qwen3.5-122B-A10B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-122b-a10b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 47, "overallScore": 47, "rawOverallScore": 46, "verifiedDisplayScore": 47, "displayCategoryScores": { "agentic": 25, "coding": 51, "reasoning": 37.3, "multimodalGrounded": 46.1, "knowledge": 79.9, "multilingual": 36.8, "instructionFollowing": 89.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 25, "coding": 51, "reasoning": 37.3, "multimodalGrounded": 46.1, "knowledge": 79.9, "multilingual": 36.8, "instructionFollowing": 89.8, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 77, "categoryRanks": { "agentic": 70, "coding": 90, "knowledge": 15, "multilingual": 10, "instructionFollowing": 14 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 49.4, "browseComp": 63.8, "osWorldVerified": 58, "tau2Bench": 93.6, "aaAgenticIndex": 21.27, "gdpvalAaNormalized": 24.4, "gdpvalAa": 987 }, "coding": { "sweVerified": 72, "aaCodingIndex": 45.71, "aaSciCode": 42 }, "reasoning": { "longBenchV2": 60.2, "lcr": 70.3, "critpt": 0.6 }, "multimodalGrounded": { "mmmu": 83.9, "mmvu": 74.7, "mathVision": 86.2, "charxiv": 77.2, "vStar": 93.2, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 86.7, "superGpqa": 67.1, "gpqa": 86.6, "artificialAnalysis": 32.85, "aaGpqaDiamond": 85.7, "aaHle": 25.2, "aaOmniscienceIndex": -41.5, "omniscienceAccuracy": 24.4, "omniscienceHallucinationRate": 87.1 }, "multilingual": { "mmluProX": 82.2 }, "instructionFollowing": { "ifeval": 93.4, "aaIfBench": 75.7 }, "math": {} } }, { "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", "id": 76, "releaseDate": "2026-04-15", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-35b-a3b", "familyName": "Qwen3.6-35B-A3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-6-35b-a3b", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-5-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 41, "rawOverallScore": 41, "verifiedDisplayScore": 41, "displayCategoryScores": { "agentic": 36.9, "coding": 23.8, "reasoning": null, "multimodalGrounded": 43.5, "knowledge": 42.8, "multilingual": null, "instructionFollowing": null, "math": 71.6 }, "verifiedDisplayCategoryScores": { "agentic": 36.9, "coding": 23.8, "reasoning": null, "multimodalGrounded": 43.5, "knowledge": 42.8, "multilingual": null, "instructionFollowing": null, "math": 71.6 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 123, "categoryRanks": { "agentic": 88, "coding": 73, "multimodalGrounded": 26, "knowledge": 56 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 39, "verifiedBenchmarkCount": 39, "rankableBenchmarkCount": 39, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 51.5, "clawEval": 68.7, "qwenClawBench": 52.6, "qwenWebBench": 1397, "tau3Bench": 67.2, "vitaBench": 35.6, "deepPlanning": 25.9, "toolathlon": 26.9, "mcpAtlas": 62.8, "wideResearch": 60.1, "aaAgenticIndex": 21.62, "tau2Bench": 95.3, "gdpvalAaNormalized": 27.8, "gdpvalAa": 1056, "gertLabs": 42.65 }, "coding": { "sweVerified": 73.4, "sweMultilingual": 67.2, "swePro": 49.5, "terminalBench2": 51.5, "liveCodeBench": 80.4, "nl2Repo": 29.4, "aaCodingIndex": 41.88, "aaSciCode": 35.8 }, "reasoning": { "lcr": 66.7, "critpt": 0.3 }, "multimodalGrounded": { "mmmu": 81.7, "mmmuPro": 75.3, "realWorldQa": 85.3, "omniDocBench15": 89.9, "charxiv": 78, "simpleVqa": 58.9, "ccOcr": 81.9, "ai2dTest": 92.7, "refcocoAvg": 92, "odinw13": 50.8, "videoMmeWithSub": 86.6, "videoMmeNoSub": 82.5, "videoMmmu": 83.7, "mlvuAvg": 86.2, "aaMmmuPro": 75 }, "knowledge": { "mmluPro": 85.2, "superGpqa": 64.7, "cEval": 90, "gpqa": 86, "hle": 21.4, "artificialAnalysis": 32.13, "aaGpqaDiamond": 84.1, "aaHle": 22.2, "aaOmniscienceIndex": -22.2, "omniscienceAccuracy": 18.8, "omniscienceHallucinationRate": 50.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 64.4 }, "math": { "hmmtFeb2025": 90.7, "hmmtNov2025": 89.1, "hmmtFeb2026": 83.6, "mmAnswerBench": 78.9, "aime2026": 92.7 } } }, { "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", "id": 60, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-35b-a3b", "familyName": "Qwen3.5-35B-A3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-35b-a3b", "relatedModelKeys": [ "qwen3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 40, "overallScore": 40, "rawOverallScore": 40, "verifiedDisplayScore": 40, "displayCategoryScores": { "agentic": 12.9, "coding": 46.3, "reasoning": 26, "multimodalGrounded": null, "knowledge": 77.8, "multilingual": 21.1, "instructionFollowing": 85.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 12.9, "coding": 46.3, "reasoning": 26, "multimodalGrounded": null, "knowledge": 77.8, "multilingual": 21.1, "instructionFollowing": 85.4, "math": null } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 100, "categoryRanks": { "agentic": 82, "coding": 89, "multimodalGrounded": 35, "knowledge": 17, "multilingual": 11, "instructionFollowing": 22 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": true, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 40.5, "browseComp": 61, "osWorldVerified": 54.5, "tau2Bench": 89.2, "gertLabs": 28.96 }, "coding": { "sweVerified": 69.2, "sweRebench": 53.7, "aaSciCode": 37.7 }, "reasoning": { "longBenchV2": 59, "lcr": 68.3, "critpt": 0.9 }, "multimodalGrounded": { "mmmu": 81.4, "mmvu": 72.3, "mathVision": 83.9, "vStar": 92.7, "aaMmmuPro": 72.7 }, "knowledge": { "mmluPro": 85.3, "superGpqa": 63.4, "gpqa": 84.2, "artificialAnalysis": 29.91, "aaGpqaDiamond": 84.5, "aaHle": 21, "aaOmniscienceIndex": -48.1, "omniscienceAccuracy": 20.1, "omniscienceHallucinationRate": 85.4 }, "multilingual": { "mmluProX": 81 }, "instructionFollowing": { "ifeval": 91.9, "aaIfBench": 72.5 }, "math": {} } }, { "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", "id": 48, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-7", "familyName": "GLM-4.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 36, "overallScore": 36, "rawOverallScore": 36, "verifiedDisplayScore": 36, "displayCategoryScores": { "agentic": 11.5, "coding": 52.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 27.6, "multilingual": null, "instructionFollowing": null, "math": 26 }, "verifiedDisplayCategoryScores": { "agentic": 11.5, "coding": 51.9, "reasoning": null, "multimodalGrounded": null, "knowledge": 27.6, "multilingual": null, "instructionFollowing": null, "math": 26 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": true, "overallRank": 66, "categoryRanks": { "agentic": 60, "coding": 67 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 9, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 41, "browseComp": 52, "vitaBench": 15.5, "aaAgenticIndex": 26.22, "tau2Bench": 95.9, "gertLabs": 39.95, "gdpvalAaNormalized": 33.3, "gdpvalAa": 1166 }, "coding": { "sweVerified": 73.8, "liveCodeBench": 84.9, "sweRebench": 58.7, "aaCodingIndex": 45.26, "aaSciCode": 45.1, "aaLiveCodeBench": 89.4 }, "reasoning": { "lcr": 68, "critpt": 1.7 }, "multimodalGrounded": { "designArenaWebsite": 1244 }, "knowledge": { "gpqa": 85.7, "mmluPro": 84.3, "hle": 24.8, "artificialAnalysis": 34.46, "aaGpqaDiamond": 85.9, "aaHle": 27.4, "aaOmniscienceIndex": -36.4, "omniscienceAccuracy": 29.3, "omniscienceHallucinationRate": 93 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.9 }, "math": { "aime2025": 95.7, "frontierMathV2Tiers13": 2.439, "frontierMathV2Tier4": 0 } } }, { "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", "id": 127, "releaseDate": "2026-03-17", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-pro", "gpt-5-4-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-5-nano" }, "scores": { "displayScore": 36, "overallScore": 34, "rawOverallScore": 34, "verifiedDisplayScore": 34, "displayCategoryScores": { "agentic": 16.9, "coding": 57, "reasoning": null, "multimodalGrounded": 15.1, "knowledge": 51.6, "multilingual": null, "instructionFollowing": null, "math": 44.2 }, "verifiedDisplayCategoryScores": { "agentic": 14.9, "coding": null, "reasoning": null, "multimodalGrounded": 15.1, "knowledge": 50.1, "multilingual": null, "instructionFollowing": null, "math": 44.2 } }, "ranking": { "rankingEligible": true, "verifiedRankingEligible": false, "overallRank": 32, "categoryRanks": { "agentic": 98, "coding": 126, "knowledge": 50 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 46.3, "osWorldVerified": 39, "mcpAtlas": 56.1, "toolathlon": 35.5, "tau2Bench": 92.5, "aaAgenticIndex": 29.67, "apexAgentsAa": 24.9, "gdpvalAaNormalized": 30.2, "gdpvalAa": 1104 }, "coding": { "vibeCodeBench": 26.097, "aaCodingIndex": 56.07, "aaSciCode": 46.9 }, "reasoning": { "lcr": 72, "critpt": 9.3 }, "multimodalGrounded": { "mmmuPro": 66.1, "mmmuProPython": 69.5, "aaMmmuPro": 65.4 }, "knowledge": { "gpqa": 82.8, "hle": 37.7, "hleNoTools": 24.3, "artificialAnalysis": 39.71, "aaGpqaDiamond": 81.7, "aaHle": 28.3, "aaOmniscienceIndex": -29.5, "omniscienceAccuracy": 25.7, "omniscienceHallucinationRate": 74.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": { "frontierMathV2Tiers13": 25.86, "frontierMathV2Tier4": 6.25 } } }, { "slug": "claude-mythos-5", "canonicalModelKey": "claude-mythos-5", "model": "Claude Mythos 5", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M+", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 86, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5.md", "id": 9, "releaseDate": "2026-06-09", "market": null, "isRegional": false, "family": { "familyKey": "claude-mythos", "familyName": "Claude Mythos", "variantType": "restricted", "snapshotLabel": null, "baseFamilyModelKey": "claude-mythos-5", "relatedModelKeys": [ "claude-mythos-preview", "claude-mythos-5-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 86, "overallScore": 86, "rawOverallScore": 86, "verifiedDisplayScore": 86, "displayCategoryScores": { "agentic": 97.7, "coding": 83, "reasoning": null, "multimodalGrounded": 84.8, "knowledge": 97.1, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 97.7, "coding": 83, "reasoning": null, "multimodalGrounded": 84.8, "knowledge": 97.1, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 88, "osWorldVerified": 85, "browseComp": 88, "cyberGym": 83.8 }, "coding": { "sweVerified": 95.5, "swePro": 80.3, "terminalBench2": 88 }, "reasoning": {}, "multimodalGrounded": { "sweMultimodal": 54.9, "charxiv": 93.5, "charxivNoTools": 88.9 }, "knowledge": { "gpqa": 94.1, "hle": 64.5, "hleNoTools": 59 }, "multilingual": { "sweMultilingual": 92.2 }, "instructionFollowing": {}, "math": { "usamo2026": 97.6 }, "external": { "exploitBench": 78, "firefox147WorkingExploit": 88.4, "anthropicOssFuzzAnyCrash": 80, "anthropicOssFuzzWritePrimitive": 32.4, "lastOnesCyberRangeCompletion": 60 } } }, { "slug": "sakana-fugu-ultra", "canonicalModelKey": "sakana-fugu-ultra", "model": "Sakana Fugu-Ultra", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 78, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu-ultra", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-ultra.md", "id": 266, "releaseDate": "2026-06-22", "market": null, "isRegional": false, "family": { "familyKey": "sakana-fugu", "familyName": "Sakana Fugu", "variantType": "ultra", "snapshotLabel": "Ultra", "baseFamilyModelKey": "sakana-fugu", "relatedModelKeys": [ "sakana-fugu-ultra-v1-1", "sakana-fugu" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 78, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 82.4, "coding": 76.8, "reasoning": 82.2, "multimodalGrounded": 71.9, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 82.4, "coding": 76.8, "reasoning": 82.2, "multimodalGrounded": 71.9, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 82.1 }, "coding": { "swePro": 73.7, "terminalBench2": 82.1, "liveCodeBenchV6": 93.2, "liveCodeBenchPro": 90.8, "sciCode": 58.7 }, "reasoning": { "mrcrv2": 93.6 }, "multimodalGrounded": { "charxiv": 86.6 }, "knowledge": { "gpqa": 95.5, "gpqaDiamond": 95.5, "hleNoTools": 50 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 40, "releaseDate": "2026-03-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-4", "familyName": "GPT-5.4", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-4", "relatedModelKeys": [ "gpt-5-4", "gpt-5-4-mini", "gpt-5-4-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 78, "overallScore": 78, "rawOverallScore": 77, "verifiedDisplayScore": 78, "displayCategoryScores": { "agentic": 81.8, "coding": null, "reasoning": 77.6, "multimodalGrounded": 87.6, "knowledge": 86.6, "multilingual": null, "instructionFollowing": null, "math": 70.6 }, "verifiedDisplayCategoryScores": { "agentic": 81.8, "coding": null, "reasoning": 77.6, "multimodalGrounded": 87.6, "knowledge": 86.6, "multilingual": null, "instructionFollowing": null, "math": 70.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 54, "categoryRanks": { "agentic": 23 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "browseComp": 89.3 }, "coding": {}, "reasoning": { "arcAgi2": 83.3, "critpt": 30 }, "multimodalGrounded": { "mmmuPro": 94 }, "knowledge": { "hle": 58.7, "frontierScience": 36.7, "frontierScienceResearch": 36.7, "hleNoTools": 42.7 }, "multilingual": {}, "instructionFollowing": {}, "math": { "ipho2025Theory": 93.5, "frontierMath": 50, "frontierMathV2Tiers13": 50, "frontierMathV2Tier4": 37.5 } } }, { "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", "id": 25, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-5", "familyName": "GPT-5.5", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-5", "relatedModelKeys": [ "gpt-5-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 75, "overallScore": 75, "rawOverallScore": 75, "verifiedDisplayScore": 75, "displayCategoryScores": { "agentic": 83.1, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 84, "multilingual": null, "instructionFollowing": null, "math": 72 }, "verifiedDisplayCategoryScores": { "agentic": 83.1, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 84, "multilingual": null, "instructionFollowing": null, "math": 72 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 42, "categoryRanks": { "agentic": 20 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "browseComp": 90.1 }, "coding": {}, "reasoning": { "critpt": 30.6 }, "multimodalGrounded": {}, "knowledge": { "hle": 57.2, "hleNoTools": 43.1 }, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMath": 52.4, "frontierMathV2Tiers13": 51, "frontierMathV2Tier4": 39.6 } } }, { "slug": "holo3-35b-a3b", "canonicalModelKey": "holo3-35b-a3b", "model": "Holo3-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 74, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-35b-a3b.md", "id": 3, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "holo3", "familyName": "Holo3", "variantType": "35b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-122b-a10b", "relatedModelKeys": [ "holo3-122b-a10b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-30b-a3b" }, "scores": { "displayScore": 74, "overallScore": 74, "rawOverallScore": 74, "verifiedDisplayScore": 74, "displayCategoryScores": { "agentic": 81.7, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 81.7, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 43 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "osWorldVerified": 82.56 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "swe-1-7", "canonicalModelKey": "swe-1-7", "model": "SWE-1.7", "creator": "Cognition", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 73, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/swe-1-7", "markdownUrl": "https://benchlm.ai/md/models/swe-1-7.md", "id": 279, "releaseDate": "2026-07-08", "market": null, "isRegional": false, "family": { "familyKey": "swe", "familyName": "SWE", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "swe-1-7", "relatedModelKeys": [ "kimi-k2-7-code" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 73, "overallScore": 73, "rawOverallScore": 73, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 81.5, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 81.5, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 40 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 81.5 }, "coding": { "frontierCode": 42.3, "terminalBench2": 81.5, "sweMultilingual": 77.8 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "sakana-fugu", "canonicalModelKey": "sakana-fugu", "model": "Sakana Fugu", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 73, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu.md", "id": 267, "releaseDate": "2026-06-22", "market": null, "isRegional": false, "family": { "familyKey": "sakana-fugu", "familyName": "Sakana Fugu", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "sakana-fugu", "relatedModelKeys": [ "sakana-fugu-ultra" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 73, "overallScore": 73, "rawOverallScore": 73, "verifiedDisplayScore": 73, "displayCategoryScores": { "agentic": 79.6, "coding": 66.8, "reasoning": 73.1, "multimodalGrounded": 67.8, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 79.6, "coding": 66.8, "reasoning": 73.1, "multimodalGrounded": 67.8, "knowledge": 85.9, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 80.2 }, "coding": { "swePro": 59, "terminalBench2": 80.2, "liveCodeBenchV6": 92.9, "liveCodeBenchPro": 87.8, "sciCode": 60.1 }, "reasoning": { "mrcrv2": 86.6 }, "multimodalGrounded": { "charxiv": 85.1 }, "knowledge": { "gpqa": 95.5, "gpqaDiamond": 95.5, "hleNoTools": 47.2 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 389, "releaseDate": "2026-08-12", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-6", "familyName": "Grok 4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-6", "relatedModelKeys": [ "grok-4-5", "grok-4-3", "grok-4-20-beta" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "grok-4-5" }, "scores": { "displayScore": 72, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 84.9, "coding": 62.1, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 47, "categoryRanks": { "agentic": 12, "coding": 24, "knowledge": 28 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "frontierBench": 26.49, "apexAgents": 57.5, "aaAgenticIndex": 58.68, "gdpvalAaNormalized": 61.5, "gdpvalAa": 1730, "aaBriefcaseElo": 1551, "aaTau3Banking": 50.7, "aaTerminalBench21": 88.4, "aaEnterpriseOpsGym": 48.3 }, "coding": { "deepSwe": 65.9, "cursorBench32": 70.8, "frontierCode11Extended": 61.3, "aaCodingIndex": 76.79, "aaSciCode": 53.6, "vulcanBench": 87 }, "reasoning": { "lcr": 75, "critpt": 17.1 }, "multimodalGrounded": { "designArenaWebsite": 1316 }, "knowledge": { "artificialAnalysis": 60.92, "aaGpqaDiamond": 94.9, "aaHle": 42.9, "aaOmniscienceIndex": 30.5, "omniscienceAccuracy": 48.2, "omniscienceHallucinationRate": 34.3 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 399, "releaseDate": "2026-08-14", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "flagship", "snapshotLabel": "5.3", "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5-2", "glm-5-1", "glm-5", "glm-5-reasoning", "glm-5-turbo", "glm-5v-turbo" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "glm-5-2" }, "scores": { "displayScore": 71, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 85.1, "coding": 59.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 63.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 50, "categoryRanks": { "agentic": 6, "coding": 13, "knowledge": 37 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench21": 88.2, "terminalBench3": 28.3, "cyberGym": 84.5, "exploitGym": 15, "toolathlonVerified": 73, "automationBench": 48.2, "agentsLastExam": 28.5, "hleWithTools": 62.5, "gdpvalAa": 1769, "aaAgenticIndex": 59.1, "gdpvalAaNormalized": 62.9, "aaTau3Banking": 50.3, "aaTerminalBench21": 83.9, "aaBriefcaseElo": 1529 }, "coding": { "terminalBench21": 88.2, "terminalBench3": 28.3, "deepSwe": 66.9, "nl2Repo": 58, "programBench": 19, "frontierSwe": 78.1, "sweMarathon": 42.5, "postTrainBench": 39.8, "aaCodingIndex": 74.76, "aaSciCode": 56.5, "vulcanBench": 78.3, "openHarmonyBench": 60.8 }, "reasoning": { "lcr": 76.3, "critpt": 19.1 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 59.51, "aaGpqaDiamond": 91.7, "aaHle": 42.3, "aaOmniscienceIndex": 14.3, "omniscienceAccuracy": 33.9, "omniscienceHallucinationRate": 29.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {}, "external": { "exploitBench": 54.4 } } }, { "slug": "exaone-4-0-32b", "canonicalModelKey": "exaone-4-0-32b", "model": "Exaone 4.0 32B", "creator": "LG AI Research", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/exaone-4-0-32b", "markdownUrl": "https://benchlm.ai/md/models/exaone-4-0-32b.md", "id": 2, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-4", "familyName": "Exaone 4.0", "variantType": "32b", "snapshotLabel": null, "baseFamilyModelKey": "exaone-4-0-32b", "relatedModelKeys": [ "exaone-4-0-1-2b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 70, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 79, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 79, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 4.1 }, "coding": { "aaSciCode": 25.2 }, "reasoning": { "lcr": 9, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "mmluPro": 81.8, "artificialAnalysis": 5.73, "aaGpqaDiamond": 62.8, "aaHle": 5, "aaOmniscienceIndex": -62.8, "omniscienceAccuracy": 10.6, "omniscienceHallucinationRate": 82.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.5 }, "math": { "aime2025": 85.3 }, "korean": {} } }, { "slug": "holo3-122b-a10b", "canonicalModelKey": "holo3-122b-a10b", "model": "Holo3-122B-A10B", "creator": "H Company", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 70, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-122b-a10b", "markdownUrl": "https://benchlm.ai/md/models/holo3-122b-a10b.md", "id": 13, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "holo3", "familyName": "Holo3", "variantType": "122b-a10b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-122b-a10b", "relatedModelKeys": [ "holo3-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "holo2-235b-a22b" }, "scores": { "displayScore": 70, "overallScore": 70, "rawOverallScore": 70, "verifiedDisplayScore": 70, "displayCategoryScores": { "agentic": 75.2, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 75.2, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 46 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "osWorldVerified": 78.85 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 398, "releaseDate": "2026-08-18", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-5", "familyName": "Ornith 1.5", "variantType": "397b", "snapshotLabel": "397B", "baseFamilyModelKey": "ornith-1-5-397b", "relatedModelKeys": [ "ornith-1-5-35b-a3b", "ornith-1-5-9b", "ornith-1-0-397b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "ornith-1-0-397b" }, "scores": { "displayScore": 69, "overallScore": 69, "rawOverallScore": 68, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 77.4, "coding": 68.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 65.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 77.4, "coding": 68.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 65.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 25, "categoryRanks": { "agentic": 17, "coding": 36 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 12, "verifiedBenchmarkCount": 12, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 86.1, "hleWithTools": 56.1, "mcpAtlas": 80, "toolathlonVerified": 71.2, "wideResearch": 80.8, "browseComp": 86.6, "clawEval": 81.4 }, "coding": { "terminalBench21": 86.1, "sweVerified": 86, "swePro": 65.1, "sweMultilingual": 79.6, "deepSwe": 56, "frontierBench": 13.5, "nl2Repo": 59.5 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 92.8, "gpqaDiamond": 92.8, "hle": 44.6, "hleNoTools": 44.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 394, "releaseDate": "2026-08-14", "market": null, "isRegional": false, "family": { "familyKey": "dots3-note", "familyName": "dots3-note", "variantType": "preview", "snapshotLabel": "Preview", "baseFamilyModelKey": "dots3-note-preview", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 69, "overallScore": 69, "rawOverallScore": 68, "verifiedDisplayScore": 69, "displayCategoryScores": { "agentic": 72, "coding": 56.7, "reasoning": 76, "multimodalGrounded": 64.1, "knowledge": 76, "multilingual": null, "instructionFollowing": 92.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 72, "coding": 56.7, "reasoning": 76, "multimodalGrounded": 64.1, "knowledge": 76, "multilingual": null, "instructionFollowing": 92.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 21, "categoryRanks": { "agentic": 19, "coding": 32, "instructionFollowing": 6 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 26, "verifiedBenchmarkCount": 26, "rankableBenchmarkCount": 26, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "clawEval": 73.4, "terminalBench21": 75.1, "toolathlonVerified": 55.6, "skillsBench": 52.8, "apexAgents": 30.8, "browseComp": 83.3, "hleWithTools": 52.6, "deepSearchQa": 92.1, "wideResearch": 78.9 }, "coding": { "codeforces": 3056, "liveCodeBenchV6": 91.5, "terminalBench21": 75.1, "sweVerified": 78.4, "sweMultilingual": 75.7, "swePro": 61, "nl2Repo": 49.8 }, "reasoning": { "arcAgi2": 81.4 }, "multimodalGrounded": { "simpleVqa": 72.5, "mmmuPro": 79.1, "mathVision": 87.7, "zeroBench": 19, "charxivNoTools": 83.1, "gdpPdf": 60.7, "perceptionBench": 53.4, "babyVision": 50, "mmvu": 79.9, "videoMmmu": 86.8 }, "knowledge": { "hle": 52.6 }, "multilingual": {}, "instructionFollowing": { "ifBench": 80.4, "ifeval": 93.9 }, "math": { "imoAnswerBench": 90.9 } } }, { "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", "id": 287, "releaseDate": "2026-07-21", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-6-flash", "familyName": "Gemini 3.6 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-6-flash", "relatedModelKeys": [ "gemini-3-5-flash", "gemini-3-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gemini-3-5-flash" }, "scores": { "displayScore": 69, "overallScore": 74, "rawOverallScore": 74, "verifiedDisplayScore": 74, "displayCategoryScores": { "agentic": 82.5, "coding": 60.1, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.8, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 82.5, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 10, "categoryRanks": { "agentic": 118, "coding": 17, "knowledge": 25 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "osWorldVerified": 83, "gdpvalAa": 1423, "aaAgenticIndex": 40.51, "gdpvalAaNormalized": 45.7, "aaAutomationBench": 51.1 }, "coding": { "deepSwe": 49, "cursorBench32": 53.5, "aaCodingIndex": 69.24, "aaSciCode": 52.7 }, "reasoning": { "lcr": 79, "critpt": 10.6 }, "multimodalGrounded": { "aaMmmuPro": 83.2, "designArenaWebsite": 1320 }, "knowledge": { "artificialAnalysis": 51.58, "aaGpqaDiamond": 92.8, "aaHle": 40.8, "aaOmniscienceIndex": 22.1, "omniscienceAccuracy": 50, "omniscienceHallucinationRate": 55.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 410, "releaseDate": "2026-08-28", "market": null, "isRegional": false, "family": { "familyKey": "hy4", "familyName": "Hy4", "variantType": "preview", "snapshotLabel": "Preview", "baseFamilyModelKey": "hy4-preview", "relatedModelKeys": [ "hy3" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "hy3" }, "scores": { "displayScore": 68, "overallScore": 68, "rawOverallScore": 67, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": null, "coding": 55.5, "reasoning": null, "multimodalGrounded": 84.5, "knowledge": 82.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 55.5, "reasoning": null, "multimodalGrounded": 84.5, "knowledge": 82.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 7, "categoryRanks": { "agentic": 7, "coding": 11 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 85.4, "cyberGym": 78.4, "wideResearch": 83.9, "draco": 77.2, "mcpAtlas": 83.7, "toolathlonVerified": 74.1, "apexAgents": 37.1, "skillsBench": 62.9, "jobBench": 61.7, "agentsLastExam": 22.8, "gdpvalAa": 1678, "automationBench": 32.1, "bankerToolBench": 78.6, "hleWithTools": 55.4 }, "coding": { "terminalBench21": 85.4, "swePro": 65.7, "sweMultilingual": 82.9, "deepSwe": 64.3, "nl2Repo": 58.9, "programBench": 17.5, "postTrainBench": 35.6, "sweMarathon": 31.9 }, "reasoning": { "critpt": 16.9 }, "multimodalGrounded": { "officeQaPro": 66.2 }, "knowledge": { "gpqa": 92.3, "gpqaDiamond": 92.3, "hle": 55.4, "hleNoTools": 43.4 }, "multilingual": {}, "instructionFollowing": {}, "math": { "apex": 74.2 } } }, { "slug": "ornith-1-0-397b", "canonicalModelKey": "ornith-1-0-397b", "model": "Ornith-1.0-397B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 68, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-397b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-397b.md", "id": 268, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-0", "familyName": "Ornith 1.0", "variantType": "397b", "snapshotLabel": "397B", "baseFamilyModelKey": "ornith-1-0-397b", "relatedModelKeys": [ "ornith-1-0-35b", "ornith-1-0-9b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 68, "overallScore": 68, "rawOverallScore": 66, "verifiedDisplayScore": 68, "displayCategoryScores": { "agentic": 75.6, "coding": 62.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 75.6, "coding": 62.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 45, "coding": 49 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 77.5, "clawEval": 77.1 }, "coding": { "sweVerified": 82.4, "swePro": 62.2, "sweMultilingual": 78.9, "nl2Repo": 48.2, "terminalBench2": 77.5 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 408, "releaseDate": "2026-08-26", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "flash", "snapshotLabel": "5.3 Flash", "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5-3", "glm-5-2", "glm-5-1", "glm-5", "glm-5-reasoning", "glm-5-turbo", "glm-5v-turbo", "glm-4-7-flash" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "glm-4-7-flash" }, "scores": { "displayScore": 67, "overallScore": 72, "rawOverallScore": 70, "verifiedDisplayScore": 72, "displayCategoryScores": { "agentic": 75.6, "coding": 60.7, "reasoning": null, "multimodalGrounded": 80.7, "knowledge": 62.7, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 80.7, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 56, "categoryRanks": { "agentic": 38, "coding": 20, "multimodalGrounded": 8, "knowledge": 38 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench21": 84.3, "toolathlonVerified": 78.4, "automationBench": 48.8, "agentsLastExam": 26.3, "hleWithTools": 55.3, "gdpvalAa": 1773, "aaTau3Banking": 47.2, "aaTerminalBench21": 84.3 }, "coding": { "terminalBench21": 84.3, "deepSwe": 63.4, "nl2Repo": 56.3, "aaSciCode": 46.1 }, "reasoning": { "lcr": 78, "critpt": 15.4 }, "multimodalGrounded": { "officeQaPro": 62.4, "charxiv": 89.4, "chartographyWithTools": 78, "babyVision": 53.4, "mmvu": 80.5 }, "knowledge": { "artificialAnalysis": 57.46, "aaGpqaDiamond": 91.2, "aaHle": 39.9, "aaOmniscienceIndex": 7.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 406, "releaseDate": "2026-08-24", "market": null, "isRegional": false, "family": { "familyKey": "apodex-1-1", "familyName": "Apodex 1.1", "variantType": "full-397b", "snapshotLabel": "397B", "baseFamilyModelKey": "apodex-1-1", "relatedModelKeys": [ "apodex-1-1-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 66, "overallScore": 66, "rawOverallScore": 63, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": null, "coding": 60.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 82, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 60.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 82, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 99, "categoryRanks": { "agentic": 49, "coding": 45 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench21": 70.8, "hleWithTools": 56.1, "apexAgents": 38.5, "deepSearchQa": 92.4, "aaAgenticIndex": 36.64, "apexAgentsAa": 2.9, "gdpvalAaNormalized": 42.3, "gdpvalAa": 1347 }, "coding": { "terminalBench21": 70.8, "sweVerified": 77.7, "aaCodingIndex": 60.76, "aaSciCode": 42.9 }, "reasoning": { "lcr": 74.7, "critpt": 4.6 }, "multimodalGrounded": { "aaMmmuPro": 79.2 }, "knowledge": { "hle": 56.1, "frontierScienceResearch": 63.3, "bioMysteryBenchHumanDifficult": 35.3, "artificialAnalysis": 44, "aaGpqaDiamond": 86.4, "aaHle": 34.1, "aaOmniscienceIndex": -21.9, "omniscienceAccuracy": 31.7, "omniscienceHallucinationRate": 78.4 }, "multilingual": {}, "instructionFollowing": {}, "math": { "imo2026": 30.5 } } }, { "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", "id": 393, "releaseDate": "2026-08-05", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-8-27b", "familyName": "Qwen3.8-27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-8-27b", "relatedModelKeys": [ "qwen3-8-max", "qwen3-6-27b", "qwen3-5-27b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "qwen3-6-27b" }, "scores": { "displayScore": 66, "overallScore": 66, "rawOverallScore": 65, "verifiedDisplayScore": 66, "displayCategoryScores": { "agentic": 84.8, "coding": 50.2, "reasoning": null, "multimodalGrounded": 81.8, "knowledge": 44.8, "multilingual": null, "instructionFollowing": 88.1, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 84.8, "coding": 48.2, "reasoning": null, "multimodalGrounded": 81.8, "knowledge": 42.8, "multilingual": null, "instructionFollowing": 88.1, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 17, "categoryRanks": { "agentic": 9, "coding": 18, "multimodalGrounded": 7, "knowledge": 55, "instructionFollowing": 16 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 21, "verifiedBenchmarkCount": 21, "rankableBenchmarkCount": 21, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench21": 73, "coworkBench": 70.7, "jobBench": 33.4, "agentsLastExam": 42.9, "osWorldVerified": 84.3, "webArenaVerified": 64.8, "androidWorld": 81.9, "aaAgenticIndex": 50.88, "gdpvalAaNormalized": 52.1, "gdpvalAa": 1543, "aaTau3Banking": 48, "aaTerminalBench21": 79.8, "aaEnterpriseOpsGym": 44.2, "aaBriefcaseElo": 1413 }, "coding": { "terminalBench21": 73, "swePro": 61.7, "nl2Repo": 42.3, "deepSwe": 42.2, "liveCodeBenchV6": 90.3, "aaCodingIndex": 68.08, "aaSciCode": 44.7, "vulcanBench": 82.6 }, "reasoning": { "lcr": 77.3, "critpt": 5.4 }, "multimodalGrounded": { "mathVision": 90, "mathVisionPython": 94.6, "babyVision": 65.7, "babyVisionPython": 85.6, "vision2Web": 62.9, "charxivNoTools": 83.7, "charxiv": 90.2, "omniDocBench15": 91.1, "realWorldQa": 85.9, "erqa": 65.5, "aaMmmuPro": 76.3 }, "knowledge": { "gpqa": 89.2, "gpqaDiamond": 89.2, "hle": 30.8, "hleNoTools": 30.8, "artificialAnalysis": 52.02, "aaGpqaDiamond": 90.5, "aaHle": 33.9, "aaOmniscienceIndex": -10, "omniscienceAccuracy": 15.6, "omniscienceHallucinationRate": 30.3, "aaOpennessIndex": 38.9 }, "multilingual": {}, "instructionFollowing": { "ifBench": 79.5 }, "math": {} } }, { "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", "id": 280, "releaseDate": "2026-07-08", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-5", "familyName": "Grok 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-5", "relatedModelKeys": [ "grok-4-3", "grok-4-20-beta", "grok-4-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "grok-4-3" }, "scores": { "displayScore": 66, "overallScore": 64, "rawOverallScore": 64, "verifiedDisplayScore": 64, "displayCategoryScores": { "agentic": 84.2, "coding": 54.9, "reasoning": 52.1, "multimodalGrounded": null, "knowledge": 68.4, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 84.2, "coding": 53.7, "reasoning": 52.1, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 11, "categoryRanks": { "agentic": 16, "coding": 39, "knowledge": 26 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "frontierBench": 15.68, "terminalBench2": 83.3, "deepSwe": 53, "aaAgenticIndex": 48.85, "gdpvalAaNormalized": 50.9, "gdpvalAa": 1518, "aaAutomationBench": 51.4 }, "coding": { "swePro": 64.7, "sweMultilingual": 78, "terminalBench2": 83.3, "cursorBench32": 66.7, "vulcanBench": 89.9, "aaCodingIndex": 72.45, "aaSciCode": 54.1 }, "reasoning": { "arcAgi2": 52.64, "arcAgi3": 0.3, "lcr": 74, "critpt": 15.4 }, "multimodalGrounded": { "aaMmmuPro": 80.4, "designArenaWebsite": 1303 }, "knowledge": { "artificialAnalysis": 55.76, "aaGpqaDiamond": 93.1, "aaHle": 42.7, "aaOmniscienceIndex": 25.3, "omniscienceAccuracy": 51.6, "omniscienceHallucinationRate": 54.1 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 174, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-7", "familyName": "Claude Opus 4.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-opus-4-7", "relatedModelKeys": [ "claude-opus-4-7-max", "claude-opus-4-6", "claude-opus-4-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-opus-4-6" }, "scores": { "displayScore": 65, "overallScore": 61, "rawOverallScore": 61, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 69.2, "coding": 62.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 63.7, "multilingual": null, "instructionFollowing": null, "math": 61.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 61.8 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 15, "categoryRanks": { "agentic": 27, "coding": 12, "knowledge": 35 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 74, "gertLabs": 65.59, "researchClawBench": 20.7, "osWorld2": 13.9 }, "coding": { "vibeCodeBench": 71.003, "reactNativeEvals": 82.8, "aaSciCode": 50.1, "frontierCode": 38.5 }, "reasoning": { "lcr": 72.3, "critpt": 5.1 }, "multimodalGrounded": { "aaMmmuPro": 76.4, "designArenaWebsite": 1313 }, "knowledge": { "artificialAnalysis": 43.86, "aaGpqaDiamond": 88.5, "aaHle": 33.3, "aaOmniscienceIndex": 14.8, "omniscienceAccuracy": 44.7, "omniscienceHallucinationRate": 54.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 43.6 }, "math": { "frontierMathV2Tiers13": 43.793, "frontierMathV2Tier4": 22.917 } } }, { "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", "id": 292, "releaseDate": "2026-07-22", "market": null, "isRegional": false, "family": { "familyKey": "celeris-1", "familyName": "Celeris-1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "celeris-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 63, "rawOverallScore": 63, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 73.3, "multilingual": null, "instructionFollowing": 53, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 73.3, "multilingual": null, "instructionFollowing": 53, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "instructionFollowing": 35 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 2.42, "gdpvalAaNormalized": 1.8, "gdpvalAa": 536 }, "coding": { "aaCodingIndex": 14.4, "aaSciCode": 20.7 }, "reasoning": { "lcr": 37.3, "critpt": 0, "drop": 81.4 }, "multimodalGrounded": {}, "knowledge": { "mmluPro": 75.9, "artificialAnalysis": 12.35, "aaGpqaDiamond": 63.1, "aaHle": 6.8, "aaOmniscienceIndex": -71.6, "omniscienceAccuracy": 11, "omniscienceHallucinationRate": 92.8 }, "multilingual": {}, "instructionFollowing": { "ifeval": 80.8 }, "math": { "gsm8k": 93.7 } } }, { "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", "id": 5, "releaseDate": "2026-02-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3-codex", "familyName": "GPT-5.3 Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-codex", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 63, "rawOverallScore": 62, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": 64, "coding": 61.7, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 64, "coding": 61.7, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 34, "categoryRanks": { "agentic": 21, "coding": 25 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 77.3, "osWorldVerified": 64.7, "tau2Bench": 86, "gertLabs": 57.47, "jobBench": 33.7 }, "coding": { "sweVerified": 85, "swePro": 56.8, "sweRebench": 58.2, "vibeCodeBench": 61.767, "aaSciCode": 53.2 }, "reasoning": { "lcr": 78.3, "critpt": 16.9 }, "multimodalGrounded": { "aaMmmuPro": 78.5, "designArenaWebsite": 1181 }, "knowledge": { "artificialAnalysis": 45.51, "aaGpqaDiamond": 91.5, "aaHle": 42.5, "aaOmniscienceIndex": 10.9, "omniscienceAccuracy": 52.9, "omniscienceHallucinationRate": 89.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.4 }, "math": {} } }, { "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", "id": 84, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-2", "familyName": "DeepSeek V3.2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-2", "relatedModelKeys": [ "deepseek-v3-2-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 63, "overallScore": 63, "rawOverallScore": 62, "verifiedDisplayScore": 63, "displayCategoryScores": { "agentic": null, "coding": 68.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 40.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 68.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 40.3 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 105, "categoryRanks": { "coding": 83 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 40.2, "vitaBench": 18.5, "tau2Bench": 78.9, "gertLabs": 29.57 }, "coding": { "sweRebench": 60.9, "reactNativeEvals": 71.5, "aaSciCode": 38.7 }, "reasoning": { "lcr": 42.7, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1193 }, "knowledge": { "artificialAnalysis": 25.13, "aaGpqaDiamond": 75.1, "aaHle": 11.2, "aaOmniscienceIndex": -46.9, "omniscienceAccuracy": 24, "omniscienceHallucinationRate": 93.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 49 }, "math": { "frontierMathV2Tiers13": 22.1, "frontierMathV2Tier4": 2.1 } } }, { "slug": "composer-2-5", "canonicalModelKey": "composer-2-5", "model": "Composer 2.5", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-5", "markdownUrl": "https://benchlm.ai/md/models/composer-2-5.md", "id": 46, "releaseDate": "2026-05-18", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "composer-2-5", "relatedModelKeys": [ "composer-2", "composer-2-fast" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "composer-2" }, "scores": { "displayScore": 62, "overallScore": 62, "rawOverallScore": 62, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": 63.4, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 63.4, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 48 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 69.3 }, "coding": { "terminalBench2": 69.3, "sweMultilingual": 79.8, "cursorBench31": 63.2, "cursorBench32": 56.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "btl-4", "canonicalModelKey": "btl-4", "model": "BTL-4", "creator": "Bad Theory Labs", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 62, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/btl-4", "markdownUrl": "https://benchlm.ai/md/models/btl-4.md", "id": 388, "releaseDate": "2026-08-05", "market": null, "isRegional": false, "family": { "familyKey": "btl", "familyName": "BTL", "variantType": "4", "snapshotLabel": "v4", "baseFamilyModelKey": "btl-4", "relatedModelKeys": [ "ornith-1-0-35b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 62, "overallScore": 62, "rawOverallScore": 58, "verifiedDisplayScore": 62, "displayCategoryScores": { "agentic": null, "coding": 61.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 61.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 51, "coding": 58 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 73.5 }, "coding": { "sweVerified": 78.4, "liveCodeBenchV6": 66.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 409, "releaseDate": "2026-08-26", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-8-flash-next", "familyName": "Qwen3.8-Flash-Next", "variantType": "experimental-preview", "snapshotLabel": "Next", "baseFamilyModelKey": "qwen3-8-flash-next", "relatedModelKeys": [ "qwen3-8-27b", "qwen3-8-max", "qwen3-7-flash", "qwen3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 61, "overallScore": 61, "rawOverallScore": 60, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": null, "coding": 49.7, "reasoning": null, "multimodalGrounded": 82.9, "knowledge": 51.3, "multilingual": null, "instructionFollowing": 91.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 49.7, "reasoning": null, "multimodalGrounded": 82.9, "knowledge": 51.3, "multilingual": null, "instructionFollowing": 91.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 64, "categoryRanks": { "agentic": 8, "coding": 26, "instructionFollowing": 10 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "coworkBench": 73.9, "jobBench": 55.7, "agentsLastExam": 51.2, "toolathlonVerified": 73.5, "androidWorld": 84.5, "osWorld2": 19.4, "aaAgenticIndex": 56.42, "gdpvalAaNormalized": 62.1, "gdpvalAa": 1743 }, "coding": { "swePro": 62.5, "sweMultilingual": 81, "nl2Repo": 48.1, "deepSwe": 58.7, "liveCodeBenchV6": 91.9, "aaCodingIndex": 73.05, "aaSciCode": 46.9 }, "reasoning": { "lcr": 77, "critpt": 11.1 }, "multimodalGrounded": { "vision2Web": 64, "erqa": 72.3, "lvBench": 76.6, "realWorldQa": 88.5, "mathVision": 90.6, "mathVisionPython": 95.7, "charxivNoTools": 84.6, "charxiv": 90.6, "aaMmmuPro": 79.8 }, "knowledge": { "gpqa": 91.7, "gpqaDiamond": 91.7, "hle": 35.9, "hleNoTools": 35.9, "artificialAnalysis": 55.81, "aaGpqaDiamond": 92.3, "aaHle": 38, "aaOmniscienceIndex": -9.7, "omniscienceAccuracy": 24.5, "omniscienceHallucinationRate": 45.3 }, "multilingual": {}, "instructionFollowing": { "ifBench": 81.3 }, "math": {} } }, { "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", "id": 58, "releaseDate": "2024-12-01", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1-pro", "o1-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "o1-preview" }, "scores": { "displayScore": 61, "overallScore": 61, "rawOverallScore": 61, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.9, "multilingual": null, "instructionFollowing": 86.3, "math": 32.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.9, "multilingual": null, "instructionFollowing": 86.3, "math": 32.7 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 146, "categoryRanks": { "coding": 81, "instructionFollowing": 21 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 62.6 }, "coding": { "aaCodingIndex": 39.72, "aaSciCode": 35.8 }, "reasoning": { "lcr": 63.3, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "mmlu": 91.8, "gpqa": 75.7, "artificialAnalysis": 23.86, "aaGpqaDiamond": 74.7, "aaHle": 7, "aaOmniscienceIndex": -11, "omniscienceAccuracy": 34.5, "omniscienceHallucinationRate": 69.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 92.2, "aaIfBench": 70.3 }, "math": { "frontierMathV2Tiers13": 9.31 }, "korean": {} } }, { "slug": "mistral-medium-3-5-128b", "canonicalModelKey": "mistral-medium-3-5-128b", "model": "Mistral Medium 3.5 128B", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 61, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-medium-3-5-128b", "markdownUrl": "https://benchlm.ai/md/models/mistral-medium-3-5-128b.md", "id": 17, "releaseDate": "2026-04-29", "market": null, "isRegional": false, "family": { "familyKey": "mistral-medium-3-5", "familyName": "Mistral Medium 3.5", "variantType": "128b", "snapshotLabel": null, "baseFamilyModelKey": "mistral-medium-3-5-128b", "relatedModelKeys": [ "mistral-medium-3" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 61, "overallScore": 61, "rawOverallScore": 57, "verifiedDisplayScore": 61, "displayCategoryScores": { "agentic": 55.6, "coding": 60.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 60.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 83, "coding": 113 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau3Bench": 91.4, "aaAgenticIndex": 19.21, "tau2Bench": 94.2, "gdpvalAaNormalized": 21.8, "gdpvalAa": 936, "gertLabs": 39.1, "aaEnterpriseOpsGym": 33.7, "aaHarveyLab": 69.1, "terminalBenchHard": 33.3, "aaAutomationBench": 13.7 }, "coding": { "sweVerified": 77.6, "aaCodingIndex": 46.9, "aaSciCode": 39.6 }, "reasoning": { "lcr": 65.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 64.9 }, "knowledge": { "artificialAnalysis": 30.39, "aaGpqaDiamond": 74.8, "aaHle": 13.8, "aaOmniscienceIndex": -36.8, "omniscienceAccuracy": 24.7, "omniscienceHallucinationRate": 81.6, "aaOpennessIndex": 33.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 68.8 }, "math": {} } }, { "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", "id": 30, "releaseDate": "2026-05-05", "market": null, "isRegional": false, "family": { "familyKey": "zaya1", "familyName": "ZAYA1", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "zaya1-8b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 60, "overallScore": 60, "rawOverallScore": 59, "verifiedDisplayScore": 60, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.3, "multilingual": null, "instructionFollowing": 40.8, "math": 62.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.3, "multilingual": null, "instructionFollowing": 40.8, "math": 62.7 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 210, "categoryRanks": { "agentic": 113, "instructionFollowing": 38 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "bfclV4": 39.22 }, "coding": { "liveCodeBenchV6": 65.8 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 71, "gpqaDiamond": 71, "mmluPro": 74.2 }, "multilingual": {}, "instructionFollowing": { "ifeval": 85.58, "ifBench": 52.56 }, "math": { "aime2026": 89.1, "hmmtFeb2026": 71.6, "imoAnswerBench": 59.3, "apex": 32.2 } } }, { "slug": "composer-2", "canonicalModelKey": "composer-2", "model": "Composer 2", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 58, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2", "markdownUrl": "https://benchlm.ai/md/models/composer-2.md", "id": 89, "releaseDate": "2026-03-19", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "composer-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 58, "overallScore": 58, "rawOverallScore": 58, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 52.1, "coding": 60.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 52.1, "coding": 60.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 54, "coding": 64 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 61.7 }, "coding": { "sweMultilingual": 73.7, "sweRebench": 58, "reactNativeEvals": 96.1, "terminalBench2": 61.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 69, "releaseDate": "2025-08-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-1-opus", "familyName": "Claude 4.1 Opus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-1-opus", "relatedModelKeys": [ "claude-4-1-opus-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 58, "overallScore": 58, "rawOverallScore": 55, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": null, "coding": 55.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 55.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 170, "categoryRanks": { "agentic": 87, "coding": 107 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "jobBench": 21.9 }, "coding": { "sweVerified": 74.5 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1195 }, "knowledge": { "artificialAnalysis": 28.84 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "laguna-s-2-1", "canonicalModelKey": "laguna-s-2-1", "model": "Laguna S 2.1", "creator": "Poolside", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 57, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-s-2-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-s-2-1.md", "id": 288, "releaseDate": "2026-07-21", "market": null, "isRegional": false, "family": { "familyKey": "laguna", "familyName": "Laguna", "variantType": "s-2-1", "snapshotLabel": "118B-A8B", "baseFamilyModelKey": "laguna-s-2-1", "relatedModelKeys": [ "laguna-m-1", "laguna-xs-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "laguna-m-1" }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 64.7, "coding": 44, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 64.7, "coding": 44, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 47, "coding": 54 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 70.2, "toolathlonVerified": 49.7 }, "coding": { "terminalBench2": 70.2, "sweMultilingual": 78.5, "swePro": 59.4, "deepSwe": 40.4 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 75, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-6-max", "familyName": "Qwen 3.6 Max", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "qwen3-6-max-preview", "relatedModelKeys": [ "qwen3-6-plus", "qwen3-5-plus" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 57.6, "coding": 47.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 71, "multilingual": null, "instructionFollowing": null, "math": 41.6 }, "verifiedDisplayCategoryScores": { "agentic": 57.6, "coding": 47.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 71, "multilingual": null, "instructionFollowing": null, "math": 41.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 69, "categoryRanks": { "agentic": 28, "coding": 41 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 9, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 65.4, "qwenClawBench": 59, "qwenWebBench": 1532, "tau2Bench": 95.9 }, "coding": { "swePro": 57.3, "sciCode": 47, "nl2Repo": 42.9, "terminalBench2": 65.4, "aaSciCode": 46.9 }, "reasoning": { "lcr": 72, "critpt": 3.7 }, "multimodalGrounded": {}, "knowledge": { "superGpqa": 73.9, "artificialAnalysis": 41.07, "aaGpqaDiamond": 88.8, "aaHle": 30.8, "aaOmniscienceIndex": 9.2, "omniscienceAccuracy": 37.9, "omniscienceHallucinationRate": 46.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 76.6 }, "math": { "frontierMathV2Tiers13": 23.103, "frontierMathV2Tier4": 4.167 } } }, { "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", "id": 42, "releaseDate": "2026-03-15", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-flash", "familyName": "MiMo-V2-Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-flash", "relatedModelKeys": [ "mimo-v2-pro", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 54, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": null, "coding": 53.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 53.4, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 115, "categoryRanks": { "coding": 59 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 83.9, "gdpvalAaNormalized": 17.3, "gdpvalAa": 847 }, "coding": { "sweVerified": 73.4, "aaCodingIndex": 49.84, "aaSciCode": 25.9 }, "reasoning": { "lcr": 35, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 83.7, "mmluPro": 84.9, "artificialAnalysis": 25.14, "aaGpqaDiamond": 65.6, "aaHle": 8.6, "aaOmniscienceIndex": -48.4, "omniscienceAccuracy": 15.6, "omniscienceHallucinationRate": 76 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.9 }, "math": { "aime2025": 94.1 } } }, { "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", "id": 274, "releaseDate": "2026-06-26", "market": null, "isRegional": false, "family": { "familyKey": "agents-a1", "familyName": "Agents-A1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "agents-a1", "relatedModelKeys": [ "agents-a1-fp8", "agents-a1-q4-k-m-gguf", "agents-a1-q8-0-gguf", "agents-a1-f16-gguf" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 59.3, "coding": null, "reasoning": 37.3, "multimodalGrounded": null, "knowledge": 67.3, "multilingual": null, "instructionFollowing": 93.9, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 59.3, "coding": null, "reasoning": 37.3, "multimodalGrounded": null, "knowledge": 67.3, "multilingual": null, "instructionFollowing": 93.9, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 58, "categoryRanks": { "agentic": 32, "instructionFollowing": 4 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "browseComp": 75.51, "hleWithTools": 47.6, "vitaBench": 38.75 }, "coding": {}, "reasoning": { "longBenchV2": 60.2 }, "multimodalGrounded": {}, "knowledge": { "hle": 47.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 94.82 }, "math": {} } }, { "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", "id": 64, "releaseDate": "2026-07-31", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v4-flash", "familyName": "DeepSeek V4 Flash", "variantType": "flash-reasoning", "snapshotLabel": "0731", "baseFamilyModelKey": "deepseek-v4-flash-max", "relatedModelKeys": [ "deepseek-v4-flash-base", "deepseek-v4-flash", "deepseek-v4-flash-high" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "deepseek-v4-flash" }, "scores": { "displayScore": 57, "overallScore": 55, "rawOverallScore": 54, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 49, "coding": 52.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 60.2, "multilingual": null, "instructionFollowing": null, "math": 80.1 }, "verifiedDisplayCategoryScores": { "agentic": 47, "coding": 50.6, "reasoning": null, "multimodalGrounded": null, "knowledge": 59.5, "multilingual": null, "instructionFollowing": null, "math": 80.1 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "knowledge": 43 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 24, "verifiedBenchmarkCount": 24, "rankableBenchmarkCount": 24, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 56.9, "browseComp": 73.2, "hleWithTools": 45.1, "mcpAtlas": 69, "gdpvalAa": 1189, "toolathlon": 47.8, "terminalBench21": 82.7, "cyberGym": 76.7, "toolathlonVerified": 70.3, "agentsLastExam": 25.2, "automationBench": 25.1, "aaAgenticIndex": 48.41, "gdpvalAaNormalized": 52.4 }, "coding": { "liveCodeBenchPass1Cot": 91.6, "codeforces": 3052, "sweVerified": 79, "swePro": 52.6, "sweMultilingual": 73.3, "terminalBench2": 56.9, "terminalBench21": 82.7, "nl2Repo": 54.2, "deepSwe": 54.4, "dsBenchFullStack": 68.7, "dsBenchHard": 59.6, "aaCodingIndex": 69.06, "aaSciCode": 49.9, "vulcanBench": 88.4, "openHarmonyBench": 53.8 }, "reasoning": { "mrcr1m": 78.7, "corpusQa1m": 60.5, "lcr": 74.3, "critpt": 16.6 }, "multimodalGrounded": { "designArenaWebsite": 1226 }, "knowledge": { "mmluPro": 86.2, "simpleQa": 34.1, "chineseSimpleQa": 78.9, "gpqa": 88.1, "gpqaDiamond": 88.1, "hle": 34.8, "artificialAnalysis": 51.77, "aaGpqaDiamond": 90.8, "aaHle": 38.6, "aaOmniscienceIndex": -14.3, "omniscienceAccuracy": 40.4, "omniscienceHallucinationRate": 91.7 }, "multilingual": {}, "instructionFollowing": {}, "math": { "hmmtFeb2026": 94.8, "imoAnswerBench": 88.4, "apex": 33, "apexShortlist": 85.7 } } }, { "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", "id": 299, "releaseDate": "2026-08-04", "market": null, "isRegional": false, "family": { "familyKey": "ling-3-0", "familyName": "Ling 3.0", "variantType": "flash-fp8", "snapshotLabel": "FP8", "baseFamilyModelKey": "ling-3-0-flash", "relatedModelKeys": [ "ling-3-0-flash", "ling-3-0-flash-fin" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 57, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": null, "coding": 38.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.2, "multilingual": null, "instructionFollowing": 77.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 38.7, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.2, "multilingual": null, "instructionFollowing": 77.3, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "coding": 69, "instructionFollowing": 27 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 29.31, "gdpvalAaNormalized": 30.3, "gdpvalAa": 1106 }, "coding": { "sciCode": 40.37, "aaCodingIndex": 50.65, "aaSciCode": 41.1 }, "reasoning": { "lcr": 67, "critpt": 1.7 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 84, "gpqaDiamond": 84, "artificialAnalysis": 37.82, "aaGpqaDiamond": 85.5, "aaHle": 23.7, "aaOmniscienceIndex": -17.9, "omniscienceAccuracy": 18.2, "omniscienceHallucinationRate": 44.1 }, "multilingual": {}, "instructionFollowing": { "ifBench": 73.4 }, "math": {} } }, { "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", "id": 88, "releaseDate": "2026-04-22", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-5", "familyName": "MiMo-V2.5", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-5", "relatedModelKeys": [ "mimo-v2-5", "mimo-v2-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "mimo-v2-pro" }, "scores": { "displayScore": 57, "overallScore": 57, "rawOverallScore": 56, "verifiedDisplayScore": 57, "displayCategoryScores": { "agentic": 62, "coding": 40, "reasoning": null, "multimodalGrounded": null, "knowledge": 68, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 62, "coding": 40, "reasoning": null, "multimodalGrounded": null, "knowledge": 68, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 20, "categoryRanks": { "agentic": 108, "coding": 46 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 63.8, "gdpvalAa": 1265, "tau3Bench": 72.9, "terminalBench2": 68.4, "aaAgenticIndex": 29.52, "tau2Bench": 94.2, "gdpvalAaNormalized": 38, "apexAgentsAa": 2.4, "gertLabs": 62.7 }, "coding": { "swePro": 57.2, "terminalBench2": 68.4, "aaCodingIndex": 60.19, "aaSciCode": 50.2 }, "reasoning": { "lcr": 77.7, "critpt": 4 }, "multimodalGrounded": { "designArenaWebsite": 1293 }, "knowledge": { "hle": 48, "hleNoTools": 34, "artificialAnalysis": 42.88, "aaGpqaDiamond": 86.6, "aaHle": 35.7, "aaOmniscienceIndex": 3.3, "omniscienceAccuracy": 22.4, "omniscienceHallucinationRate": 24.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 79.9 }, "math": {} } }, { "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", "id": 286, "releaseDate": "2026-07-21", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-5-flash-lite", "familyName": "Gemini 3.5 Flash-Lite", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-5-flash-lite", "relatedModelKeys": [ "gemini-3-1-flash-lite" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gemini-3-1-flash-lite" }, "scores": { "displayScore": 57, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": 52.3, "coding": 36.5, "reasoning": 54.3, "multimodalGrounded": 53.8, "knowledge": 57.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 51.2, "coding": 34.5, "reasoning": 54.3, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 37, "categoryRanks": { "agentic": 132, "coding": 62, "multimodalGrounded": 23, "knowledge": 45 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": true, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 54, "osWorldVerified": 74, "gdpvalAa": 1139, "aaAgenticIndex": 27.16, "gdpvalAaNormalized": 31.8, "aaTau3Banking": 17.5, "aaAutomationBench": 32.7, "aaEnterpriseOpsGym": 42.3 }, "coding": { "terminalBench2": 54, "swePro": 54.2, "aaCodingIndex": 49.32, "aaSciCode": 40.9 }, "reasoning": { "mrcrv2": 72.2, "lcr": 74.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 79 }, "knowledge": { "artificialAnalysis": 37.44, "aaGpqaDiamond": 83.8, "aaHle": 18.8, "aaOmniscienceIndex": 5.2, "omniscienceAccuracy": 29.5, "omniscienceHallucinationRate": 34.4 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 67, "releaseDate": "2025-05-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-sonnet", "familyName": "Claude 4 Sonnet", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-sonnet", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 56, "overallScore": 56, "rawOverallScore": 53, "verifiedDisplayScore": 56, "displayCategoryScores": { "agentic": null, "coding": 52.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 52.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 187, "categoryRanks": { "agentic": 102, "coding": 116 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 52.3, "gertLabs": 39.66, "jobBench": 18.4 }, "coding": { "sweVerified": 72.7, "aaSciCode": 37.3 }, "reasoning": { "lcr": 45.7, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 62.4, "designArenaWebsite": 1164 }, "knowledge": { "artificialAnalysis": 25.99, "aaGpqaDiamond": 68.3, "aaHle": 4.3, "aaOmniscienceIndex": -9, "omniscienceAccuracy": 22.7, "omniscienceHallucinationRate": 41 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 45.4 }, "math": {} } }, { "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", "id": 300, "releaseDate": "2026-08-04", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-2-6b", "familyName": "LFM2.5-2.6B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-2-6b", "relatedModelKeys": [ "lfm2-5-8b-a1b", "lfm2-5-1-2b-thinking", "lfm2-5-230m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 52.1, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 52.1, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 181, "categoryRanks": { "agentic": 106, "coding": 123, "instructionFollowing": 36 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 56.88, "tau3Bench": 5.67, "clawEval": 62.85, "pinchBench": 68.22, "aaAgenticIndex": 2.41, "gdpvalAaNormalized": 0, "gdpvalAa": 254 }, "coding": { "liveCodeBenchV6": 59.41, "aaCodingIndex": 7.74, "aaSciCode": 14.2 }, "reasoning": { "lcr": 5.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "aaOmniscienceIndex": -29.5, "artificialAnalysis": 10.99, "aaGpqaDiamond": 55.8, "aaHle": 6.2, "omniscienceAccuracy": 4.4, "omniscienceHallucinationRate": 16 }, "multilingual": {}, "instructionFollowing": { "ifBench": 59.17 }, "math": { "aime2025": 51.87 } } }, { "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", "id": 35, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-5", "familyName": "Kimi K2.5", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-5", "relatedModelKeys": [ "kimi-k2-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 54, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 29.4, "coding": 59.2, "reasoning": null, "multimodalGrounded": 61.2, "knowledge": 83.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 29.4, "coding": 59.2, "reasoning": null, "multimodalGrounded": 61.2, "knowledge": 83.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 70, "categoryRanks": { "agentic": 63, "coding": 51 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 50.8, "browseComp": 60.6, "apexAgentsAa": 11.5, "tau2Bench": 95.9, "gertLabs": 32.58, "aaAgenticIndex": 21.69, "gdpvalAaNormalized": 25.3, "gdpvalAa": 1006 }, "coding": { "sweVerified": 76.8, "vibeCodeBench": 17.536, "aaSciCode": 49, "aaCodingIndex": 46.78 }, "reasoning": { "lcr": 73, "critpt": 3.1 }, "multimodalGrounded": { "mmmuPro": 78.5, "aaMmmuPro": 75.4, "designArenaWebsite": 1267 }, "knowledge": { "gpqa": 87.6, "mmluPro": 87.1, "artificialAnalysis": 36.02, "aaGpqaDiamond": 87.9, "aaHle": 30.7, "aaOmniscienceIndex": -7.3, "omniscienceAccuracy": 35.2, "omniscienceHallucinationRate": 65.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70.2 }, "math": { "aime2025": 96.1 } } }, { "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", "id": 77, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-flash", "familyName": "Gemini 3 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 50.3 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 50.3 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 73, "categoryRanks": { "agentic": 138, "coding": 109 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 49.2, "tau2Bench": 43.3, "gertLabs": 56.63, "jobBench": 11.4 }, "coding": { "vibeCodeBench": 20.204, "aaSciCode": 49.9 }, "reasoning": { "lcr": 53, "critpt": 1.4 }, "multimodalGrounded": { "aaMmmuPro": 78.6, "designArenaWebsite": 1214 }, "knowledge": { "artificialAnalysis": 27.94, "aaGpqaDiamond": 81.2, "aaHle": 15, "aaOmniscienceIndex": -4.3, "omniscienceAccuracy": 45.8, "omniscienceHallucinationRate": 92.4 }, "multilingual": { "aaGlobalMmluLite": 92.7 }, "instructionFollowing": { "aaIfBench": 55.1 }, "math": { "frontierMathV2Tiers13": 35.64, "frontierMathV2Tier4": 4.167 } } }, { "slug": "interfaze-beta", "canonicalModelKey": "interfaze-beta", "model": "Interfaze Beta", "creator": "Interfaze", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 55, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/interfaze-beta", "markdownUrl": "https://benchlm.ai/md/models/interfaze-beta.md", "id": 10, "releaseDate": "2026-05-11", "market": null, "isRegional": false, "family": { "familyKey": "interfaze", "familyName": "Interfaze", "variantType": "beta", "snapshotLabel": "beta", "baseFamilyModelKey": "interfaze-beta", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 24.9, "knowledge": 81.2, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 24.9, "knowledge": 81.2, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "spider2Lite": 52.9 }, "reasoning": {}, "multimodalGrounded": { "ocrBenchV2": 70.7, "olmOcr": 85.7, "refcocoAvg": 82.1, "voxPopuliWer": 2.4, "mmmuPro": 71.1 }, "knowledge": { "gpqa": 89.9, "gpqaDiamond": 89.9, "mmmlu": 90.9 }, "multilingual": {}, "instructionFollowing": { "sobValueAcc": 79.5 }, "math": {} } }, { "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", "id": 103, "releaseDate": "2026-04-08", "market": null, "isRegional": false, "family": { "familyKey": "muse-spark", "familyName": "Muse Spark", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "muse-spark-1-2", "relatedModelKeys": [ "muse-spark-1-2", "muse-spark-1-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 54, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": 48.1, "coding": 48.6, "reasoning": 43.7, "multimodalGrounded": 73.5, "knowledge": 72.1, "multilingual": null, "instructionFollowing": null, "math": 55.9 }, "verifiedDisplayCategoryScores": { "agentic": 48.1, "coding": 48.6, "reasoning": 43.7, "multimodalGrounded": 73.5, "knowledge": 72.1, "multilingual": null, "instructionFollowing": null, "math": 55.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 19, "categoryRanks": { "agentic": 13, "coding": 22, "multimodalGrounded": 10 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 22, "verifiedBenchmarkCount": 22, "rankableBenchmarkCount": 22, "generatedBenchmarkCount": 0, "scoreConfidence": 3 }, "benchmarks": { "agentic": { "terminalBench2": 59, "tau2Bench": 91.5, "deepSearchQa": 74.8, "cyberGym": 43.5, "clawEval": 63.8, "gdpvalAaNormalized": 32.2, "gdpvalAa": 1145 }, "coding": { "sweVerified": 77.4, "swePro": 52.4, "liveCodeBenchPro": 80, "vibeCodeBench": 19.674, "aaCodingIndex": 58.62, "aaSciCode": 51.5 }, "reasoning": { "arcAgi2": 42.5, "lcr": 77, "critpt": 11.3 }, "multimodalGrounded": { "charxiv": 86.4, "mmmuPro": 80.4, "erqa": 64.7, "simpleVqa": 71.3, "screenSpotPro": 84.1, "zeroBench": 33, "medXpertQaMm": 78.4, "aaMmmuPro": 80.5 }, "knowledge": { "gpqaDiamond": 89.5, "hle": 50.4, "hleNoTools": 42.8, "healthBenchHard": 42.8, "medXpertQaText": 52.6, "artificialAnalysis": 44.25, "aaGpqaDiamond": 88.4, "aaHle": 40.7, "aaOmniscienceIndex": 7.2, "omniscienceAccuracy": 49.6, "omniscienceHallucinationRate": 84.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.9 }, "math": { "frontierMathV2Tiers13": 39, "frontierMathV2Tier4": 14.6 } } }, { "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", "id": 23, "releaseDate": "2025-11-13", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1", "familyName": "GPT-5.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 55, "overallScore": 55, "rawOverallScore": 55, "verifiedDisplayScore": 55, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 49.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 49.7 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 114, "categoryRanks": { "agentic": 69, "coding": 60 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 21.63, "tau2Bench": 81.9, "gertLabs": 41.24, "gdpvalAaNormalized": 24.7, "gdpvalAa": 994 }, "coding": { "vibeCodeBench": 24.606, "aaCodingIndex": 49.39, "aaSciCode": 43.3 }, "reasoning": { "lcr": 76.7, "critpt": 4.9 }, "multimodalGrounded": { "aaMmmuPro": 75.5, "designArenaWebsite": 1205 }, "knowledge": { "artificialAnalysis": 37.47, "aaGpqaDiamond": 87.3, "aaHle": 28.5, "aaOmniscienceIndex": 5.4, "omniscienceAccuracy": 37.7, "omniscienceHallucinationRate": 51.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 72.9 }, "math": { "frontierMathV2Tiers13": 31.034, "frontierMathV2Tier4": 12.5 }, "korean": {} } }, { "slug": "ornith-1-0-35b", "canonicalModelKey": "ornith-1-0-35b", "model": "Ornith-1.0-35B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 54, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-35b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-35b.md", "id": 269, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-0", "familyName": "Ornith 1.0", "variantType": "35b", "snapshotLabel": "35B", "baseFamilyModelKey": "ornith-1-0-397b", "relatedModelKeys": [ "ornith-1-0-397b", "ornith-1-0-9b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 53, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": 55.8, "coding": 44.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 55.8, "coding": 44.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 52, "coding": 61 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 64.2, "clawEval": 69.8 }, "coding": { "sweVerified": 75.6, "swePro": 50.4, "sweMultilingual": 69.3, "nl2Repo": 34.6, "terminalBench2": 64.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 87, "releaseDate": "2026-04-30", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-3", "familyName": "Grok 4.3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 58, "rawOverallScore": 57, "verifiedDisplayScore": 58, "displayCategoryScores": { "agentic": 43.7, "coding": 53.3, "reasoning": null, "multimodalGrounded": 59.2, "knowledge": 51.6, "multilingual": null, "instructionFollowing": 91.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 53, "reasoning": null, "multimodalGrounded": 59.2, "knowledge": 49.6, "multilingual": null, "instructionFollowing": 91.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 44, "categoryRanks": { "agentic": 142, "coding": 131, "knowledge": 51, "instructionFollowing": 11 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 97.7, "gdpvalAaNormalized": 29.2, "aaAgenticIndex": 24.16, "apexAgentsAa": 17, "gdpvalAa": 1087, "gertLabs": 43.86, "researchClawBench": 12.4 }, "coding": { "sciCode": 47.3, "aaCodingIndex": 42.25, "aaSciCode": 47.3 }, "reasoning": { "lcr": 64.3, "critpt": 8 }, "multimodalGrounded": { "mmmuPro": 78.1, "designArenaWebsite": 1211, "aaMmmuPro": 78.1 }, "knowledge": { "artificialAnalysis": 37.58, "gpqa": 90.1, "hle": 35, "omniscienceAccuracy": 34.6, "omniscienceHallucinationRate": 25, "aaGpqaDiamond": 90.1, "aaHle": 37.2, "aaOmniscienceIndex": 18 }, "multilingual": {}, "instructionFollowing": { "ifBench": 81.3, "aaIfBench": 81.3 }, "math": {} } }, { "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", "id": 78, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "claude-haiku-4-5", "familyName": "Claude Haiku 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-haiku-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 51, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": null, "coding": 53.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 29 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 53.2, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 29 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 91, "categoryRanks": { "agentic": 57, "coding": 95 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "jobBench": 16 }, "coding": { "sweVerified": 73.3, "vulcanBench": 76.2 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1140 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 5.903, "frontierMathV2Tier4": 2.083 } } }, { "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", "id": 70, "releaseDate": "2026-04-22", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-5", "familyName": "MiMo-V2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-5", "relatedModelKeys": [ "mimo-v2-5-pro", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "mimo-v2-omni" }, "scores": { "displayScore": 54, "overallScore": 54, "rawOverallScore": 53, "verifiedDisplayScore": 54, "displayCategoryScores": { "agentic": 58.2, "coding": 37.9, "reasoning": null, "multimodalGrounded": 57.1, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 58.2, "coding": 37.9, "reasoning": null, "multimodalGrounded": 57.1, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 78, "categoryRanks": { "agentic": 44, "coding": 75, "multimodalGrounded": 22 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "clawEval": 62.3, "mmClawBench": 23.8, "terminalBench2": 65.8, "gertLabs": 46.89, "researchClawBench": 16.9 }, "coding": { "swePro": 56.1, "terminalBench2": 65.8 }, "reasoning": {}, "multimodalGrounded": { "videoMmeWithSub": 87.7, "charxiv": 81, "mmmuPro": 77.9, "designArenaWebsite": 1285 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 144, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-235b-2507", "familyName": "Qwen3 235B 2507", "variantType": "base", "snapshotLabel": "2507", "baseFamilyModelKey": "qwen3-235b-2507", "relatedModelKeys": [ "qwen3-235b-2507-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 53, "overallScore": 53, "rawOverallScore": 52, "verifiedDisplayScore": 53, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 74.5, "multilingual": 1, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 74.5, "multilingual": 1, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 95, "categoryRanks": { "knowledge": 22, "multilingual": 12 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": true, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 77.5, "superGpqa": 62.6, "mmluPro": 83 }, "multilingual": { "mmluProX": 79.4 }, "instructionFollowing": {}, "math": {} } }, { "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", "id": 12, "releaseDate": "2026-02-12", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-pro", "familyName": "Gemini 3 Pro", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-pro", "relatedModelKeys": [ "gemini-3-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 52, "overallScore": 52, "rawOverallScore": 51, "verifiedDisplayScore": 52, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 45.9, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 45.9, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 52, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": { "arcAgi2": 45.1, "critpt": 25.7 }, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 90, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o4-mini", "familyName": "o4-mini", "variantType": "reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "o4-mini-high", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 52, "overallScore": 52, "rawOverallScore": 51, "verifiedDisplayScore": 52, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 43.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 43.5 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 132, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 24.828, "frontierMathV2Tier4": 6.25 } } }, { "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", "id": 252, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "mellum2-12b-a2-5b", "familyName": "Mellum2 12B-A2.5B", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "mellum2-12b-a2-5b-instruct", "relatedModelKeys": [ "mellum2-12b-a2-5b-instruct" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 51, "overallScore": 51, "rawOverallScore": 51, "verifiedDisplayScore": 51, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 48.7, "multilingual": null, "instructionFollowing": 40.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 48.7, "multilingual": null, "instructionFollowing": 40.4, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 75, "instructionFollowing": 39 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 45.6 }, "coding": { "liveCodeBenchV6": 69.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluRedux": 86.2, "gpqa": 57.6, "gpqaDiamond": 57.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 76.5 }, "math": {} } }, { "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", "id": 239, "releaseDate": "2026-05-29", "market": null, "isRegional": false, "family": { "familyKey": "step-3-7-flash", "familyName": "Step 3.7 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-3-7-flash", "relatedModelKeys": [ "step-3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "step-3-5-flash" }, "scores": { "displayScore": 51, "overallScore": 51, "rawOverallScore": 50, "verifiedDisplayScore": 51, "displayCategoryScores": { "agentic": 52, "coding": 38.3, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 52, "coding": 38.3, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 127, "categoryRanks": { "agentic": 84, "coding": 74 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 10, "verifiedBenchmarkCount": 10, "rankableBenchmarkCount": 10, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 59.5, "browseComp": 75.82, "deepSearchQa": 92.82, "gdpvalAaNormalized": 25.8, "toolathlon": 49.5, "clawEval": 67.1, "hleWithTools": 47.2, "gertLabs": 51.57, "aaAgenticIndex": 21.74, "tau2Bench": 98.5, "gdpvalAa": 1018, "apexAgentsAa": 14.8 }, "coding": { "swePro": 56.3, "terminalBench2": 59.5, "aaCodingIndex": 39.57, "aaSciCode": 40 }, "reasoning": { "lcr": 69.7, "critpt": 2.3 }, "multimodalGrounded": { "simpleVqa": 79.2, "vStar": 95.3, "aaMmmuPro": 75.3, "designArenaWebsite": 1211 }, "knowledge": { "artificialAnalysis": 30.9, "aaGpqaDiamond": 80.9, "aaHle": 21.4, "aaOmniscienceIndex": -37.3, "omniscienceAccuracy": 25.8, "omniscienceHallucinationRate": 85 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 67.3 }, "math": {} } }, { "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", "id": 397, "releaseDate": "2026-08-18", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-5", "familyName": "Ornith 1.5", "variantType": "35b-a3b", "snapshotLabel": "35B-A3B", "baseFamilyModelKey": "ornith-1-5-397b", "relatedModelKeys": [ "ornith-1-5-397b", "ornith-1-5-9b", "ornith-1-0-35b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "ornith-1-0-35b" }, "scores": { "displayScore": 51, "overallScore": 51, "rawOverallScore": 49, "verifiedDisplayScore": 51, "displayCategoryScores": { "agentic": 46.3, "coding": 56.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 34.5, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 46.3, "coding": 56.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 34.5, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 149, "categoryRanks": { "agentic": 73, "coding": 82 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 12, "verifiedBenchmarkCount": 12, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 67.8, "hleWithTools": 33.4, "mcpAtlas": 70.2, "toolathlonVerified": 48.7, "wideResearch": 67.8, "browseComp": 67.6, "clawEval": 72.5 }, "coding": { "terminalBench21": 67.8, "sweVerified": 79, "swePro": 59.6, "sweMultilingual": 71.4, "deepSwe": 22, "frontierBench": 5.1, "nl2Repo": 46.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 89.2, "gpqaDiamond": 89.2, "hle": 25.6, "hleNoTools": 25.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 41, "releaseDate": "2025-01-31", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3", "o3-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.4, "multilingual": null, "instructionFollowing": 91.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 68.4, "multilingual": null, "instructionFollowing": 91.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 158, "categoryRanks": { "coding": 96, "instructionFollowing": 12 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 28.7 }, "coding": { "sweVerified": 49.3, "aaSciCode": 39.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmlu": 86.9, "gpqa": 77.2, "artificialAnalysis": 19.22, "aaGpqaDiamond": 74.8, "aaHle": 7.9 }, "multilingual": {}, "instructionFollowing": { "ifeval": 93.9 }, "math": { "aime2024": 87.3 } } }, { "slug": "soofi-s-30b-a3b", "canonicalModelKey": "soofi-s-30b-a3b", "model": "Soofi S 30B-A3B", "creator": "Soofi Project", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 50, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/soofi-s-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/soofi-s-30b-a3b.md", "id": 283, "releaseDate": "2026-07-10", "market": null, "isRegional": false, "family": { "familyKey": "soofi-s", "familyName": "Soofi S", "variantType": "base", "snapshotLabel": "30B-A3B", "baseFamilyModelKey": "soofi-s-30b-a3b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 50, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 42.6, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 42.6, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "humaneval": 73.8 }, "reasoning": { "bbh": 78.8, "drop": 66.5 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 43.4, "gpqaDiamond": 43.4, "mmluPro": 51.4, "agieval": 66.9 }, "multilingual": {}, "instructionFollowing": {}, "math": { "gsm8k": 86.1 } } }, { "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", "id": 240, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-8b-a1b", "familyName": "LFM2.5-8B-A1B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-8b-a1b", "relatedModelKeys": [ "lfm2-5-1-2b-thinking", "lfm2-5-350m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 49, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 55.7, "math": 27.8 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": 55.7, "math": 27.8 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 188, "categoryRanks": { "agentic": 81, "instructionFollowing": 34 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 49.73, "tau2Bench": 88.07 }, "coding": { "aaSciCode": 7.8 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "aaGpqaDiamond": 51.3, "aaHle": 6.9, "aaOmniscienceIndex": -33.3, "omniscienceAccuracy": 9.4, "omniscienceHallucinationRate": 46.9, "artificialAnalysis": 8.14 }, "multilingual": {}, "instructionFollowing": { "ifeval": 91.84, "ifBench": 56.47, "aaIfBench": 55.6 }, "math": { "math500": 88.76, "aime2025": 42.53, "aime2026": 50 } } }, { "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", "id": 227, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-plus", "familyName": "Qwen3.5 Plus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-plus", "relatedModelKeys": [ "qwen3-5-397b", "qwen3-5-397b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 50, "overallScore": 50, "rawOverallScore": 49, "verifiedDisplayScore": 50, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 39.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 39.5 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 150, "categoryRanks": { "agentic": 66 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "jobBench": 18.5 }, "coding": { "vibeCodeBench": 15.738 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 21.034, "frontierMathV2Tier4": 2.083 } } }, { "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", "id": 96, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2", "familyName": "Kimi K2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": 49, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 39.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 39.2 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 213, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 61.1 }, "coding": { "aaSciCode": 34.5 }, "reasoning": { "lcr": 53, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1068 }, "knowledge": { "artificialAnalysis": 19.65, "aaGpqaDiamond": 76.6, "aaHle": 7.4, "aaOmniscienceIndex": -28.3, "omniscienceAccuracy": 27.4, "omniscienceHallucinationRate": 76.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.5 }, "math": { "frontierMathV2Tiers13": 21.404, "frontierMathV2Tier4": 0 } } }, { "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", "id": 117, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m2-7", "familyName": "MiniMax M2.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m2-7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": "minimax-m2-5" }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": 49, "displayCategoryScores": { "agentic": 45.1, "coding": 41.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 45.1, "coding": 41.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 49, "categoryRanks": { "agentic": 126, "coding": 110 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 16, "verifiedBenchmarkCount": 16, "rankableBenchmarkCount": 16, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 57, "tau2Bench": 84.8, "toolathlon": 46.3, "mleBenchLite": 66.6, "mmClawBench": 62.7, "clawEval": 48.7, "aaAgenticIndex": 25.92, "apexAgentsAa": 10.6, "gdpvalAaNormalized": 32.9, "gdpvalAa": 1157, "gertLabs": 40.4 }, "coding": { "sweVerifiedArcee": 75.4, "swePro": 56.2, "sweRebench": 51.9, "sweMultilingual": 76.5, "multiSweBench": 52.7, "vibePro": 55.6, "nl2Repo": 39.8, "vibeCodeBench": 27.037, "reactNativeEvals": 71.4, "aaCodingIndex": 52.62, "aaSciCode": 47 }, "reasoning": { "lcr": 75.3, "critpt": 0.6 }, "multimodalGrounded": { "designArenaWebsite": 1263 }, "knowledge": { "gpqaDiamond": 87, "mmluProArcee": 80.8, "artificialAnalysis": 38.87, "aaGpqaDiamond": 87.4, "aaHle": 29.6, "aaOmniscienceIndex": 0.8, "omniscienceAccuracy": 26.8, "omniscienceHallucinationRate": 35.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.7 }, "math": { "aime2025Arcee": 80 } } }, { "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", "id": 56, "releaseDate": "2025-07-09", "market": null, "isRegional": false, "family": { "familyKey": "grok-4", "familyName": "Grok 4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 49, "verifiedDisplayScore": 49, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 38.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 38.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 79, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 74.9, "gertLabs": 42.34 }, "coding": { "reactNativeEvals": 72.6, "aaSciCode": 45.7 }, "reasoning": { "lcr": 67, "critpt": 2 }, "multimodalGrounded": { "aaMmmuPro": 68.8 }, "knowledge": { "artificialAnalysis": 34.08, "aaGpqaDiamond": 87.7, "aaHle": 26.7, "aaOmniscienceIndex": 2.1, "omniscienceAccuracy": 40.5, "omniscienceHallucinationRate": 64.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 53.7 }, "math": { "frontierMathV2Tiers13": 19.655, "frontierMathV2Tier4": 2.083 } } }, { "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", "id": 50, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3-pro", "o3-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 49, "overallScore": 49, "rawOverallScore": 48, "verifiedDisplayScore": 49, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 37.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 37.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 157, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 80.7 }, "coding": { "aaSciCode": 41 }, "reasoning": { "lcr": 73.3, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 70.1, "designArenaWebsite": 1054 }, "knowledge": { "artificialAnalysis": 31.1, "aaGpqaDiamond": 82.7, "aaHle": 20.1, "aaOmniscienceIndex": -15.5, "omniscienceAccuracy": 38.6, "omniscienceHallucinationRate": 88.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.4 }, "math": { "aaMath500": 99.2, "frontierMathV2Tiers13": 18.685, "frontierMathV2Tier4": 2.083 } } }, { "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", "id": 413, "releaseDate": "2026-08-25", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-2", "familyName": "Granite 4.2", "variantType": "8b-dense", "snapshotLabel": "8B", "baseFamilyModelKey": "granite-4-2-8b", "relatedModelKeys": [ "granite-4-0-h-1b", "granite-4-0-1b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 48, "rawOverallScore": 49, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": null, "coding": 18.8, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.5, "multilingual": null, "instructionFollowing": 87.8, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 18.8, "reasoning": null, "multimodalGrounded": null, "knowledge": 66.5, "multilingual": null, "instructionFollowing": 87.8, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 161, "categoryRanks": { "agentic": 93, "coding": 105, "instructionFollowing": 17 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 20.56, "tau3Bench": 58.06, "bfclV4": 52.39, "aaAgenticIndex": 9.17, "gdpvalAaNormalized": 10.1, "gdpvalAa": 702 }, "coding": { "sweVerified": 47.67, "swePro": 19.11, "sweMultilingual": 30.78, "terminalBench21": 20.56, "liveCodeBenchV6": 73.24, "sciCode": 36.09, "aaCodingIndex": 22.38, "aaSciCode": 30.4 }, "reasoning": { "lcr": 43.3, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 64.14, "mmluPro": 74.04, "artificialAnalysis": 19.61, "aaGpqaDiamond": 63.1, "aaHle": 9.7, "aaOmniscienceIndex": -17.2, "omniscienceAccuracy": 11.2, "omniscienceHallucinationRate": 32 }, "multilingual": {}, "instructionFollowing": { "ifBench": 79.33 }, "math": { "aime2025": 86.67, "hmmtFeb2025": 78.33 } } }, { "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", "id": 52, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-nano-omni", "familyName": "Nemotron 3 Nano Omni", "variantType": "30b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-nano-omni-30b-a3b", "relatedModelKeys": [ "nemotron-3-nano-30b", "nemotron-3-super-120b-a12b", "nemotron-3-super-100b", "nemotron-3-ultra-500b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 48, "rawOverallScore": 48, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": null, "coding": 21.4, "reasoning": null, "multimodalGrounded": 43.5, "knowledge": 71.2, "multilingual": null, "instructionFollowing": 78.7, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.4, "reasoning": null, "multimodalGrounded": 43.5, "knowledge": 71.2, "multilingual": null, "instructionFollowing": 78.7, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 172, "categoryRanks": { "coding": 115, "instructionFollowing": 26 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 14, "verifiedBenchmarkCount": 14, "rankableBenchmarkCount": 14, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "osWorld": 47.4, "tau2Bench": 45.3, "gdpvalAaNormalized": 0, "gdpvalAa": 469 }, "coding": { "liveCodeBenchV5": 63.2, "sciCode": 32, "aaSciCode": 27.8, "aaCodingIndex": 13.75 }, "reasoning": { "lcr": 40.7, "critpt": 0 }, "multimodalGrounded": { "mmmu": 70.8, "mmLongBenchDoc": 57.5, "charxiv": 76.25, "screenSpotPro": 57.8, "videoMmeNoSub": 72.2, "ai2dTest": 88.5, "refcocoAvg": 90.5, "aaMmmuPro": 53.2 }, "knowledge": { "mmluPro": 77.3, "gpqa": 72.2, "gpqaDiamond": 72.2, "artificialAnalysis": 15.01, "aaGpqaDiamond": 46.9, "aaHle": 4.8, "aaOmniscienceIndex": -57.4, "omniscienceAccuracy": 15.2, "omniscienceHallucinationRate": 85.7 }, "multilingual": {}, "instructionFollowing": { "ifBench": 74.2, "aaIfBench": 63.2 }, "math": { "aime2025": 82.1 } } }, { "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", "id": 121, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1", "gpt-4-1-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 48, "rawOverallScore": 48, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 41.4, "multilingual": null, "instructionFollowing": 60, "math": 25.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 41.4, "multilingual": null, "instructionFollowing": 60, "math": 25.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 183, "categoryRanks": { "agentic": 109, "coding": 118, "instructionFollowing": 31 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.17, "tau2Bench": 17.3, "gdpvalAaNormalized": 0, "gdpvalAa": 62 }, "coding": { "aaCodingIndex": 11.14, "aaSciCode": 25.9 }, "reasoning": { "lcr": 19.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 40.1, "designArenaWebsite": 991 }, "knowledge": { "mmlu": 80.1, "gpqa": 50.3, "artificialAnalysis": 9.64, "aaGpqaDiamond": 51.2, "aaHle": 3.8, "aaOmniscienceIndex": -57.6, "omniscienceAccuracy": 13.7, "omniscienceHallucinationRate": 82.6 }, "multilingual": {}, "instructionFollowing": { "ifeval": 83.2, "aaIfBench": 32 }, "math": { "frontierMathV2Tiers13": 1.034 }, "korean": {} } }, { "slug": "pokee-isaac-28b", "canonicalModelKey": "pokee-isaac-28b", "model": "Pokee-Isaac 28B", "creator": "Pokee AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "10M", "contextWindowTokens": 10000000, "displayScore": null, "provisionalDisplayScore": 48, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pokee-isaac-28b", "markdownUrl": "https://benchlm.ai/md/models/pokee-isaac-28b.md", "id": 405, "releaseDate": "2026-08-03", "market": null, "isRegional": false, "family": { "familyKey": "pokee-isaac", "familyName": "Pokee-Isaac", "variantType": "base", "snapshotLabel": "v0", "baseFamilyModelKey": "pokee-isaac-28b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 48, "overallScore": 48, "rawOverallScore": 47, "verifiedDisplayScore": 48, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 39.3, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 39.3, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 53 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench21": 65.1, "bfclV4": 70.94, "tau3Bench": 66.2, "mcpAtlasClaimCoverage": 74.59, "pinchBench": 95.67 }, "coding": { "terminalBench21": 65.1 }, "reasoning": { "mrcrv2": 60.7 }, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 74, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "26b-a4b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 46, "overallScore": 46, "rawOverallScore": 46, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 38.1, "knowledge": 39.1, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 38.1, "knowledge": 39.1, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 93, "categoryRanks": { "agentic": 67, "coding": 108 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 11.04, "tau2Bench": 43.6, "gdpvalAaNormalized": 13.5, "gdpvalAa": 770 }, "coding": { "aaCodingIndex": 39.32, "aaSciCode": 40 }, "reasoning": { "lcr": 61.7, "critpt": 0 }, "multimodalGrounded": { "mmmuPro": 73.8, "aaMmmuPro": 69.2 }, "knowledge": { "mmluPro": 82.6, "hle": 17.2, "hleNoTools": 8.7, "artificialAnalysis": 26.07, "aaGpqaDiamond": 79.2, "aaHle": 19.3, "aaOmniscienceIndex": -50.8, "omniscienceAccuracy": 19.1, "omniscienceHallucinationRate": 86.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 72.4 }, "math": {} } }, { "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", "id": 31, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-5", "familyName": "Claude Sonnet 4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-sonnet-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 46, "overallScore": 46, "rawOverallScore": 45, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": 33.7, "coding": 59.8, "reasoning": 19.7, "multimodalGrounded": null, "knowledge": 74.6, "multilingual": null, "instructionFollowing": null, "math": 34.9 }, "verifiedDisplayCategoryScores": { "agentic": 33.7, "coding": 59.8, "reasoning": 19.7, "multimodalGrounded": null, "knowledge": 74.6, "multilingual": null, "instructionFollowing": null, "math": 34.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 106, "categoryRanks": { "agentic": 80, "coding": 70 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 9, "verifiedBenchmarkCount": 9, "rankableBenchmarkCount": 9, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 50, "osWorldVerified": 61.4, "vitaBench": 17, "gertLabs": 48.51, "jobBench": 27.7 }, "coding": { "sweVerified": 77.2 }, "reasoning": { "arcAgi2": 13.6 }, "multimodalGrounded": { "designArenaWebsite": 1208 }, "knowledge": { "gpqa": 83.4 }, "multilingual": {}, "instructionFollowing": {}, "math": { "aime2025": 87, "frontierMathV2Tiers13": 13.495, "frontierMathV2Tier4": 4.167 } } }, { "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", "id": 113, "releaseDate": "2026-03-03", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-1-flash-lite", "familyName": "Gemini 3.1 Flash-Lite", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-1-flash-lite", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 46, "overallScore": 46, "rawOverallScore": 45, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 35.2, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 35.2, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 129, "categoryRanks": { "coding": 120 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "gertLabs": 38.46 }, "coding": { "vibeCodeBench": 0 }, "reasoning": {}, "multimodalGrounded": { "charxiv": 73.2 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 111, "releaseDate": "2026-04-23", "market": null, "isRegional": false, "family": { "familyKey": "hy3", "familyName": "Hy3", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "hy3", "relatedModelKeys": [ "hy3" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 46, "overallScore": 46, "rawOverallScore": 45, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": 41.2, "coding": 46.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 34, "multilingual": null, "instructionFollowing": 59, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 41.2, "coding": 46.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 34, "multilingual": null, "instructionFollowing": 59, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 176, "categoryRanks": { "agentic": 79, "coding": 99, "instructionFollowing": 32 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 8, "verifiedBenchmarkCount": 8, "rankableBenchmarkCount": 8, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 54.4, "gertLabs": 36.91, "aaAgenticIndex": 31.42, "gdpvalAaNormalized": 35.8, "gdpvalAa": 1212 }, "coding": { "sweVerified": 74.4, "terminalBench2": 54.4, "sciCode": 41.2, "aaSciCode": 47.6, "aaCodingIndex": 58.8 }, "reasoning": { "lcr": 66.7, "critpt": 4.9 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 41.23, "gpqa": 87.2, "gpqaDiamond": 87.2, "hle": 25.5, "omniscienceAccuracy": 31.5, "omniscienceHallucinationRate": 73, "aaGpqaDiamond": 89.7, "aaHle": 33.5, "aaOmniscienceIndex": -18.5 }, "multilingual": {}, "instructionFollowing": { "ifBench": 63.1 }, "math": {} } }, { "slug": "zaya1-74b-preview", "canonicalModelKey": "zaya1-74b-preview", "model": "ZAYA1-74B-Preview", "creator": "Zyphra", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 46, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/zaya1-74b-preview", "markdownUrl": "https://benchlm.ai/md/models/zaya1-74b-preview.md", "id": 105, "releaseDate": "2026-05-07", "market": null, "isRegional": false, "family": { "familyKey": "zaya1", "familyName": "ZAYA1", "variantType": "74b-preview", "snapshotLabel": "preview", "baseFamilyModelKey": "zaya1-74b-preview", "relatedModelKeys": [ "zaya1-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 46, "overallScore": 46, "rawOverallScore": 46, "verifiedDisplayScore": 46, "displayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 59.9, "multilingual": null, "instructionFollowing": null, "math": 56.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 59.9, "multilingual": null, "instructionFollowing": null, "math": 56.5 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "coding": 84 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Airline": 56.1 }, "coding": { "liveCodeBenchV6": 65.7, "sweVerified": 53.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluPro": 68.1, "gpqa": 57.3, "gpqaDiamond": 57.3 }, "multilingual": {}, "instructionFollowing": {}, "math": { "aime2026": 76.4 } } }, { "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", "id": 119, "releaseDate": "2025-07-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-235b-2507", "familyName": "Qwen3 235B 2507", "variantType": "reasoning", "snapshotLabel": "2507", "baseFamilyModelKey": "qwen3-235b-2507", "relatedModelKeys": [ "qwen3-235b-2507" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 45, "overallScore": 45, "rawOverallScore": 44, "verifiedDisplayScore": 45, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 30.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 30.2 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 83, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 8.481, "frontierMathV2Tier4": 0 } } }, { "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", "id": 59, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1-mini", "gpt-4-1-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "gpt-4o" }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 45, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 57.5, "multilingual": null, "instructionFollowing": 72.3, "math": 28.1 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 57.5, "multilingual": null, "instructionFollowing": 72.3, "math": 28.1 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 128, "categoryRanks": { "coding": 87, "instructionFollowing": 30 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 47.1, "gertLabs": 25.65 }, "coding": { "sweVerified": 54.6, "aaSciCode": 38.1 }, "reasoning": { "lcr": 64.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 61.2, "designArenaWebsite": 1057 }, "knowledge": { "mmlu": 90.2, "gpqa": 66.3, "artificialAnalysis": 19.61, "aaGpqaDiamond": 66.6, "aaHle": 4.2, "aaOmniscienceIndex": -39.6, "omniscienceAccuracy": 27.8, "omniscienceHallucinationRate": 93.3 }, "multilingual": {}, "instructionFollowing": { "ifeval": 87.4, "aaIfBench": 43 }, "math": { "frontierMathV2Tiers13": 5.517, "frontierMathV2Tier4": 0 }, "korean": {} } }, { "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", "id": 91, "releaseDate": "2025-04-14", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-1", "familyName": "GPT-4.1", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-1", "relatedModelKeys": [ "gpt-4-1", "gpt-4-1-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "gpt-4o-mini" }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 44, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 55.4, "multilingual": null, "instructionFollowing": 75.5, "math": 28.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 55.4, "multilingual": null, "instructionFollowing": 75.5, "math": 28.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 173, "categoryRanks": { "agentic": 104, "coding": 112, "instructionFollowing": 29 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.79, "tau2Bench": 52.9, "gdpvalAaNormalized": 0.4, "gdpvalAa": 508 }, "coding": { "sweVerified": 23.6, "aaCodingIndex": 20.21, "aaSciCode": 40.4 }, "reasoning": { "lcr": 45.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 58.7, "designArenaWebsite": 1015 }, "knowledge": { "mmlu": 87.5, "gpqa": 64.2, "artificialAnalysis": 14.82, "aaGpqaDiamond": 66.4, "aaHle": 5, "aaOmniscienceIndex": -53.6, "omniscienceAccuracy": 20.3, "omniscienceHallucinationRate": 92.7 }, "multilingual": {}, "instructionFollowing": { "ifeval": 88.5, "aaIfBench": 38.3 }, "math": { "frontierMathV2Tiers13": 4.483 }, "korean": {} } }, { "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", "id": 85, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-20", "familyName": "Grok 4.20", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-20-beta", "relatedModelKeys": [ "grok-4-20-multi-agent-beta" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "grok-4-1" }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 43, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": 30.4, "coding": 47.3, "reasoning": 52.7, "multimodalGrounded": 30.5, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 30.4, "coding": 47.3, "reasoning": 52.7, "multimodalGrounded": 30.5, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 102, "categoryRanks": { "agentic": 61, "coding": 104, "multimodalGrounded": 31 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 17, "verifiedBenchmarkCount": 17, "rankableBenchmarkCount": 17, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 47.1, "deepSearchQa": 62.8, "gertLabs": 38.36 }, "coding": { "liveCodeBenchPro": 74.2, "sweVerified": 76.7, "swePro": 51.8, "vibeCodeBench": 4.064 }, "reasoning": { "arcAgi2": 53.3, "arcAgi3": 0.09 }, "multimodalGrounded": { "mmmuPro": 75.2, "charxiv": 60.9, "erqa": 54.1, "simpleVqa": 57.4, "medXpertQaMm": 65.8, "designArenaWebsite": 1247 }, "knowledge": { "gpqaDiamond": 88.5, "hleNoTools": 31.6, "healthBenchHard": 20.3, "medXpertQaText": 50.2 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 125, "releaseDate": "2025-06-17", "market": null, "isRegional": false, "family": { "familyKey": "gemini-2-5-flash", "familyName": "Gemini 2.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-2-5-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 44, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 28.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 28.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 153, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 14.9 }, "coding": { "aaSciCode": 29.1 }, "reasoning": { "lcr": 48, "critpt": 1.4 }, "multimodalGrounded": { "aaMmmuPro": 65.5, "designArenaWebsite": 1133 }, "knowledge": { "artificialAnalysis": 14.19, "aaGpqaDiamond": 68.3, "aaHle": 4.7, "aaOmniscienceIndex": -42.6, "omniscienceAccuracy": 26.1, "omniscienceHallucinationRate": 93 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39 }, "math": { "frontierMathV2Tiers13": 4.844, "frontierMathV2Tier4": 4.167 } } }, { "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", "id": 94, "releaseDate": "2026-03-04", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-flash", "familyName": "Qwen3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-flash", "relatedModelKeys": [ "qwen3-5-35b-a3b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 43, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 28.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 28.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 152, "categoryRanks": { "coding": 124 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 6.207, "frontierMathV2Tier4": 0 } } }, { "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", "id": 253, "releaseDate": "2026-05-28", "market": null, "isRegional": false, "family": { "familyKey": "mellum2-12b-a2-5b", "familyName": "Mellum2 12B-A2.5B", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "mellum2-12b-a2-5b-instruct", "relatedModelKeys": [ "mellum2-12b-a2-5b-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 44, "overallScore": 44, "rawOverallScore": 44, "verifiedDisplayScore": 44, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 32, "multilingual": null, "instructionFollowing": 38.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 32, "multilingual": null, "instructionFollowing": 38.4, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 78, "instructionFollowing": 40 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 44.2 }, "coding": { "liveCodeBenchV6": 37.2 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "mmluRedux": 78.1, "gpqa": 40.9, "gpqaDiamond": 40.9 }, "multilingual": {}, "instructionFollowing": { "ifeval": 75.8 }, "math": {} } }, { "slug": "laguna-m-1", "canonicalModelKey": "laguna-m-1", "model": "Laguna M.1", "creator": "Poolside", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 43, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-m-1", "markdownUrl": "https://benchlm.ai/md/models/laguna-m-1.md", "id": 118, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "laguna", "familyName": "Laguna", "variantType": "m-1", "snapshotLabel": null, "baseFamilyModelKey": "laguna-m-1", "relatedModelKeys": [ "laguna-xs-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 43, "rawOverallScore": 42, "verifiedDisplayScore": 43, "displayCategoryScores": { "agentic": 28.4, "coding": 42.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 28.4, "coding": 42.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 64, "coding": 86 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 45.8 }, "coding": { "sweVerified": 74.6, "sweMultilingual": 63.1, "swePro": 49.2, "terminalBench2": 45.8 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 234, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-6", "familyName": "GLM-4.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-6", "relatedModelKeys": [ "glm-4-7" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 43, "rawOverallScore": 43, "verifiedDisplayScore": 43, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 27.6 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 27.6 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 107, "categoryRanks": { "coding": 80 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 76.9 }, "coding": { "vibeCodeBench": 3.09, "aaSciCode": 33.1 }, "reasoning": { "lcr": 28.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 23.38, "aaGpqaDiamond": 63.2, "aaHle": 5.5, "aaOmniscienceIndex": -31.7, "omniscienceAccuracy": 21.4, "omniscienceHallucinationRate": 67.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.7 }, "math": { "frontierMathV2Tiers13": 3.819, "frontierMathV2Tier4": 2.128 } } }, { "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", "id": 65, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "31b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-26b-a4b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 43, "rawOverallScore": 43, "verifiedDisplayScore": 43, "displayCategoryScores": { "agentic": null, "coding": 19.3, "reasoning": null, "multimodalGrounded": 53.3, "knowledge": 47, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 19.3, "reasoning": null, "multimodalGrounded": 53.3, "knowledge": 47, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 71, "categoryRanks": { "agentic": 136, "coding": 93 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 14.38, "tau2Bench": 59.9, "gdpvalAaNormalized": 15.7, "gdpvalAa": 814, "gertLabs": 35.26 }, "coding": { "sweRebench": 41.6, "reactNativeEvals": 75.2, "aaCodingIndex": 43.43, "aaSciCode": 43.4 }, "reasoning": { "lcr": 68.3, "critpt": 1.4 }, "multimodalGrounded": { "mmmuPro": 76.9, "aaMmmuPro": 73.4 }, "knowledge": { "gpqa": 84.3, "mmluPro": 85.2, "hle": 26.5, "hleNoTools": 19.5, "artificialAnalysis": 29.69, "aaGpqaDiamond": 85.7, "aaHle": 23.6, "aaOmniscienceIndex": -47.9, "omniscienceAccuracy": 20, "omniscienceHallucinationRate": 85 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 75.6 }, "math": {} } }, { "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", "id": 149, "releaseDate": "2025-02-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-3", "familyName": "Grok 3", "variantType": "snapshot", "snapshotLabel": "beta", "baseFamilyModelKey": "grok-3-beta", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 43, "rawOverallScore": 43, "verifiedDisplayScore": 43, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 26.9 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 26.9 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 197, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 3.793, "frontierMathV2Tier4": 0 } } }, { "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", "id": 112, "releaseDate": "2024-12-26", "market": null, "isRegional": false, "family": { "familyKey": "deepseek", "familyName": "DeepSeek", "variantType": "snapshot", "snapshotLabel": "V3", "baseFamilyModelKey": "deepseek-v3", "relatedModelKeys": [ "deepseek-v3-1", "deepseek-v3-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 43, "overallScore": 43, "rawOverallScore": 42, "verifiedDisplayScore": 43, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 26.2 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 26.2 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 174, "categoryRanks": { "agentic": 120, "coding": 122 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.58, "tau2Bench": 22.8, "gdpvalAaNormalized": 0, "gdpvalAa": 235 }, "coding": { "liveCodeBench": 37.6, "sweVerified": 42, "aaCodingIndex": 23.04, "aaSciCode": 35.4 }, "reasoning": { "lcr": 31.7, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1138 }, "knowledge": { "gpqa": 59.1, "mmluPro": 75.9, "artificialAnalysis": 14.22, "aaGpqaDiamond": 55.7, "aaHle": 2.9, "aaOmniscienceIndex": -41.6, "omniscienceAccuracy": 25.5, "omniscienceHallucinationRate": 90 }, "multilingual": {}, "instructionFollowing": { "ifeval": 86.1, "aaIfBench": 34.8 }, "math": { "frontierMathV2Tiers13": 1.724 } } }, { "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", "id": 95, "releaseDate": "2024-06-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-5-sonnet", "familyName": "Claude 3.5 Sonnet", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-5-sonnet", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 42, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.7 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 144, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "sweVerified": 49 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 59.4 }, "multilingual": {}, "instructionFollowing": {}, "math": { "frontierMathV2Tiers13": 2.069, "frontierMathV2Tier4": 0 } } }, { "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", "id": 108, "releaseDate": "2024-05-13", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o", "familyName": "GPT-4o", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o", "relatedModelKeys": [ "gpt-4o-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 42, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 191, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 25.1 }, "coding": { "aaSciCode": 33.3 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 849 }, "knowledge": { "artificialAnalysis": 11.11, "aaGpqaDiamond": 54.3, "aaHle": 2.4, "aaOmniscienceIndex": -10.5, "omniscienceAccuracy": 19.9, "omniscienceHallucinationRate": 37.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 34.3 }, "math": { "frontierMathV2Tiers13": 0.345 }, "korean": {} } }, { "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", "id": 151, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-scout", "familyName": "Llama 4 Scout", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-scout", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 42, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 200, "categoryRanks": { "agentic": 127, "coding": 133 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.1, "tau2Bench": 15.5, "gdpvalAaNormalized": 0, "gdpvalAa": 111 }, "coding": { "aaCodingIndex": 8.17, "aaSciCode": 17 }, "reasoning": { "lcr": 30.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 52.9, "designArenaWebsite": 768 }, "knowledge": { "artificialAnalysis": 10.26, "aaGpqaDiamond": 58.7, "aaHle": 3.8, "aaOmniscienceIndex": -52.1, "omniscienceAccuracy": 15.2, "omniscienceHallucinationRate": 79.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.5 }, "math": { "frontierMathV2Tiers13": 0 } } }, { "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", "id": 150, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-maverick", "familyName": "Llama 4 Maverick", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-maverick", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 42, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": 25.4 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 215, "categoryRanks": { "agentic": 137, "coding": 144 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 1.24, "tau2Bench": 17.8, "gdpvalAaNormalized": 0, "gdpvalAa": 7 }, "coding": { "aaCodingIndex": 16.28, "aaSciCode": 33.1 }, "reasoning": { "lcr": 50, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 62.1, "designArenaWebsite": 889 }, "knowledge": { "artificialAnalysis": 14.48, "aaGpqaDiamond": 67.1, "aaHle": 4.9, "aaOmniscienceIndex": -41.8, "omniscienceAccuracy": 24.9, "omniscienceHallucinationRate": 88.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 43 }, "math": { "frontierMathV2Tiers13": 0.69 } } }, { "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", "id": 153, "releaseDate": "2026-04-21", "market": null, "isRegional": false, "family": { "familyKey": "ling-2-6", "familyName": "Ling 2.6", "variantType": "flash", "snapshotLabel": null, "baseFamilyModelKey": "ling-2-6-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 42, "overallScore": 42, "rawOverallScore": 42, "verifiedDisplayScore": 42, "displayCategoryScores": { "agentic": null, "coding": 21.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 50.1, "multilingual": null, "instructionFollowing": 48.2, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 21.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 50.1, "multilingual": null, "instructionFollowing": 48.2, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 175, "categoryRanks": { "agentic": 103, "coding": 106, "instructionFollowing": 37 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 86, "gdpvalAaNormalized": 2.3, "gdpvalAa": 550, "aaAgenticIndex": 2.25 }, "coding": { "sciCode": 27, "aaCodingIndex": 25.26, "aaSciCode": 27.1 }, "reasoning": { "lcr": 28, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 14.05, "gpqa": 59, "aaGpqaDiamond": 59.3, "aaHle": 6.3, "aaOmniscienceIndex": -66.1, "omniscienceAccuracy": 15.6, "omniscienceHallucinationRate": 96.7 }, "multilingual": {}, "instructionFollowing": { "ifBench": 57, "aaIfBench": 57.4 }, "math": {} } }, { "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", "id": 251, "releaseDate": "2026-06-03", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "12b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 41, "rawOverallScore": 41, "verifiedDisplayScore": 41, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": 16.7, "multimodalGrounded": 15.1, "knowledge": 72.8, "multilingual": null, "instructionFollowing": null, "math": 57.7 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": 16.7, "multimodalGrounded": 15.1, "knowledge": 72.8, "multilingual": null, "instructionFollowing": null, "math": 57.7 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 154, "categoryRanks": { "coding": 92 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 11, "verifiedBenchmarkCount": 11, "rankableBenchmarkCount": 11, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "tau2Bench": 36.3, "gdpvalAaNormalized": 7.3, "gdpvalAa": 647 }, "coding": { "liveCodeBenchV6": 72, "aaSciCode": 38.2, "aaCodingIndex": 30.96 }, "reasoning": { "bbh": 53, "mrcrv2": 43.4, "lcr": 61.7, "critpt": 0 }, "multimodalGrounded": { "mmmuPro": 69.1, "mathVision": 79.7, "medXpertQaMm": 48.7, "aaMmmuPro": 69.7 }, "knowledge": { "gpqa": 78.8, "gpqaDiamond": 78.8, "mmluPro": 77.2, "hleNoTools": 5.2, "mmmlu": 83.4, "artificialAnalysis": 22.16, "aaGpqaDiamond": 75.3, "aaHle": 15.7, "aaOmniscienceIndex": -52.7, "omniscienceAccuracy": 15.6, "omniscienceHallucinationRate": 81 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.5 }, "math": { "aime2026": 77.5 } } }, { "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", "id": 68, "releaseDate": "2025-03-01", "market": null, "isRegional": false, "family": { "familyKey": "gemini-2-5-pro", "familyName": "Gemini 2.5 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-2-5-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 41, "overallScore": 41, "rawOverallScore": 40, "verifiedDisplayScore": 41, "displayCategoryScores": { "agentic": null, "coding": 37, "reasoning": null, "multimodalGrounded": null, "knowledge": 21.7, "multilingual": null, "instructionFollowing": null, "math": 35.4 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": 37, "reasoning": null, "multimodalGrounded": null, "knowledge": 21.7, "multilingual": null, "instructionFollowing": null, "math": 35.4 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 94, "categoryRanks": { "agentic": 76, "coding": 136 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 7.24, "tau2Bench": 54.1, "gertLabs": 42.01, "gdpvalAaNormalized": 8.7, "gdpvalAa": 673 }, "coding": { "sweVerified": 63.8, "vibeCodeBench": 0.4, "aaCodingIndex": 33.25, "aaSciCode": 42.8 }, "reasoning": { "lcr": 66, "critpt": 2.6 }, "multimodalGrounded": { "aaMmmuPro": 74.9, "designArenaWebsite": 1185 }, "knowledge": { "gpqa": 83, "hle": 18.8, "artificialAnalysis": 25.91, "aaGpqaDiamond": 84.4, "aaHle": 22.5, "aaOmniscienceIndex": -16.3, "omniscienceAccuracy": 39.1, "omniscienceHallucinationRate": 90.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.7 }, "math": { "frontierMathV2Tiers13": 14.138, "frontierMathV2Tier4": 4.167 } } }, { "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", "id": 123, "releaseDate": "2026-05-25", "market": null, "isRegional": false, "family": { "familyKey": "minicpm5", "familyName": "MiniCPM5", "variantType": "1b", "snapshotLabel": null, "baseFamilyModelKey": "minicpm5-1b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 40, "overallScore": 40, "rawOverallScore": 40, "verifiedDisplayScore": 40, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 40.8, "multilingual": null, "instructionFollowing": 24.7, "math": 5.5 }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 40.8, "multilingual": null, "instructionFollowing": 24.7, "math": 5.5 } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 225, "categoryRanks": { "agentic": 134, "instructionFollowing": 42 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "bfclV4": 25.15 }, "coding": { "liveCodeBenchPro": 22.68, "liveCodeBenchV6": 33.52 }, "reasoning": { "bbh": 71.89 }, "multimodalGrounded": {}, "knowledge": { "mmluPro": 48.85, "mmluRedux": 70.06, "gpqaDiamond": 26.26, "superGpqa": 23.14 }, "multilingual": {}, "instructionFollowing": { "ifBench": 46.67, "ifeval": 80.41 }, "math": { "aime2025": 40.42, "aime2026": 40.42, "hmmtFeb2026": 25.76, "math500": 91.6 } } }, { "slug": "ornith-1-0-9b", "canonicalModelKey": "ornith-1-0-9b", "model": "Ornith-1.0-9B", "creator": "DeepReinforce AI", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 40, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ornith-1-0-9b", "markdownUrl": "https://benchlm.ai/md/models/ornith-1-0-9b.md", "id": 270, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-0", "familyName": "Ornith 1.0", "variantType": "9b", "snapshotLabel": "9B", "baseFamilyModelKey": "ornith-1-0-397b", "relatedModelKeys": [ "ornith-1-0-397b", "ornith-1-0-35b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 40, "overallScore": 40, "rawOverallScore": 39, "verifiedDisplayScore": 40, "displayCategoryScores": { "agentic": 24.4, "coding": 36.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 24.4, "coding": 36.9, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 65, "coding": 79 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 43.1, "clawEval": 63.1 }, "coding": { "sweVerified": 69.4, "swePro": 42.9, "sweMultilingual": 52, "nl2Repo": 27.2, "terminalBench2": 43.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "laguna-xs-2", "canonicalModelKey": "laguna-xs-2", "model": "Laguna XS.2", "creator": "Poolside", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 39, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/laguna-xs-2", "markdownUrl": "https://benchlm.ai/md/models/laguna-xs-2.md", "id": 147, "releaseDate": "2026-04-28", "market": null, "isRegional": false, "family": { "familyKey": "laguna", "familyName": "Laguna", "variantType": "xs-2", "snapshotLabel": null, "baseFamilyModelKey": "laguna-m-1", "relatedModelKeys": [ "laguna-m-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 39, "overallScore": 39, "rawOverallScore": 38, "verifiedDisplayScore": 39, "displayCategoryScores": { "agentic": 21.3, "coding": 37.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 21.3, "coding": 37.5, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 74, "coding": 97 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 5, "verifiedBenchmarkCount": 5, "rankableBenchmarkCount": 5, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench2": 35.7 }, "coding": { "sweVerified": 69.9, "sweMultilingual": 57.7, "swePro": 46.3, "terminalBench2": 35.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 396, "releaseDate": "2026-08-18", "market": null, "isRegional": false, "family": { "familyKey": "ornith-1-5", "familyName": "Ornith 1.5", "variantType": "9b", "snapshotLabel": "9B", "baseFamilyModelKey": "ornith-1-5-397b", "relatedModelKeys": [ "ornith-1-5-397b", "ornith-1-5-35b-a3b", "ornith-1-0-9b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "ornith-1-0-9b" }, "scores": { "displayScore": 39, "overallScore": 39, "rawOverallScore": 38, "verifiedDisplayScore": 39, "displayCategoryScores": { "agentic": 28.1, "coding": 38.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 27.3, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 28.1, "coding": 38.3, "reasoning": null, "multimodalGrounded": null, "knowledge": 27.3, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 205, "categoryRanks": { "agentic": 110, "coding": 114 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 12, "verifiedBenchmarkCount": 12, "rankableBenchmarkCount": 12, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench21": 46.2, "hleWithTools": 30.5, "mcpAtlas": 54.2, "toolathlonVerified": 41.2, "wideResearch": 59.5, "browseComp": 56.4, "clawEval": 66.5 }, "coding": { "terminalBench21": 46.2, "sweVerified": 70.6, "swePro": 47.5, "sweMultilingual": 54.4, "nl2Repo": 32.4 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 86.4, "gpqaDiamond": 86.4, "hle": 20.2, "hleNoTools": 20.2 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 386, "releaseDate": "2026-08-11", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-5-lightning", "familyName": "Nemotron 3.5 Lightning", "variantType": "30b-a3b-nvfp4", "snapshotLabel": "NVFP4", "baseFamilyModelKey": "nemotron-3-5-lightning-30b-a3b-nvfp4", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 37, "overallScore": 37, "rawOverallScore": 37, "verifiedDisplayScore": 37, "displayCategoryScores": { "agentic": 11.5, "coding": 16.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.6, "multilingual": null, "instructionFollowing": 76.3, "math": null }, "verifiedDisplayCategoryScores": { "agentic": 11.5, "coding": 16.2, "reasoning": null, "multimodalGrounded": null, "knowledge": 75.6, "multilingual": null, "instructionFollowing": 76.3, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 212, "categoryRanks": { "agentic": 131, "coding": 134, "instructionFollowing": 28 }, "categoryRankingEligible": { "agentic": true, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 13, "verifiedBenchmarkCount": 13, "rankableBenchmarkCount": 13, "generatedBenchmarkCount": 0, "scoreConfidence": 2 }, "benchmarks": { "agentic": { "terminalBench2": 23.46, "pinchBench": 83.43, "browseComp": 36.81, "tau3Bench": 9.48, "gdpvalAa": 865, "aaAgenticIndex": 13.76, "gdpvalAaNormalized": 16.2 }, "coding": { "sweVerified": 52.8, "sweMultilingual": 36.47, "terminalBench2": 23.46, "sciCode": 31.38, "aaCodingIndex": 26.76, "aaSciCode": 31.6 }, "reasoning": { "lcr": 49.19, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "gpqa": 75.57, "gpqaDiamond": 75.57, "hleNoTools": 10.47, "mmluPro": 81.62, "artificialAnalysis": 23.61, "aaGpqaDiamond": 74.3, "aaHle": 10.6, "aaOmniscienceIndex": -17.7, "omniscienceAccuracy": 14.4, "omniscienceHallucinationRate": 37.6, "aaOpennessIndex": 77.8 }, "multilingual": {}, "instructionFollowing": { "ifBench": 72.88 }, "math": {} } }, { "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", "id": 168, "releaseDate": "2026-04-08", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-450m", "familyName": "LFM2.5-VL-450M", "variantType": "vl", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-450m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 35, "overallScore": 35, "rawOverallScore": 35, "verifiedDisplayScore": 35, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 16.1, "multilingual": null, "instructionFollowing": 26.4, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 16.1, "multilingual": null, "instructionFollowing": 26.4, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 86, "instructionFollowing": 41 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 7, "verifiedBenchmarkCount": 7, "rankableBenchmarkCount": 7, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 21.08 }, "coding": {}, "reasoning": {}, "multimodalGrounded": { "mmmu": 32.67, "realWorldQa": 58.43, "countBench": 73.31 }, "knowledge": { "gpqa": 25.66, "mmluPro": 19.32 }, "multilingual": {}, "instructionFollowing": { "ifeval": 61.16 }, "math": {} } }, { "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", "id": 86, "releaseDate": "2026-05-20", "market": null, "isRegional": false, "family": { "familyKey": "command-a", "familyName": "Command A", "variantType": "plus", "snapshotLabel": null, "baseFamilyModelKey": "command-a-plus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 31, "overallScore": 31, "rawOverallScore": 31, "verifiedDisplayScore": 31, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": 8, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 151, "categoryRanks": { "agentic": 92, "coding": 94, "multimodalGrounded": 33 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": true, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 85, "aaAgenticIndex": 9.23, "gdpvalAaNormalized": 10.7, "gdpvalAa": 715, "terminalBenchHard": 25 }, "coding": { "aaCodingIndex": 27.85, "aaSciCode": 37.8 }, "reasoning": { "lcr": 48.7, "critpt": 0.3 }, "multimodalGrounded": { "mmmu": 75.1, "mmmuPro": 63, "charxiv": 52.7, "aaMmmuPro": 63.2 }, "knowledge": { "artificialAnalysis": 22.51, "aaGpqaDiamond": 76.1, "aaHle": 12, "aaOmniscienceIndex": -4, "omniscienceAccuracy": 8.9, "omniscienceHallucinationRate": 14.2, "aaOpennessIndex": 38.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.9 }, "math": {} } }, { "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", "id": 271, "releaseDate": "2026-06-25", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-230m", "familyName": "LFM2.5-230M", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-230m", "relatedModelKeys": [ "lfm2-5-350m", "lfm2-5-8b-a1b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 31, "overallScore": 31, "rawOverallScore": 31, "verifiedDisplayScore": 31, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 16.1, "multilingual": null, "instructionFollowing": 1, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 16.1, "multilingual": null, "instructionFollowing": 1, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 85, "instructionFollowing": 43 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": true, "math": false } }, "coverage": { "trustedBenchmarkCount": 6, "verifiedBenchmarkCount": 6, "rankableBenchmarkCount": 6, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "bfclV4": 21.03 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 25.41, "gpqaDiamond": 25.41, "mmluPro": 20.25 }, "multilingual": {}, "instructionFollowing": { "ifeval": 71.71, "ifBench": 38.4 }, "math": {} } }, { "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", "id": 228, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-6", "familyName": "Claude Opus 4.6", "variantType": "reasoning", "snapshotLabel": "adaptive", "baseFamilyModelKey": "claude-opus-4-6", "relatedModelKeys": [ "claude-opus-4-6" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 38, "categoryRanks": { "agentic": 29, "coding": 35 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "apexAgentsAa": 33, "tau2Bench": 92.1 }, "coding": { "vibeCodeBench": 53.498, "aaSciCode": 51.9 }, "reasoning": { "lcr": 74.3, "critpt": 12.6 }, "multimodalGrounded": { "aaMmmuPro": 75.4, "designArenaWebsite": 1309 }, "knowledge": { "artificialAnalysis": 44.93, "aaGpqaDiamond": 89.6, "aaHle": 39.9, "aaOmniscienceIndex": 13.7, "omniscienceAccuracy": 47, "omniscienceHallucinationRate": 62.8 }, "multilingual": { "aaGlobalMmluLite": 92.2 }, "instructionFollowing": { "aaIfBench": 53.1 }, "math": {} } }, { "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", "id": 7, "releaseDate": "2025-11-17", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1", "familyName": "Grok 4.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 65, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "researchClawBench": 13.5 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 273, "releaseDate": "2026-07-06", "market": null, "isRegional": false, "family": { "familyKey": "hy3", "familyName": "Hy3", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "hy3", "relatedModelKeys": [ "hy3-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "hy3-preview" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 24, "categoryRanks": { "agentic": 94, "coding": 23 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 31.42, "gdpvalAaNormalized": 35.6, "gdpvalAa": 1212 }, "coding": { "aaSciCode": 47.6, "aaCodingIndex": 58.8 }, "reasoning": { "lcr": 74.7, "critpt": 4.9 }, "multimodalGrounded": { "designArenaWebsite": 1200 }, "knowledge": { "artificialAnalysis": 42.21, "aaGpqaDiamond": 89.7, "aaHle": 33.5, "aaOmniscienceIndex": -18.5, "omniscienceAccuracy": 32, "omniscienceHallucinationRate": 74.1 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 22, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 67, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 23.359 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1266 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 204, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "turbo", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 33, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 55.8, "tau2Bench": 98.5 }, "coding": { "aaSciCode": 43.6 }, "reasoning": { "lcr": 66.7, "critpt": 0.3 }, "multimodalGrounded": { "designArenaWebsite": 1286 }, "knowledge": { "artificialAnalysis": 39.05, "aaGpqaDiamond": 84.7, "aaHle": 27.8, "aaOmniscienceIndex": -16.4, "omniscienceAccuracy": 28.4, "omniscienceHallucinationRate": 62.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.2 }, "math": {} } }, { "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", "id": 28, "releaseDate": "2026-02-16", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-5-397b", "familyName": "Qwen3.5 397B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-5-397b", "relatedModelKeys": [ "qwen3-5-397b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 68, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 19.85, "apexAgentsAa": 15.3, "tau2Bench": 95.6, "gdpvalAaNormalized": 23.3, "gdpvalAa": 966 }, "coding": { "aaCodingIndex": 48.21, "aaSciCode": 42 }, "reasoning": { "lcr": 72.7, "critpt": 1.7 }, "multimodalGrounded": { "aaMmmuPro": 77.3 }, "knowledge": { "artificialAnalysis": 34.26, "aaGpqaDiamond": 89.3, "aaHle": 29, "aaOmniscienceIndex": -30.7, "omniscienceAccuracy": 30.8, "omniscienceHallucinationRate": 88.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 78.8 }, "math": {} } }, { "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", "id": 6, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-pro", "familyName": "MiMo-V2-Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-pro", "relatedModelKeys": [ "mimo-v2-flash", "mimo-v2-omni" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 30, "categoryRanks": { "coding": 33 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 57.8, "tau2Bench": 95, "gertLabs": 36.68, "researchClawBench": 15.3 }, "coding": { "sweVerified": 78, "aaSciCode": 42.5 }, "reasoning": { "lcr": 65.7, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 41.37, "aaGpqaDiamond": 87, "aaHle": 30.4, "aaOmniscienceIndex": 4.6, "omniscienceAccuracy": 26.6, "omniscienceHallucinationRate": 30 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 68.8 }, "math": {} } }, { "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", "id": 179, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "instant", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2", "gpt-5-2-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 72, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 177, "releaseDate": "2025-12-11", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2", "familyName": "GPT-5.2", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2", "relatedModelKeys": [ "gpt-5-2", "gpt-5-2-instant" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 27, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 4, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 178, "releaseDate": "2026-03-03", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3", "familyName": "GPT-5.3", "variantType": "instant", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-instant", "relatedModelKeys": [ "gpt-5-3-codex" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 75, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 5, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 19, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "reasoning", "snapshotLabel": "high", "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-medium", "gpt-5-mini", "gpt-5-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 80, "categoryRanks": { "agentic": 59 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 26.53, "tau2Bench": 84.8, "gdpvalAaNormalized": 29.1, "gdpvalAa": 1082, "jobBench": 8.53 }, "coding": { "vibeCodeBench": 20.088, "aaCodingIndex": 37.78, "aaSciCode": 42.9 }, "reasoning": { "lcr": 76.3, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 74.2, "designArenaWebsite": 1203 }, "knowledge": { "artificialAnalysis": 35.31, "aaGpqaDiamond": 85.4, "aaHle": 28.5, "aaOmniscienceIndex": -8.7, "omniscienceAccuracy": 40.3, "omniscienceHallucinationRate": 82.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 73.1 }, "math": { "aaMath500": 99.4 } } }, { "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", "id": 102, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-5", "familyName": "GLM-5", "variantType": "vision-turbo", "snapshotLabel": null, "baseFamilyModelKey": "glm-5", "relatedModelKeys": [ "glm-5", "glm-5-reasoning", "glm-5-1", "glm-5-turbo" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 53, "categoryRanks": { "coding": 43 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 53.8, "tau2Bench": 98.5, "gertLabs": 30.76 }, "coding": { "aaSciCode": 43.5 }, "reasoning": { "lcr": 65.7, "critpt": 0.6 }, "multimodalGrounded": { "aaMmmuPro": 72.8, "designArenaWebsite": 1249 }, "knowledge": { "artificialAnalysis": 35.35, "aaGpqaDiamond": 80.9, "aaHle": 17.1, "aaOmniscienceIndex": -19.3, "omniscienceAccuracy": 29.3, "omniscienceHallucinationRate": 68.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 61.1 }, "math": {} } }, { "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", "id": 24, "releaseDate": "2026-03-18", "market": null, "isRegional": false, "family": { "familyKey": "mimo-v2-omni", "familyName": "MiMo-V2-Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mimo-v2-omni", "relatedModelKeys": [ "mimo-v2-flash", "mimo-v2-pro" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 51, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 45.2, "tau2Bench": 91.2 }, "coding": { "sweVerified": 74.8, "aaSciCode": 36.7 }, "reasoning": { "lcr": 71.7, "critpt": 1.1 }, "multimodalGrounded": { "aaMmmuPro": 69.9 }, "knowledge": { "artificialAnalysis": 35.87, "aaGpqaDiamond": 82.8, "aaHle": 22.1, "aaOmniscienceIndex": -20.1, "omniscienceAccuracy": 19.3, "omniscienceHallucinationRate": 48.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 53.5 }, "math": {} } }, { "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", "id": 235, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1-fast", "familyName": "Grok 4.1 Fast", "variantType": "reasoning", "snapshotLabel": "reasoning", "baseFamilyModelKey": "grok-4-1-fast", "relatedModelKeys": [ "grok-4-1-fast" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 76, "categoryRanks": { "coding": 77 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 93.3 }, "coding": { "vibeCodeBench": 1.2, "aaSciCode": 44.2 }, "reasoning": { "lcr": 70.3, "critpt": 2.9 }, "multimodalGrounded": { "aaMmmuPro": 63.3 }, "knowledge": { "artificialAnalysis": 31.32, "aaGpqaDiamond": 85.3, "aaHle": 19.3, "aaOmniscienceIndex": -29.9, "omniscienceAccuracy": 25.1, "omniscienceHallucinationRate": 73.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 52.7 }, "math": {} } }, { "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", "id": 72, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-2", "familyName": "DeepSeek V3.2", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-2", "relatedModelKeys": [ "deepseek-v3-2" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 82, "categoryRanks": { "coding": 72 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 5.108 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1193 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 21, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-1-fast", "familyName": "Grok 4.1 Fast", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-1-fast", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 131, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 63.7, "gertLabs": 47.32 }, "coding": { "aaSciCode": 29.6 }, "reasoning": { "lcr": 28.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 48.4 }, "knowledge": { "artificialAnalysis": 17.03, "aaGpqaDiamond": 63.7, "aaHle": 5.1, "aaOmniscienceIndex": -50.9, "omniscienceAccuracy": 17.2, "omniscienceHallucinationRate": 82.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.5 }, "math": {} } }, { "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", "id": 155, "releaseDate": "2025-08-21", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-1", "familyName": "DeepSeek V3.1", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-1", "relatedModelKeys": [ "deepseek-v3-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 118, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 37.4 }, "coding": { "aaSciCode": 39.1 }, "reasoning": { "lcr": 56.7, "critpt": 2 }, "multimodalGrounded": { "designArenaWebsite": 1141 }, "knowledge": { "artificialAnalysis": 20.97, "aaGpqaDiamond": 77.9, "aaHle": 14.3, "aaOmniscienceIndex": -29.6, "omniscienceAccuracy": 29, "omniscienceHallucinationRate": 82.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.5 }, "math": {} } }, { "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", "id": 166, "releaseDate": "2025-08-21", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-v3-1", "familyName": "DeepSeek V3.1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-v3-1", "relatedModelKeys": [ "deepseek-v3-1-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 116, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 34.8 }, "coding": { "aaSciCode": 36.7 }, "reasoning": { "lcr": 46.7, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1141 }, "knowledge": { "artificialAnalysis": 21.37, "aaGpqaDiamond": 73.5, "aaHle": 6.7, "aaOmniscienceIndex": -42.7, "omniscienceAccuracy": 23.1, "omniscienceHallucinationRate": 85.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 37.8 }, "math": {} } }, { "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", "id": 99, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "mistral-large-3", "familyName": "Mistral Large 3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-large-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 139, "categoryRanks": { "agentic": 100, "coding": 142 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 5.52, "tau2Bench": 24.6, "gdpvalAaNormalized": 7.2, "gdpvalAa": 644 }, "coding": { "aaCodingIndex": 20.07, "aaSciCode": 36.2 }, "reasoning": { "lcr": 34.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 55.7 }, "knowledge": { "artificialAnalysis": 15.92, "aaGpqaDiamond": 68, "aaHle": 4.2, "aaOmniscienceIndex": -39.6, "omniscienceAccuracy": 25, "omniscienceHallucinationRate": 86 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.2 }, "math": {} } }, { "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", "id": 164, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-5", "familyName": "GLM-4.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 86, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1188 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 236, "releaseDate": "2025-09-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-fast", "familyName": "Grok 4 Fast", "variantType": "reasoning", "snapshotLabel": "reasoning", "baseFamilyModelKey": "grok-4-fast-reasoning", "relatedModelKeys": [ "grok-4" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 101, "categoryRanks": { "coding": 111 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 65.8 }, "coding": { "vibeCodeBench": 0, "aaSciCode": 44.2 }, "reasoning": { "lcr": 71, "critpt": 2.9 }, "multimodalGrounded": { "aaMmmuPro": 61.8 }, "knowledge": { "artificialAnalysis": 27.95, "aaGpqaDiamond": 84.7, "aaHle": 19.1, "aaOmniscienceIndex": -29.9, "omniscienceAccuracy": 22.8, "omniscienceHallucinationRate": 68.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 50.5 }, "math": {} } }, { "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", "id": 142, "releaseDate": "2025-01-20", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-r1", "familyName": "DeepSeek-R1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-r1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 124, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 36.5 }, "coding": { "aaSciCode": 40.3 }, "reasoning": { "lcr": 56.7, "critpt": 1.4 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 20.37, "aaGpqaDiamond": 81.3, "aaHle": 15.8, "aaOmniscienceIndex": -27.4, "omniscienceAccuracy": 30.5, "omniscienceHallucinationRate": 83.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.6 }, "math": {} } }, { "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", "id": 180, "releaseDate": "2026-02-12", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-3-codex", "familyName": "GPT-5.3 Codex", "variantType": "spark", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-3-codex", "relatedModelKeys": [ "gpt-5-3-codex" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 90, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 15, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 181, "releaseDate": "2026-01-20", "market": null, "isRegional": false, "family": { "familyKey": "step-3-5-flash", "familyName": "Step 3.5 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-3-5-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 108, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 23, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 189, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m2-5", "familyName": "MiniMax M2.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m2-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 85, "categoryRanks": { "agentic": 97, "coding": 68 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 38, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 14.852 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 20, "releaseDate": "2024-09-12", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "snapshot", "snapshotLabel": "preview", "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1", "o1-pro" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 143, "categoryRanks": { "coding": 98 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 34.05 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 17.21, "aaGpqaDiamond": 76.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 175, "releaseDate": "2026-01-27", "market": null, "isRegional": false, "family": { "familyKey": "trinity-large", "familyName": "Trinity Large", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "trinity-large-thinking", "relatedModelKeys": [ "trinity-large-thinking" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 97, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 90.1, "gdpvalAaNormalized": 3.3, "gdpvalAa": 565, "aaAgenticIndex": 3.72 }, "coding": { "aaSciCode": 36.1, "aaCodingIndex": 25.77 }, "reasoning": { "lcr": 38.3, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1155 }, "knowledge": { "mmlu": 87.2, "mmluProArcee": 75.2, "gpqaDiamond": 63.3, "artificialAnalysis": 18.66, "aaGpqaDiamond": 75.2, "aaHle": 15.8, "aaOmniscienceIndex": -44.1, "omniscienceAccuracy": 22.5, "omniscienceHallucinationRate": 85.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 56.3 }, "math": { "aime2025Arcee": 24 } } }, { "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", "id": 163, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-5-air", "familyName": "GLM-4.5-Air", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-5-air", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 156, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 46.5 }, "coding": { "aaSciCode": 30.6 }, "reasoning": { "lcr": 45.7, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1165 }, "knowledge": { "artificialAnalysis": 16.66, "aaGpqaDiamond": 73.3, "aaHle": 7, "aaOmniscienceIndex": -61.5, "omniscienceAccuracy": 16.3, "omniscienceHallucinationRate": 92.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 37.6 }, "math": {} } }, { "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", "id": 116, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "trinity-large", "familyName": "Trinity Large", "variantType": "thinking", "snapshotLabel": null, "baseFamilyModelKey": "trinity-large-thinking", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 148, "categoryRanks": { "agentic": 107, "coding": 139 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 4, "verifiedBenchmarkCount": 4, "rankableBenchmarkCount": 4, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 90.1, "gertLabs": 32.55, "gdpvalAaNormalized": 3.3, "gdpvalAa": 565, "aaAgenticIndex": 3.72 }, "coding": { "sweVerifiedArcee": 63.2, "aaSciCode": 36.1, "aaCodingIndex": 25.77 }, "reasoning": { "lcr": 38.3, "critpt": 0.9 }, "multimodalGrounded": { "designArenaWebsite": 1155 }, "knowledge": { "gpqaDiamond": 76.3, "mmluProArcee": 83.4, "artificialAnalysis": 18.66, "aaGpqaDiamond": 75.2, "aaHle": 15.8, "aaOmniscienceIndex": -44.1, "omniscienceAccuracy": 22.5, "omniscienceHallucinationRate": 85.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 56.3 }, "math": { "aime2025Arcee": 96.3 } } }, { "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", "id": 186, "releaseDate": "2025-10-01", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-7-flash", "familyName": "GLM-4.7-Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-7-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 137, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 35, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 165, "releaseDate": "2025-03-12", "market": null, "isRegional": false, "family": { "familyKey": "gemma-3-27b", "familyName": "Gemma 3 27B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemma-3-27b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 189, "categoryRanks": { "agentic": 125, "coding": 130 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 0.27, "tau2Bench": 10.5, "gdpvalAaNormalized": 0, "gdpvalAa": -119 }, "coding": { "aaCodingIndex": 10.06, "aaSciCode": 21.2 }, "reasoning": { "lcr": 6.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 48 }, "knowledge": { "artificialAnalysis": 7.36, "aaGpqaDiamond": 42.8, "aaHle": 4.4, "aaOmniscienceIndex": -67.2, "omniscienceAccuracy": 13, "omniscienceHallucinationRate": 92.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31.8 }, "math": {} } }, { "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", "id": 66, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-small-4", "familyName": "Mistral Small 4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-small-4", "relatedModelKeys": [ "mistral-small-4-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 160, "categoryRanks": { "agentic": 99, "coding": 102 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 4.63, "tau2Bench": 41.2, "gdpvalAaNormalized": 4.5, "gdpvalAa": 590 }, "coding": { "aaCodingIndex": 26.64, "aaSciCode": 38 }, "reasoning": { "lcr": 47.3, "critpt": 0.3 }, "multimodalGrounded": { "aaMmmuPro": 56.8 }, "knowledge": { "artificialAnalysis": 19.71, "aaGpqaDiamond": 76.9, "aaHle": 9.9, "aaOmniscienceIndex": -30.4, "omniscienceAccuracy": 21.7, "omniscienceHallucinationRate": 66.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.2 }, "math": {} } }, { "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", "id": 129, "releaseDate": "2025-08-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-oss", "familyName": "GPT-OSS", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-oss-120b", "relatedModelKeys": [ "gpt-oss-20b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 56.4, "reasoning": null, "multimodalGrounded": null, "knowledge": 60.8, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 141, "categoryRanks": { "agentic": 91, "coding": 101, "knowledge": 40 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 13.43, "apexAgentsAa": 3.1, "tau2Bench": 65.8, "gdpvalAaNormalized": 15.1, "gdpvalAa": 803, "gertLabs": 29.61, "aaItbench": 5.6, "aaHarveyLab": 13.9, "terminalBenchHard": 23.5 }, "coding": { "reactNativeEvals": 71.6, "aaCodingIndex": 30.44, "aaSciCode": 38.9, "aaLiveCodeBench": 87.8 }, "reasoning": { "lcr": 51, "critpt": 1.1 }, "multimodalGrounded": { "designArenaWebsite": 986 }, "knowledge": { "artificialAnalysis": 24.13, "aaGpqaDiamond": 78.2, "aaHle": 19.6, "aaOmniscienceIndex": -49.2, "omniscienceAccuracy": 21.8, "omniscienceHallucinationRate": 90.8, "aaOpennessIndex": 38.9, "aaMmluPro": 80.8 }, "multilingual": { "aaGlobalMmluLite": 82.8 }, "instructionFollowing": { "aaIfBench": 69 }, "math": { "aaAime2025": 93.4 } } }, { "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", "id": 79, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseek-llm-2-0", "familyName": "DeepSeek LLM 2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-llm-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 103, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 1, "releaseDate": "2025-11-19", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1-codex-max", "familyName": "GPT-5.1-Codex-Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1-codex-max", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 104, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 83 }, "coding": { "vibeCodeBench": 22.168, "aaSciCode": 40.2 }, "reasoning": { "lcr": 69, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 72.5 }, "knowledge": { "artificialAnalysis": 35.6, "aaGpqaDiamond": 86, "aaHle": 25.7, "aaOmniscienceIndex": -6.5, "omniscienceAccuracy": 39.9, "omniscienceHallucinationRate": 77.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70 }, "math": {} } }, { "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", "id": 184, "releaseDate": "2026-02-24", "market": null, "isRegional": false, "family": { "familyKey": "mercury-2", "familyName": "Mercury 2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mercury-2", "relatedModelKeys": [ "mercury-2-5-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 147, "categoryRanks": { "agentic": 101, "coding": 143 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 29, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 4, "releaseDate": "2025-12-18", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-2-codex", "familyName": "GPT-5.2-Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-2-codex", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": 58.6, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 88, "categoryRanks": { "agentic": 50, "coding": 47 }, "categoryRankingEligible": { "agentic": false, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 92.1, "gertLabs": 51.79, "jobBench": 26 }, "coding": { "vibeCodeBench": 37.912, "aaSciCode": 54.6 }, "reasoning": { "lcr": 79.3, "critpt": 8.7 }, "multimodalGrounded": { "aaMmmuPro": 76.3 }, "knowledge": { "artificialAnalysis": 41.22, "aaGpqaDiamond": 89.9, "aaHle": 35.7, "aaOmniscienceIndex": -2.2, "omniscienceAccuracy": 41.1, "omniscienceHallucinationRate": 73.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 77.6 }, "math": {} } }, { "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", "id": 16, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "reasoning", "snapshotLabel": "medium", "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-mini", "gpt-5-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 109, "categoryRanks": { "coding": 65 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 86.5 }, "coding": { "aaSciCode": 41.1 }, "reasoning": { "lcr": 76.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 74.3, "designArenaWebsite": 1203 }, "knowledge": { "artificialAnalysis": 34.57, "aaGpqaDiamond": 84.2, "aaHle": 25.4, "aaOmniscienceIndex": -10.9, "omniscienceAccuracy": 39.5, "omniscienceHallucinationRate": 83.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70.6 }, "math": { "aaMath500": 99.1 } } }, { "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", "id": 124, "releaseDate": "2024-03-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-opus", "familyName": "Claude 3 Opus", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-opus", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 193, "categoryRanks": { "coding": 129 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 19.53, "aaSciCode": 23.3 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 11.76, "aaGpqaDiamond": 48.9, "aaHle": 2.8 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 145, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-nano-30b", "familyName": "Nemotron 3 Nano 30B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-nano-30b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 111, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 40.9, "gdpvalAaNormalized": 0, "gdpvalAa": 493, "aaAgenticIndex": 1.99 }, "coding": { "aaSciCode": 29.6, "aaCodingIndex": 14.37 }, "reasoning": { "lcr": 37.3, "critpt": 0.9 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 14.54, "aaGpqaDiamond": 75.7, "aaHle": 11.4, "aaOmniscienceIndex": -51.6, "omniscienceAccuracy": 17.3, "omniscienceHallucinationRate": 83.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.1 }, "math": {} } }, { "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", "id": 167, "releaseDate": "2025-08-05", "market": null, "isRegional": false, "family": { "familyKey": "gpt-oss", "familyName": "GPT-OSS", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-oss-120b", "relatedModelKeys": [ "gpt-oss-120b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 185, "categoryRanks": { "agentic": 123, "coding": 127 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 3.1, "apexAgentsAa": 0.7, "tau2Bench": 60.2, "gdpvalAaNormalized": 3.4, "gdpvalAa": 569 }, "coding": { "reactNativeEvals": 71, "aaCodingIndex": 20.7, "aaSciCode": 34.4 }, "reasoning": { "lcr": 33.3, "critpt": 1.4 }, "multimodalGrounded": { "designArenaWebsite": 871 }, "knowledge": { "artificialAnalysis": 15.23, "aaGpqaDiamond": 68.8, "aaHle": 11, "aaOmniscienceIndex": -63, "omniscienceAccuracy": 16, "omniscienceHallucinationRate": 94.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 65.1 }, "math": {} } }, { "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", "id": 101, "releaseDate": "2024-07-18", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o", "familyName": "GPT-4o", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o", "relatedModelKeys": [ "gpt-4o" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 204, "categoryRanks": { "agentic": 129, "coding": 135 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 0.96, "gdpvalAaNormalized": 0, "gdpvalAa": 239 }, "coding": { "aaSciCode": 22.9, "aaCodingIndex": 11.38 }, "reasoning": {}, "multimodalGrounded": { "aaMmmuPro": 41.5 }, "knowledge": { "artificialAnalysis": 6.67, "aaGpqaDiamond": 42.6, "aaHle": 4.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31 }, "math": {}, "korean": {} } }, { "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", "id": 100, "releaseDate": "2024-07-24", "market": null, "isRegional": false, "family": { "familyKey": "mistral-large-2", "familyName": "Mistral Large 2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-large-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 186, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 30.7 }, "coding": { "aaSciCode": 29.2 }, "reasoning": { "lcr": 5.3, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 8.99, "aaGpqaDiamond": 48.6, "aaHle": 3.3, "aaOmniscienceIndex": -34.4, "omniscienceAccuracy": 19.9, "omniscienceHallucinationRate": 67.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 31.2 }, "math": {} } }, { "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", "id": 73, "releaseDate": "2024-09-19", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-72b", "familyName": "Qwen2.5-72B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-72b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 117, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 97, "releaseDate": "2024-07-23", "market": null, "isRegional": false, "family": { "familyKey": "llama-3-1-405b", "familyName": "Llama 3.1 405B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-3-1-405b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 120, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 19 }, "coding": { "aaSciCode": 29.9 }, "reasoning": { "lcr": 24.7, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 8.32, "aaGpqaDiamond": 51.5, "aaHle": 4, "aaOmniscienceIndex": -17.1, "omniscienceAccuracy": 23.2, "omniscienceHallucinationRate": 52.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39 }, "math": {} } }, { "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", "id": 187, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-super-120b-a12b", "familyName": "Nemotron 3 Super 120B A12B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-super-120b-a12b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 121, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 19, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 143, "releaseDate": "2024-04-18", "market": null, "isRegional": false, "family": { "familyKey": "llama-3-70b", "familyName": "Llama 3 70B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-3-70b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 122, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 216, "releaseDate": "2025-01-01", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-coder", "familyName": "Qwen2.5 Coder", "variantType": "32b-instruct", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-coder-32b-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 208, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 27.1 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 6.88, "aaGpqaDiamond": 41.7, "aaHle": 3.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 61, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseek-coder-2-0", "familyName": "DeepSeek Coder 2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-coder-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 125, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 183, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "seed-1-6", "familyName": "Seed 1.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "seed-1-6", "relatedModelKeys": [ "seed-1-6-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 126, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 92, "releaseDate": "2026-01-15", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-3-super-100b", "familyName": "Nemotron 3 Super 100B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-3-super-100b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 130, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "clawEval": 5.5, "aaAgenticIndex": 8.79, "apexAgentsAa": 1.8, "tau2Bench": 67.8, "gdpvalAaNormalized": 10, "gdpvalAa": 701 }, "coding": { "aaCodingIndex": 37.72, "aaSciCode": 36 }, "reasoning": { "lcr": 60.3, "critpt": 3.1 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 25.67, "aaGpqaDiamond": 80, "aaHle": 20.8, "aaOmniscienceIndex": -41.5, "omniscienceAccuracy": 24.3, "omniscienceHallucinationRate": 87 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 71.5 }, "math": {} } }, { "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", "id": 114, "releaseDate": "2024-02-15", "market": null, "isRegional": false, "family": { "familyKey": "gemini-1-5-pro", "familyName": "Gemini 1.5 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-1-5-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 207, "categoryRanks": { "coding": 132 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 23.63, "aaSciCode": 29.5 }, "reasoning": {}, "multimodalGrounded": { "aaMmmuPro": 55 }, "knowledge": { "artificialAnalysis": 9.85, "aaGpqaDiamond": 58.9, "aaHle": 4.6 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 54, "releaseDate": "2025-01-27", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-1m", "familyName": "Qwen2.5-1M", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-1m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 134, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 128, "releaseDate": "2025-01-01", "market": null, "isRegional": false, "family": { "familyKey": "phi-4", "familyName": "Phi-4", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "phi-4", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 216, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 0 }, "coding": { "aaSciCode": 26 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 4.55, "aaGpqaDiamond": 57.5, "aaHle": 3.8, "aaOmniscienceIndex": -55.7, "omniscienceAccuracy": 14.1, "omniscienceHallucinationRate": 81.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 23.5 }, "math": {} } }, { "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", "id": 62, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepseekmath", "familyName": "DeepSeekMath", "variantType": "snapshot", "snapshotLabel": "V2", "baseFamilyModelKey": "deepseekmath-v2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 133, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 185, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "seed-2-0", "familyName": "Seed 2.0", "variantType": "lite", "snapshotLabel": null, "baseFamilyModelKey": "seed-2-0-lite", "relatedModelKeys": [ "seed-2-0-mini" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 136, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 188, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-14b", "familyName": "Ministral 3 14B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-14b", "relatedModelKeys": [ "ministral-3-14b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 138, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 24, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 182, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-medium", "gpt-5-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 180, "categoryRanks": { "agentic": 105, "coding": 128 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 50, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 14.171 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "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", "id": 39, "releaseDate": "2025-04-16", "market": null, "isRegional": false, "family": { "familyKey": "o3", "familyName": "o3", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "o3", "relatedModelKeys": [ "o3", "o3-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 155, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 33.29, "aaGpqaDiamond": 84.5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 192, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-14b", "familyName": "Ministral 3 14B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-14b", "relatedModelKeys": [ "ministral-3-14b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 209, "categoryRanks": { "agentic": 133, "coding": 137 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 190, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "aion-2-0", "familyName": "Aion-2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "aion-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 140, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 158, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mixtral-8x22b", "familyName": "Mixtral 8x22B", "variantType": "instruct", "snapshotLabel": "v0.1", "baseFamilyModelKey": "mixtral-8x22b-instruct-v0-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 142, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 93, "releaseDate": "2025-08-28", "market": null, "isRegional": false, "family": { "familyKey": "grok-code-fast-1", "familyName": "Grok Code Fast 1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-code-fast-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 203, "categoryRanks": { "coding": 138 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 75.7 }, "coding": { "sweVerified": 70.8, "aaSciCode": 36.2 }, "reasoning": { "lcr": 51, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 21.95, "aaGpqaDiamond": 72.7, "aaHle": 8, "aaOmniscienceIndex": -37.1, "omniscienceAccuracy": 23.5, "omniscienceHallucinationRate": 79.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 41.4 }, "math": {} } }, { "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", "id": 135, "releaseDate": "2023-11-06", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4-turbo", "familyName": "GPT-4 Turbo", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4-turbo", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 211, "categoryRanks": { "coding": 141 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaCodingIndex": 21.49, "aaSciCode": 31.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 7.69, "aaHle": 3.1 }, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "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", "id": 138, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "z-1", "familyName": "Z-1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "z-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 163, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 191, "releaseDate": "2025-06-01", "market": null, "isRegional": false, "family": { "familyKey": "seed-1-6", "familyName": "Seed 1.6", "variantType": "flash", "snapshotLabel": null, "baseFamilyModelKey": "seed-1-6", "relatedModelKeys": [ "seed-1-6" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 166, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 140, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "nemotron-4-15b", "familyName": "Nemotron-4 15B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-4-15b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 165, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 133, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-8x7b", "familyName": "Mistral 8x7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-8x7b", "relatedModelKeys": [ "mistral-8x7b-v0-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 167, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 137, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "moonshot", "familyName": "Moonshot", "variantType": "snapshot", "snapshotLabel": "v1", "baseFamilyModelKey": "moonshot-v1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 168, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 193, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "seed-2-0", "familyName": "Seed 2.0", "variantType": "mini", "snapshotLabel": null, "baseFamilyModelKey": "seed-2-0-lite", "relatedModelKeys": [ "seed-2-0-lite" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 169, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 2, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 132, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "nemotron-ultra-253b", "familyName": "Nemotron Ultra 253B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nemotron-ultra-253b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 171, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 11.4 }, "coding": { "aaSciCode": 34.7 }, "reasoning": { "lcr": 7.7, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 8.92, "aaGpqaDiamond": 72.8, "aaHle": 7.4, "aaOmniscienceIndex": -44.9, "omniscienceAccuracy": 20.1, "omniscienceHallucinationRate": 81.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38.2 }, "math": {} } }, { "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", "id": 146, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gemini-1-0-pro", "familyName": "Gemini 1.0 Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-1-0-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 217, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 11.7 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 2.74, "aaGpqaDiamond": 27.7, "aaHle": 4.2 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 130, "releaseDate": "2024-03-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-3-haiku", "familyName": "Claude 3 Haiku", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "claude-3-haiku", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 218, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 21.1 }, "coding": { "aaSciCode": 18.6 }, "reasoning": { "lcr": 25, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 30.8 }, "knowledge": { "artificialAnalysis": 3.5, "aaGpqaDiamond": 37.4, "aaHle": 4.1, "aaOmniscienceIndex": -48.6, "omniscienceAccuracy": 17.6, "omniscienceHallucinationRate": 80.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 36.1 }, "math": {} } }, { "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", "id": 196, "releaseDate": "2026-01-10", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-24b-a2b", "familyName": "LFM2-24B-A2B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-24b-a2b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 221, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 13, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 98, "releaseDate": "2025-08-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-4-1-opus", "familyName": "Claude 4.1 Opus", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "claude-4-1-opus", "relatedModelKeys": [ "claude-4-1-opus" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 206, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 71.4 }, "coding": { "aaSciCode": 40.9 }, "reasoning": { "lcr": 73.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 67.9 }, "knowledge": { "artificialAnalysis": 34.54, "aaGpqaDiamond": 80.9, "aaHle": 12.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 55.4 }, "math": {} } }, { "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", "id": 197, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-8b", "familyName": "Ministral 3 8B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-8b", "relatedModelKeys": [ "ministral-3-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 192, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 162, "releaseDate": "2025-04-01", "market": null, "isRegional": false, "family": { "familyKey": "nova-pro", "familyName": "Nova Pro", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "nova-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 220, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 14 }, "coding": { "aaSciCode": 20.8 }, "reasoning": { "lcr": 22.3, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 44.3 }, "knowledge": { "artificialAnalysis": 7.46, "aaGpqaDiamond": 49.9, "aaHle": 3.2, "aaOmniscienceIndex": -47.7, "omniscienceAccuracy": 16.9, "omniscienceHallucinationRate": 77.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38.1 }, "math": {} } }, { "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", "id": 199, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-8b", "familyName": "Ministral 3 8B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-8b", "relatedModelKeys": [ "ministral-3-8b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 219, "categoryRanks": { "agentic": 139, "coding": 145 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 169, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-7b", "familyName": "Mistral 7B", "variantType": "snapshot", "snapshotLabel": "v0.3", "baseFamilyModelKey": "mistral-7b-v0-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 194, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 107, "releaseDate": "2025-01-26", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-vl-32b", "familyName": "Qwen2.5-VL-32B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-vl-32b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 195, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 156, "releaseDate": "2026-02-28", "market": null, "isRegional": false, "family": { "familyKey": "llama-4-behemoth", "familyName": "Llama 4 Behemoth", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-4-behemoth", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 196, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 198, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5 1.2B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-instruct" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 223, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 13, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 200, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-3b", "familyName": "Ministral 3 3B", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-3b", "relatedModelKeys": [ "ministral-3-3b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 198, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 195, "releaseDate": "2025-01-15", "market": null, "isRegional": false, "family": { "familyKey": "minimax-m1-80k", "familyName": "MiniMax M1 80k", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minimax-m1-80k", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 214, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 35, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 202, "releaseDate": "2025-12-02", "market": null, "isRegional": false, "family": { "familyKey": "ministral-3-3b", "familyName": "Ministral 3 3B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ministral-3-3b", "relatedModelKeys": [ "ministral-3-3b-reasoning" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 222, "categoryRanks": { "agentic": 140, "coding": 146 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 170, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mistral-8x7b", "familyName": "Mistral 8x7B", "variantType": "snapshot", "snapshotLabel": "v0.2", "baseFamilyModelKey": "mistral-8x7b", "relatedModelKeys": [ "mistral-8x7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 199, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 201, "releaseDate": "2026-03-01", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5 1.2B", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-thinking" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 224, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 13, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ling-3-0-flash-fin", "canonicalModelKey": "ling-3-0-flash-fin", "model": "Ling 3.0 Flash Fin", "creator": "InclusionAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ling-3-0-flash-fin", "markdownUrl": "https://benchlm.ai/md/models/ling-3-0-flash-fin.md", "id": 411, "releaseDate": "2026-08-28", "market": null, "isRegional": false, "family": { "familyKey": "ling-3-0", "familyName": "Ling 3.0", "variantType": "flash-fin", "snapshotLabel": "Fin", "baseFamilyModelKey": "ling-3-0-flash", "relatedModelKeys": [ "ling-3-0-flash", "ling-3-0-flash-fp8" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "financeAgentV2": 59.81, "apexAgents": 29.17, "spreadsheetBench2": 21.81 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 258, "releaseDate": "2026-06-12", "market": null, "isRegional": false, "family": { "familyKey": "kimi-k2-7-code", "familyName": "Kimi K2.7 Code", "variantType": "code", "snapshotLabel": null, "baseFamilyModelKey": "kimi-k2-7-code", "relatedModelKeys": [ "kimi-2-6", "kimi-k2-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "kimi-2-6" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": 61.6, "coding": 59.8, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 110, "categoryRanks": { "agentic": 111, "coding": 55 }, "categoryRankingEligible": { "agentic": true, "coding": true, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "kimiClaw247": 46.9, "mcpAtlas": 76, "mcpMarkVerified": 81.1, "aaAgenticIndex": 30.28, "tau2Bench": 90.1, "gdpvalAaNormalized": 34.3, "gdpvalAa": 1187 }, "coding": { "kimiCodeBenchV2": 62, "programBench": 53.6, "mlsBenchLite": 35.1, "cursorBench32": 49.7, "aaCodingIndex": 60.76, "aaSciCode": 47.5, "openHarmonyBench": 52.1 }, "reasoning": { "lcr": 75, "critpt": 10 }, "multimodalGrounded": { "designArenaWebsite": 1287 }, "knowledge": { "artificialAnalysis": 43.02, "aaGpqaDiamond": 89.6, "aaHle": 35, "aaOmniscienceIndex": -10.2, "omniscienceAccuracy": 39.6, "omniscienceHallucinationRate": 82.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 63.1 }, "math": {} } }, { "slug": "lfm2-5-vl-1-6b-extract", "canonicalModelKey": "lfm2-5-vl-1-6b-extract", "model": "LFM2.5-VL-1.6B-Extract", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-1-6b-extract", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-1-6b-extract.md", "id": 256, "releaseDate": "2026-05-26", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-extract", "familyName": "LFM2.5-VL Extract", "variantType": "1-6b", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-1-6b-extract", "relatedModelKeys": [ "lfm2-5-vl-450m-extract", "lfm2-5-vl-450m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 8.5 }, "coding": { "aaSciCode": 3 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": { "liquidExtractJsonValidity": 99.6, "liquidExtractSchemaF1": 99.6, "liquidExtractVlmJudge": 90.6, "aaMmmuPro": 26.5 }, "knowledge": { "artificialAnalysis": 1, "aaGpqaDiamond": 28.9, "aaHle": 5.1, "aaOmniscienceIndex": -84.4, "omniscienceAccuracy": 5.8, "omniscienceHallucinationRate": 95.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.1 }, "math": {} } }, { "slug": "lfm2-5-vl-450m-extract", "canonicalModelKey": "lfm2-5-vl-450m-extract", "model": "LFM2.5-VL-450M-Extract", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-vl-450m-extract", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-vl-450m-extract.md", "id": 255, "releaseDate": "2026-05-26", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-vl-extract", "familyName": "LFM2.5-VL Extract", "variantType": "450m", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-vl-1-6b-extract", "relatedModelKeys": [ "lfm2-5-vl-1-6b-extract", "lfm2-5-vl-450m" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 3, "verifiedBenchmarkCount": 3, "rankableBenchmarkCount": 3, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "liquidExtractJsonValidity": 98.9, "liquidExtractSchemaF1": 98.8, "liquidExtractVlmJudge": 84.5 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "apodex-1-1-mini", "canonicalModelKey": "apodex-1-1-mini", "model": "Apodex 1.1 Mini", "creator": "Apodex", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/apodex-1-1-mini", "markdownUrl": "https://benchlm.ai/md/models/apodex-1-1-mini.md", "id": 407, "releaseDate": "2026-08-24", "market": null, "isRegional": false, "family": { "familyKey": "apodex-1-1", "familyName": "Apodex 1.1", "variantType": "mini-35b-a3b", "snapshotLabel": "35B-A3B", "baseFamilyModelKey": "apodex-1-1", "relatedModelKeys": [ "apodex-1-1" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "apexAgents": 27.7, "aaAgenticIndex": 36.64, "apexAgentsAa": 2.9, "gdpvalAaNormalized": 42.3, "gdpvalAa": 1347 }, "coding": { "aaCodingIndex": 60.76, "aaSciCode": 42.9 }, "reasoning": { "lcr": 74.7, "critpt": 4.6 }, "multimodalGrounded": { "aaMmmuPro": 79.2 }, "knowledge": { "frontierScienceResearch": 51.7, "artificialAnalysis": 44, "aaGpqaDiamond": 86.4, "aaHle": 34.1, "aaOmniscienceIndex": -21.9, "omniscienceAccuracy": 31.7, "omniscienceHallucinationRate": 78.4 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 231, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-1-codex", "familyName": "GPT-5.1-Codex", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-1-codex", "relatedModelKeys": [ "gpt-5-1-codex-max" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 119, "categoryRanks": { "agentic": 56, "coding": 88 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 2, "verifiedBenchmarkCount": 2, "rankableBenchmarkCount": 2, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 83, "gertLabs": 49.68, "jobBench": 26.2 }, "coding": { "vibeCodeBench": 13.115, "aaSciCode": 40.2 }, "reasoning": { "lcr": 69, "critpt": 5.7 }, "multimodalGrounded": { "aaMmmuPro": 72.5, "designArenaWebsite": 1180 }, "knowledge": { "artificialAnalysis": 35.6, "aaGpqaDiamond": 86, "aaHle": 25.7, "aaOmniscienceIndex": -6.5, "omniscienceAccuracy": 39.9, "omniscienceHallucinationRate": 77.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 70 }, "math": {} } }, { "slug": "claude-mythos-5-1", "canonicalModelKey": "claude-mythos-5-1", "model": "Claude Mythos 5.1", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-5-1", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-5-1.md", "id": 417, "releaseDate": "2026-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-mythos", "familyName": "Claude Mythos", "variantType": "restricted", "snapshotLabel": null, "baseFamilyModelKey": "claude-mythos-5-1", "relatedModelKeys": [ "claude-fable-5-1", "claude-mythos-5" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "claude-mythos-5" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "terminalBench4": 60.9 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "sakana-fugu-cyber", "canonicalModelKey": "sakana-fugu-cyber", "model": "Fugu Cyber", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu-cyber", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-cyber.md", "id": 290, "releaseDate": "2026-07-21", "market": null, "isRegional": false, "family": { "familyKey": "sakana-fugu", "familyName": "Sakana Fugu", "variantType": "cyber", "snapshotLabel": "Cyber", "baseFamilyModelKey": "sakana-fugu-ultra", "relatedModelKeys": [ "sakana-fugu-ultra", "sakana-fugu" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "cyberGym": 86.9, "ctiRealm": 72.1 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen3-8-max-preview", "canonicalModelKey": "qwen3-8-max-preview", "model": "Qwen3.8 Max Preview", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-8-max-preview", "markdownUrl": "https://benchlm.ai/md/models/qwen3-8-max-preview.md", "id": 285, "releaseDate": "2026-07-19", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-8-max", "familyName": "Qwen3.8 Max", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "qwen3-8-max", "relatedModelKeys": [ "qwen3-8-max", "qwen3-7-max", "qwen3-6-max-preview" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "qwen3-7-max" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 58.4, "gdpvalAaNormalized": 61, "gdpvalAa": 1721 }, "coding": { "aaCodingIndex": 71.81, "aaSciCode": 52.9, "openHarmonyBench": 56 }, "reasoning": { "lcr": 74.3, "critpt": 20 }, "multimodalGrounded": { "aaMmmuPro": 82.3, "designArenaWebsite": 1299 }, "knowledge": { "artificialAnalysis": 58.08, "aaGpqaDiamond": 92.7, "aaHle": 43, "aaOmniscienceIndex": 3.4, "omniscienceAccuracy": 31.9, "omniscienceHallucinationRate": 41.7 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b", "canonicalModelKey": "holo3-1-35b-a3b", "model": "Holo3.1-35B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b.md", "id": 242, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "holo3-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 79.3 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-4b", "canonicalModelKey": "holo3-1-4b", "model": "Holo3.1-4B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-4b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-4b.md", "id": 247, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-4b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 71 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-9b", "canonicalModelKey": "holo3-1-9b", "model": "Holo3.1-9B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-9b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-9b.md", "id": 246, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "9b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo2-8b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "androidWorld": 71 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 233, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-max", "familyName": "Qwen3 Max", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-max", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 145, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 74.3, "gertLabs": 43.74 }, "coding": { "vibeCodeBench": 3.506, "aaSciCode": 38.3 }, "reasoning": { "lcr": 48.3, "critpt": 0 }, "multimodalGrounded": { "designArenaWebsite": 1137 }, "knowledge": { "artificialAnalysis": 24.45, "aaGpqaDiamond": 76.4, "aaHle": 11.9, "aaOmniscienceIndex": -43.5, "omniscienceAccuracy": 24.4, "omniscienceHallucinationRate": 89.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.1 }, "math": {} } }, { "slug": "claude-mythos-preview", "canonicalModelKey": "claude-mythos-preview", "model": "Claude Mythos Preview", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-mythos-preview", "markdownUrl": "https://benchlm.ai/md/models/claude-mythos-preview.md", "id": 391, "releaseDate": "2026-04-07", "market": null, "isRegional": false, "family": { "familyKey": "claude-mythos", "familyName": "Claude Mythos", "variantType": "preview", "snapshotLabel": "preview", "baseFamilyModelKey": "claude-mythos-5", "relatedModelKeys": [ "claude-mythos-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "cyberGym": 83.1, "exploitGym": 17.5 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "external": { "exploitBench": 69, "sconePostCutoffSuccess": 100, "sconePostCutoffRevenueUsdM": 35 } } }, { "slug": "composer-2-fast", "canonicalModelKey": "composer-2-fast", "model": "Composer 2 Fast", "creator": "Cursor", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/composer-2-fast", "markdownUrl": "https://benchlm.ai/md/models/composer-2-fast.md", "id": 176, "releaseDate": "2026-03-19", "market": null, "isRegional": false, "family": { "familyKey": "composer", "familyName": "Composer", "variantType": "fast", "snapshotLabel": null, "baseFamilyModelKey": "composer-2", "relatedModelKeys": [ "composer-2" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "reactNativeEvals": 94.9 }, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 230, "releaseDate": "2025-11-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-opus-4-5", "familyName": "Claude Opus 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-opus-4-5", "relatedModelKeys": [ "claude-opus-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": 63.7, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 92, "categoryRanks": { "knowledge": 36 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": true, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 89.5 }, "coding": { "vibeCodeBench": 20.63, "aaSciCode": 49.5 }, "reasoning": { "lcr": 76, "critpt": 4.6 }, "multimodalGrounded": { "aaMmmuPro": 74, "designArenaWebsite": 1265 }, "knowledge": { "artificialAnalysis": 41.87, "aaGpqaDiamond": 86.6, "aaHle": 30.1, "aaOmniscienceIndex": 14, "omniscienceAccuracy": 46.6, "omniscienceHallucinationRate": 61, "aaMmluPro": 89.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 58 }, "math": {} } }, { "slug": "claude-haiku-4-5-thinking", "canonicalModelKey": "claude-haiku-4-5-thinking", "model": "Claude Haiku 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-haiku-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-haiku-4-5-thinking.md", "id": 232, "releaseDate": "2025-10-15", "market": null, "isRegional": false, "family": { "familyKey": "claude-haiku-4-5", "familyName": "Claude Haiku 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-haiku-4-5", "relatedModelKeys": [ "claude-haiku-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 11.393 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1140 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "claude-sonnet-4-5-thinking", "canonicalModelKey": "claude-sonnet-4-5-thinking", "model": "Claude Sonnet 4.5 Thinking", "creator": "Anthropic", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "200K", "contextWindowTokens": 200000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/claude-sonnet-4-5-thinking", "markdownUrl": "https://benchlm.ai/md/models/claude-sonnet-4-5-thinking.md", "id": 229, "releaseDate": "2025-09-01", "market": null, "isRegional": false, "family": { "familyKey": "claude-sonnet-4-5", "familyName": "Claude Sonnet 4.5", "variantType": "reasoning", "snapshotLabel": "thinking", "baseFamilyModelKey": "claude-sonnet-4-5", "relatedModelKeys": [ "claude-sonnet-4-5" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "vibeCodeBench": 22.621 }, "reasoning": {}, "multimodalGrounded": { "designArenaWebsite": 1208 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-235b-a22b", "canonicalModelKey": "holo2-235b-a22b", "model": "Holo2-235B-A22B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-235b-a22b", "markdownUrl": "https://benchlm.ai/md/models/holo2-235b-a22b.md", "id": 223, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "235b-a22b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-30b-a3b", "holo2-8b", "holo2-4b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 70.6 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-30b-a3b", "canonicalModelKey": "holo2-30b-a3b", "model": "Holo2-30B-A3B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/holo2-30b-a3b.md", "id": 224, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "30b-a3b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-8b", "holo2-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 66.1 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-4b", "canonicalModelKey": "holo2-4b", "model": "Holo2-4B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-4b", "markdownUrl": "https://benchlm.ai/md/models/holo2-4b.md", "id": 226, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-30b-a3b", "holo2-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 57.2 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo2-8b", "canonicalModelKey": "holo2-8b", "model": "Holo2-8B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo2-8b", "markdownUrl": "https://benchlm.ai/md/models/holo2-8b.md", "id": 225, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holo2", "familyName": "Holo2", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "holo2-235b-a22b", "relatedModelKeys": [ "holo2-235b-a22b", "holo2-30b-a3b", "holo2-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 1, "verifiedBenchmarkCount": 1, "rankableBenchmarkCount": 1, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": { "screenSpotPro": 58.9 }, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "muse-voice-transcribe", "canonicalModelKey": "muse-voice-transcribe", "model": "Muse Voice Transcribe", "creator": "Meta", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/muse-voice-transcribe", "markdownUrl": "https://benchlm.ai/md/models/muse-voice-transcribe.md", "id": 415, "releaseDate": "2026-09-01", "market": null, "isRegional": false, "family": { "familyKey": "muse-voice-transcribe", "familyName": "Muse Voice Transcribe", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "muse-voice-transcribe", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mercury-2-5-preview", "canonicalModelKey": "mercury-2-5-preview", "model": "Mercury 2.5 Preview", "creator": "Inception", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "260K", "contextWindowTokens": 260000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mercury-2-5-preview", "markdownUrl": "https://benchlm.ai/md/models/mercury-2-5-preview.md", "id": 414, "releaseDate": "2026-08-31", "market": null, "isRegional": false, "family": { "familyKey": "mercury-2-5", "familyName": "Mercury 2.5", "variantType": "preview", "snapshotLabel": "Preview", "baseFamilyModelKey": "mercury-2-5-preview", "relatedModelKeys": [ "mercury-2" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "mercury-2" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 9.46, "tau2Bench": 70.8, "gdpvalAaNormalized": 10.1, "gdpvalAa": 702 }, "coding": { "aaCodingIndex": 31.11, "aaSciCode": 38.7 }, "reasoning": { "lcr": 40.7, "critpt": 0.8 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 21.9, "aaGpqaDiamond": 77, "aaHle": 17.1, "aaOmniscienceIndex": -50.7, "omniscienceAccuracy": 21.2, "omniscienceHallucinationRate": 91.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 69.8 }, "math": {} } }, { "slug": "toast-1", "canonicalModelKey": "toast-1", "model": "Toast 1", "creator": "Mixedbread", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "131K", "contextWindowTokens": 131000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/toast-1", "markdownUrl": "https://benchlm.ai/md/models/toast-1.md", "id": 395, "releaseDate": "2026-08-13", "market": null, "isRegional": false, "family": { "familyKey": "toast-1", "familyName": "Toast 1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "toast-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-5-6-cyber", "canonicalModelKey": "gpt-5-6-cyber", "model": "GPT-5.6 Cyber", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-5-6-cyber", "markdownUrl": "https://benchlm.ai/md/models/gpt-5-6-cyber.md", "id": 390, "releaseDate": "2026-08-10", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5-6", "familyName": "GPT-5.6", "variantType": "cyber", "snapshotLabel": "daybreak-red", "baseFamilyModelKey": "gpt-5-6-sol", "relatedModelKeys": [ "gpt-5-6-sol" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "external": { "advancedCyberCompletionRateRed": 95 } } }, { "slug": "lfg-3", "canonicalModelKey": "lfg-3", "model": "LFG-3", "creator": "glenn2", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfg-3", "markdownUrl": "https://benchlm.ai/md/models/lfg-3.md", "id": 400, "releaseDate": "2026-08-06", "market": null, "isRegional": false, "family": { "familyKey": "lfg-3", "familyName": "LFG-3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lfg-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hark-handoff", "canonicalModelKey": "hark-handoff", "model": "Hark Handoff", "creator": "Hark", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hark-handoff", "markdownUrl": "https://benchlm.ai/md/models/hark-handoff.md", "id": 384, "releaseDate": "2026-08-05", "market": null, "isRegional": false, "family": { "familyKey": "hark-handoff", "familyName": "Hark Handoff", "variantType": "research-preview", "snapshotLabel": "Research Preview", "baseFamilyModelKey": "hark-handoff", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "macaw-v1", "canonicalModelKey": "macaw-v1", "model": "Macaw", "creator": "Bad Theory Labs", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/macaw-v1", "markdownUrl": "https://benchlm.ai/md/models/macaw-v1.md", "id": 387, "releaseDate": "2026-08-05", "market": null, "isRegional": false, "family": { "familyKey": "macaw", "familyName": "Macaw", "variantType": "v1", "snapshotLabel": "v1", "baseFamilyModelKey": "macaw-v1", "relatedModelKeys": [ "lfm2-5-2-6b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen3-7-flash", "canonicalModelKey": "qwen3-7-flash", "model": "Qwen3.7 Flash", "creator": "Alibaba", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen3-7-flash", "markdownUrl": "https://benchlm.ai/md/models/qwen3-7-flash.md", "id": 296, "releaseDate": "2026-07-27", "market": null, "isRegional": false, "family": { "familyKey": "qwen3-7-flash", "familyName": "Qwen3.7 Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen3-7-flash", "relatedModelKeys": [ "qwen3-7-max", "qwen3-7-plus", "qwen3-5-flash" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "sakana-fugu-ultra-v1-1", "canonicalModelKey": "sakana-fugu-ultra-v1-1", "model": "Sakana Fugu-Ultra v1.1", "creator": "Sakana AI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/sakana-fugu-ultra-v1-1", "markdownUrl": "https://benchlm.ai/md/models/sakana-fugu-ultra-v1-1.md", "id": 293, "releaseDate": "2026-07-24", "market": null, "isRegional": false, "family": { "familyKey": "sakana-fugu", "familyName": "Sakana Fugu", "variantType": "ultra", "snapshotLabel": "Ultra v1.1", "baseFamilyModelKey": "sakana-fugu", "relatedModelKeys": [ "sakana-fugu-ultra", "sakana-fugu", "sakana-fugu-cyber" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "sakana-fugu-ultra" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemini-3-5-flash-cyber", "canonicalModelKey": "gemini-3-5-flash-cyber", "model": "Gemini 3.5 Flash Cyber", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": null, "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-3-5-flash-cyber", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-5-flash-cyber.md", "id": 291, "releaseDate": "2026-07-21", "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-5-flash", "familyName": "Gemini 3.5 Flash", "variantType": "cyber", "snapshotLabel": "Cyber", "baseFamilyModelKey": "gemini-3-5-flash", "relatedModelKeys": [ "gemini-3-5-flash", "gemini-3-6-flash" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "cyberGym": 83.2 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "cosmos3-edge", "canonicalModelKey": "cosmos3-edge", "model": "Cosmos3-Edge", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/cosmos3-edge", "markdownUrl": "https://benchlm.ai/md/models/cosmos3-edge.md", "id": 289, "releaseDate": "2026-07-20", "market": null, "isRegional": false, "family": { "familyKey": "cosmos3", "familyName": "Cosmos 3", "variantType": "edge", "snapshotLabel": "4B", "baseFamilyModelKey": "cosmos3-edge", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 278, "releaseDate": "2026-07-02", "market": null, "isRegional": false, "family": { "familyKey": "agents-a1", "familyName": "Agents-A1", "variantType": "f16-gguf", "snapshotLabel": null, "baseFamilyModelKey": "agents-a1", "relatedModelKeys": [ "agents-a1", "agents-a1-fp8", "agents-a1-q4-k-m-gguf", "agents-a1-q8-0-gguf" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 59, "categoryRanks": { "agentic": 33 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 275, "releaseDate": "2026-07-02", "market": null, "isRegional": false, "family": { "familyKey": "agents-a1", "familyName": "Agents-A1", "variantType": "fp8", "snapshotLabel": null, "baseFamilyModelKey": "agents-a1", "relatedModelKeys": [ "agents-a1", "agents-a1-q4-k-m-gguf", "agents-a1-q8-0-gguf", "agents-a1-f16-gguf" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 60, "categoryRanks": { "agentic": 34 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 276, "releaseDate": "2026-07-02", "market": null, "isRegional": false, "family": { "familyKey": "agents-a1", "familyName": "Agents-A1", "variantType": "q4-k-m-gguf", "snapshotLabel": null, "baseFamilyModelKey": "agents-a1", "relatedModelKeys": [ "agents-a1", "agents-a1-fp8", "agents-a1-q8-0-gguf", "agents-a1-f16-gguf" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 61, "categoryRanks": { "agentic": 35 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 277, "releaseDate": "2026-07-02", "market": null, "isRegional": false, "family": { "familyKey": "agents-a1", "familyName": "Agents-A1", "variantType": "q8-0-gguf", "snapshotLabel": null, "baseFamilyModelKey": "agents-a1", "relatedModelKeys": [ "agents-a1", "agents-a1-fp8", "agents-a1-q4-k-m-gguf", "agents-a1-f16-gguf" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 62, "categoryRanks": { "agentic": 36 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfg-2", "canonicalModelKey": "lfg-2", "model": "LFG-2", "creator": "glenn2", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfg-2", "markdownUrl": "https://benchlm.ai/md/models/lfg-2.md", "id": 401, "releaseDate": "2026-06-30", "market": null, "isRegional": false, "family": { "familyKey": "lfg-2", "familyName": "LFG-2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lfg-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "longcat-2-0", "canonicalModelKey": "longcat-2-0", "model": "LongCat-2.0", "creator": "Meituan", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "1M", "contextWindowTokens": 1000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/longcat-2-0", "markdownUrl": "https://benchlm.ai/md/models/longcat-2-0.md", "id": 272, "releaseDate": "2026-06-30", "market": null, "isRegional": false, "family": { "familyKey": "longcat-2-0", "familyName": "LongCat-2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "longcat-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-colbert-350m", "canonicalModelKey": "lfm2-5-colbert-350m", "model": "LFM2.5-ColBERT-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-colbert-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-colbert-350m.md", "id": 261, "releaseDate": "2026-06-18", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-retrievers", "familyName": "LFM2.5 Retrievers", "variantType": "colbert", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-embedding-350m", "relatedModelKeys": [ "lfm2-5-embedding-350m", "lfm2-5-350m" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": { "nanoBeirMultilingual": 60.5, "mkqa11": 69.4 }, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-embedding-350m", "canonicalModelKey": "lfm2-5-embedding-350m", "model": "LFM2.5-Embedding-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-embedding-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-embedding-350m.md", "id": 260, "releaseDate": "2026-06-18", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-retrievers", "familyName": "LFM2.5 Retrievers", "variantType": "embedding", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-embedding-350m", "relatedModelKeys": [ "lfm2-5-colbert-350m", "lfm2-5-350m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": { "nanoBeirMultilingual": 57.7, "mkqa11": 69.1 }, "instructionFollowing": {}, "math": {} } }, { "slug": "mai-voice-2", "canonicalModelKey": "mai-voice-2", "model": "MAI-Voice-2", "creator": "Microsoft", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mai-voice-2", "markdownUrl": "https://benchlm.ai/md/models/mai-voice-2.md", "id": 308, "releaseDate": "2026-06-02", "market": null, "isRegional": false, "family": { "familyKey": "mai-voice", "familyName": "MAI-Voice", "variantType": "quality", "snapshotLabel": "Voice 2", "baseFamilyModelKey": "mai-voice-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-0-8b", "canonicalModelKey": "holo3-1-0-8b", "model": "Holo3.1-0.8B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-0-8b", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-0-8b.md", "id": 248, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "0-8b", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-fp8", "canonicalModelKey": "holo3-1-35b-a3b-fp8", "model": "Holo3.1-35B-A3B-FP8", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-fp8", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-fp8.md", "id": 243, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-fp8", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-nvfp4", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-gguf", "canonicalModelKey": "holo3-1-35b-a3b-gguf", "model": "Holo3.1-35B-A3B-GGUF", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-gguf", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-gguf.md", "id": 245, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-gguf", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-nvfp4", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holo3-1-35b-a3b-nvfp4", "canonicalModelKey": "holo3-1-35b-a3b-nvfp4", "model": "Holo3.1-35B-A3B-NVFP4", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holo3-1-35b-a3b-nvfp4", "markdownUrl": "https://benchlm.ai/md/models/holo3-1-35b-a3b-nvfp4.md", "id": 244, "releaseDate": "2026-06-01", "market": null, "isRegional": false, "family": { "familyKey": "holo3-1", "familyName": "Holo3.1", "variantType": "35b-a3b-nvfp4", "snapshotLabel": null, "baseFamilyModelKey": "holo3-1-35b-a3b", "relatedModelKeys": [ "holo3-1-35b-a3b", "holo3-1-35b-a3b-fp8", "holo3-1-35b-a3b-gguf", "holo3-1-9b", "holo3-1-4b", "holo3-1-0-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": "holo3-1-35b-a3b" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-1-2b-jp-202606", "canonicalModelKey": "lfm2-5-1-2b-jp-202606", "model": "LFM2.5-1.2B-JP-202606", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-1-2b-jp-202606", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-1-2b-jp-202606.md", "id": 254, "releaseDate": "2026-05-26", "market": "Japan", "isRegional": true, "family": { "familyKey": "lfm2-5-1-2b", "familyName": "LFM2.5-1.2B", "variantType": "jp-202606", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-1-2b-instruct", "relatedModelKeys": [ "lfm2-5-1-2b-instruct", "lfm2-5-1-2b-thinking" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hy-mt2-1-8b", "canonicalModelKey": "hy-mt2-1-8b", "model": "Hy-MT2-1.8B", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hy-mt2-1-8b", "markdownUrl": "https://benchlm.ai/md/models/hy-mt2-1-8b.md", "id": 404, "releaseDate": "2026-05-21", "market": null, "isRegional": false, "family": { "familyKey": "hy-mt2", "familyName": "Hy-MT2", "variantType": "1-8b", "snapshotLabel": "1.8B", "baseFamilyModelKey": "hy-mt2-30b-a3b", "relatedModelKeys": [ "hy-mt2-30b-a3b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hy-mt2-30b-a3b", "canonicalModelKey": "hy-mt2-30b-a3b", "model": "Hy-MT2-30B-A3B", "creator": "Tencent", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hy-mt2-30b-a3b", "markdownUrl": "https://benchlm.ai/md/models/hy-mt2-30b-a3b.md", "id": 403, "releaseDate": "2026-05-21", "market": null, "isRegional": false, "family": { "familyKey": "hy-mt2", "familyName": "Hy-MT2", "variantType": "30b-a3b", "snapshotLabel": "30B-A3B", "baseFamilyModelKey": "hy-mt2-30b-a3b", "relatedModelKeys": [ "hy-mt2-1-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-build-0-1", "markdownUrl": "https://benchlm.ai/md/models/grok-build-0-1.md", "id": 173, "releaseDate": "2026-05-20", "market": null, "isRegional": false, "family": { "familyKey": "grok-build", "familyName": "Grok Build", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-build-0-1", "relatedModelKeys": [ "grok-code-fast-1" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": { "agentic": 135, "coding": 121 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "gertLabs": 49.15 }, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "cartesia-sonic-3-5", "canonicalModelKey": "cartesia-sonic-3-5", "model": "Cartesia Sonic 3.5", "creator": "Cartesia", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/cartesia-sonic-3-5", "markdownUrl": "https://benchlm.ai/md/models/cartesia-sonic-3-5.md", "id": 311, "releaseDate": "2026-05-04", "market": null, "isRegional": false, "family": { "familyKey": "cartesia-sonic", "familyName": "Cartesia Sonic", "variantType": "v3.5", "snapshotLabel": "Stable alias", "baseFamilyModelKey": "cartesia-sonic-3-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hy-mt1-5-1-8b-1-25bit", "canonicalModelKey": "hy-mt1-5-1-8b-1-25bit", "model": "Hy-MT1.5-1.8B-1.25bit", "creator": "Tencent Hunyuan", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hy-mt1-5-1-8b-1-25bit", "markdownUrl": "https://benchlm.ai/md/models/hy-mt1-5-1-8b-1-25bit.md", "id": 237, "releaseDate": "2026-04-29", "market": null, "isRegional": false, "family": { "familyKey": "hy-mt1-5-1-8b", "familyName": "Hy-MT1.5-1.8B", "variantType": "1.25bit", "snapshotLabel": null, "baseFamilyModelKey": "hy-mt1-5-1-8b-1-25bit", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfg-1", "canonicalModelKey": "lfg-1", "model": "LFG-1", "creator": "glenn2", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfg-1", "markdownUrl": "https://benchlm.ai/md/models/lfg-1.md", "id": 324, "releaseDate": "2026-04-20", "market": null, "isRegional": false, "family": { "familyKey": "lfg-1", "familyName": "LFG-1", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lfg-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-tts", "canonicalModelKey": "grok-tts", "model": "Grok TTS", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-tts", "markdownUrl": "https://benchlm.ai/md/models/grok-tts.md", "id": 309, "releaseDate": "2026-04-17", "market": null, "isRegional": false, "family": { "familyKey": "grok-voice", "familyName": "Grok Voice", "variantType": "tts", "snapshotLabel": "TTS API", "baseFamilyModelKey": "grok-tts", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ternary-bonsai-1-7b", "canonicalModelKey": "ternary-bonsai-1-7b", "model": "Ternary Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-1-7b.md", "id": 109, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "1-7b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-8b", "ternary-bonsai-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ternary-bonsai-4b", "canonicalModelKey": "ternary-bonsai-4b", "model": "Ternary Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-4b.md", "id": 120, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-8b", "ternary-bonsai-1-7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ternary-bonsai-8b", "canonicalModelKey": "ternary-bonsai-8b", "model": "Ternary Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ternary-bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/ternary-bonsai-8b.md", "id": 80, "releaseDate": "2026-04-16", "market": null, "isRegional": false, "family": { "familyKey": "ternary-bonsai", "familyName": "Ternary Bonsai", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "ternary-bonsai-8b", "relatedModelKeys": [ "ternary-bonsai-4b", "ternary-bonsai-1-7b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemini-3-1-flash-tts-preview", "canonicalModelKey": "gemini-3-1-flash-tts-preview", "model": "Gemini 3.1 Flash TTS Preview", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-3-1-flash-tts-preview", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-tts-preview.md", "id": 313, "releaseDate": "2026-04-13", "market": null, "isRegional": false, "family": { "familyKey": "gemini-tts", "familyName": "Gemini TTS", "variantType": "flash-preview", "snapshotLabel": "3.1 Flash Preview", "baseFamilyModelKey": "gemini-2-5-flash-tts-preview", "relatedModelKeys": [ "gemini-2-5-flash-tts-preview", "gemini-2-5-pro-tts-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 161, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "e2b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 184, "categoryRanks": { "coding": 125 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 20.8, "gdpvalAaNormalized": 0, "gdpvalAa": 89 }, "coding": { "aaSciCode": 20.9, "aaCodingIndex": 7.23 }, "reasoning": { "lcr": 17, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 44.6 }, "knowledge": { "gpqa": 43.4, "mmluPro": 60, "artificialAnalysis": 9.53, "aaGpqaDiamond": 43.3, "aaHle": 4.8, "aaOmniscienceIndex": -23.6, "omniscienceAccuracy": 6.6, "omniscienceHallucinationRate": 32.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 38 }, "math": {} } }, { "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", "id": 139, "releaseDate": "2026-04-02", "market": null, "isRegional": false, "family": { "familyKey": "gemma-4", "familyName": "Gemma 4", "variantType": "e4b", "snapshotLabel": null, "baseFamilyModelKey": "gemma-4-31b", "relatedModelKeys": [ "gemma-4-31b", "gemma-4-26b-a4b", "gemma-4-e2b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 178, "categoryRanks": { "coding": 119 }, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 20.8, "gdpvalAaNormalized": 0, "gdpvalAa": 231 }, "coding": { "aaSciCode": 24.4, "aaCodingIndex": 9.39 }, "reasoning": { "lcr": 33, "critpt": 0.6 }, "multimodalGrounded": { "aaMmmuPro": 51.4 }, "knowledge": { "gpqa": 58.6, "mmluPro": 69.4, "artificialAnalysis": 12.18, "aaGpqaDiamond": 57.6, "aaHle": 3.8, "aaOmniscienceIndex": -19.7, "omniscienceAccuracy": 8.6, "omniscienceHallucinationRate": 30.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 44.2 }, "math": {} } }, { "slug": "bonsai-1-7b", "canonicalModelKey": "bonsai-1-7b", "model": "1-bit Bonsai 1.7B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-1-7b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-1-7b.md", "id": 160, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "1-7b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-8b", "bonsai-4b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "bonsai-4b", "canonicalModelKey": "bonsai-4b", "model": "1-bit Bonsai 4B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-4b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-4b.md", "id": 148, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "4b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-8b", "bonsai-1-7b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "bonsai-8b", "canonicalModelKey": "bonsai-8b", "model": "1-bit Bonsai 8B", "creator": "Prism ML", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bonsai-8b", "markdownUrl": "https://benchlm.ai/md/models/bonsai-8b.md", "id": 126, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "bonsai", "familyName": "1-bit Bonsai", "variantType": "8b", "snapshotLabel": null, "baseFamilyModelKey": "bonsai-8b", "relatedModelKeys": [ "bonsai-4b", "bonsai-1-7b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lfm2-5-350m", "canonicalModelKey": "lfm2-5-350m", "model": "LFM2.5-350M", "creator": "LiquidAI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lfm2-5-350m", "markdownUrl": "https://benchlm.ai/md/models/lfm2-5-350m.md", "id": 159, "releaseDate": "2026-03-31", "market": null, "isRegional": false, "family": { "familyKey": "lfm2-5-350m", "familyName": "LFM2.5-350M", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "lfm2-5-350m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "leanstral", "canonicalModelKey": "leanstral", "model": "Leanstral", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/leanstral", "markdownUrl": "https://benchlm.ai/md/models/leanstral.md", "id": 203, "releaseDate": "2026-03-15", "market": null, "isRegional": false, "family": { "familyKey": "leanstral", "familyName": "Leanstral", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "leanstral", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-4-20-multi-agent-beta", "canonicalModelKey": "grok-4-20-multi-agent-beta", "model": "Grok 4.20 Multi-agent", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "2M", "contextWindowTokens": 2000000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-4-20-multi-agent-beta", "markdownUrl": "https://benchlm.ai/md/models/grok-4-20-multi-agent-beta.md", "id": 8, "releaseDate": "2026-03-10", "market": null, "isRegional": false, "family": { "familyKey": "grok-4-20", "familyName": "Grok 4.20", "variantType": "multi-agent", "snapshotLabel": null, "baseFamilyModelKey": "grok-4-20-beta", "relatedModelKeys": [ "grok-4-20-beta" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 115, "releaseDate": "2026-03-06", "market": null, "isRegional": false, "family": { "familyKey": "sarvam-105b", "familyName": "Sarvam 105B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "sarvam-105b", "relatedModelKeys": [ "sarvam-30b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "sarvam-m" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 179, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 46.8 }, "coding": { "aaSciCode": 26.4 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 11.9, "aaGpqaDiamond": 73.8, "aaHle": 11, "aaOmniscienceIndex": -59.4, "omniscienceAccuracy": 17.6, "omniscienceHallucinationRate": 93.4 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 34.4 }, "math": {} } }, { "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", "id": 136, "releaseDate": "2026-03-06", "market": null, "isRegional": false, "family": { "familyKey": "sarvam-30b", "familyName": "Sarvam 30B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "sarvam-30b", "relatedModelKeys": [ "sarvam-105b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": "sarvam-m" }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 190, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 34.5 }, "coding": { "aaSciCode": 19.2 }, "reasoning": { "lcr": 0, "critpt": 0.3 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 6.39, "aaGpqaDiamond": 63.3, "aaHle": 7.5, "aaOmniscienceIndex": -71.5, "omniscienceAccuracy": 12.6, "omniscienceHallucinationRate": 96.3 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 26.5 }, "math": {} } }, { "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", "id": 106, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-medium-3", "familyName": "Mistral Medium 3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mistral-medium-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 177, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 24.3 }, "coding": { "aaSciCode": 33.1 }, "reasoning": { "lcr": 31.7, "critpt": 0 }, "multimodalGrounded": { "aaMmmuPro": 53, "designArenaWebsite": 1097 }, "knowledge": { "artificialAnalysis": 12.47, "aaGpqaDiamond": 57.8, "aaHle": 4.1, "aaOmniscienceIndex": -31.4, "omniscienceAccuracy": 18.3, "omniscienceHallucinationRate": 60.9 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 39.3 }, "math": {} } }, { "slug": "mistral-small-4-reasoning", "canonicalModelKey": "mistral-small-4-reasoning", "model": "Mistral Small 4 (Reasoning)", "creator": "Mistral", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mistral-small-4-reasoning", "markdownUrl": "https://benchlm.ai/md/models/mistral-small-4-reasoning.md", "id": 49, "releaseDate": "2026-02-20", "market": null, "isRegional": false, "family": { "familyKey": "mistral-small-4", "familyName": "Mistral Small 4", "variantType": "reasoning", "snapshotLabel": null, "baseFamilyModelKey": "mistral-small-4", "relatedModelKeys": [ "mistral-small-4" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "aaAgenticIndex": 4.63, "tau2Bench": 41.2, "gdpvalAaNormalized": 4.5, "gdpvalAa": 590 }, "coding": { "aaCodingIndex": 26.64, "aaSciCode": 38 }, "reasoning": { "lcr": 47.3, "critpt": 0.3 }, "multimodalGrounded": { "aaMmmuPro": 56.8 }, "knowledge": { "artificialAnalysis": 19.71, "aaGpqaDiamond": 76.9, "aaHle": 9.9, "aaOmniscienceIndex": -30.4, "omniscienceAccuracy": 21.7, "omniscienceHallucinationRate": 66.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 48.2 }, "math": {} } }, { "slug": "elevenlabs-eleven-v3", "canonicalModelKey": "elevenlabs-eleven-v3", "model": "ElevenLabs Eleven v3", "creator": "ElevenLabs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/elevenlabs-eleven-v3", "markdownUrl": "https://benchlm.ai/md/models/elevenlabs-eleven-v3.md", "id": 317, "releaseDate": "2026-02-02", "market": null, "isRegional": false, "family": { "familyKey": "elevenlabs-eleven", "familyName": "ElevenLabs Eleven", "variantType": "v3", "snapshotLabel": "Generally available", "baseFamilyModelKey": "elevenlabs-eleven-v3", "relatedModelKeys": [ "elevenlabs-eleven-v3-conversational" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "elevenlabs-eleven-v3-conversational", "canonicalModelKey": "elevenlabs-eleven-v3-conversational", "model": "ElevenLabs Eleven v3 Conversational", "creator": "ElevenLabs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/elevenlabs-eleven-v3-conversational", "markdownUrl": "https://benchlm.ai/md/models/elevenlabs-eleven-v3-conversational.md", "id": 412, "releaseDate": "2026-02-02", "market": null, "isRegional": false, "family": { "familyKey": "elevenlabs-eleven", "familyName": "ElevenLabs Eleven", "variantType": "v3-conversational", "snapshotLabel": "Conversational", "baseFamilyModelKey": "elevenlabs-eleven-v3", "relatedModelKeys": [ "elevenlabs-eleven-v3" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-realtime-1-5", "canonicalModelKey": "gpt-realtime-1-5", "model": "GPT Realtime 1.5", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-realtime-1-5", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-1-5.md", "id": 361, "releaseDate": "2026-02-01", "market": null, "isRegional": false, "family": { "familyKey": "gpt-realtime-1-5", "familyName": "GPT Realtime 1.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-realtime-1-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "inworld-tts-1-5-max", "canonicalModelKey": "inworld-tts-1-5-max", "model": "Inworld TTS-1.5 Max", "creator": "Inworld", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/inworld-tts-1-5-max", "markdownUrl": "https://benchlm.ai/md/models/inworld-tts-1-5-max.md", "id": 318, "releaseDate": "2026-01-21", "market": null, "isRegional": false, "family": { "familyKey": "inworld-tts", "familyName": "Inworld TTS", "variantType": "max", "snapshotLabel": "1.5 Max", "baseFamilyModelKey": "inworld-tts-1-5-max", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemini-2-5-flash-native-audio-preview-12-2025", "canonicalModelKey": "gemini-2-5-flash-native-audio-preview-12-2025", "model": "Gemini 2.5 Flash Native Audio Preview (12-2025)", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-2-5-flash-native-audio-preview-12-2025", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash-native-audio-preview-12-2025.md", "id": 355, "releaseDate": "2025-12-01", "market": null, "isRegional": false, "family": { "familyKey": "gemini-2-5-flash-native-audio-preview-12-2025", "familyName": "Gemini 2.5 Flash Native Audio Preview (12-2025)", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-2-5-flash-native-audio-preview-12-2025", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "granite-4-0-1b", "canonicalModelKey": "granite-4-0-1b", "model": "Granite-4.0-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-1b.md", "id": 157, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-1b", "familyName": "Granite 4.0 1B", "variantType": "dense", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-h-1b", "relatedModelKeys": [ "granite-4-0-h-1b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 22.8 }, "coding": { "aaSciCode": 8.7 }, "reasoning": { "lcr": 6, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 1.63, "aaGpqaDiamond": 28.1, "aaHle": 4.8, "aaOmniscienceIndex": -81.6, "omniscienceAccuracy": 6.2, "omniscienceHallucinationRate": 93.5 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 20.5 }, "math": {} } }, { "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", "id": 171, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-350m", "familyName": "Granite 4.0 350M", "variantType": "dense", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-350m", "relatedModelKeys": [ "granite-4-0-h-350m" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 201, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 13.2 }, "coding": { "aaSciCode": 0.9 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 1, "aaGpqaDiamond": 26.1, "aaHle": 5.5, "aaOmniscienceIndex": -69.3, "omniscienceAccuracy": 3.9, "omniscienceHallucinationRate": 76.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 15.9 }, "math": {} } }, { "slug": "granite-4-0-h-1b", "canonicalModelKey": "granite-4-0-h-1b", "model": "Granite-4.0-H-1B", "creator": "IBM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/granite-4-0-h-1b", "markdownUrl": "https://benchlm.ai/md/models/granite-4-0-h-1b.md", "id": 152, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-1b", "familyName": "Granite 4.0 1B", "variantType": "hybrid", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-h-1b", "relatedModelKeys": [ "granite-4-0-1b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 19.6 }, "coding": { "aaSciCode": 8.2 }, "reasoning": { "lcr": 6, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 2.25, "aaGpqaDiamond": 26.3, "aaHle": 5, "aaOmniscienceIndex": -72.3, "omniscienceAccuracy": 5.2, "omniscienceHallucinationRate": 81.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 26.2 }, "math": {} } }, { "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", "id": 172, "releaseDate": "2025-10-28", "market": null, "isRegional": false, "family": { "familyKey": "granite-4-0-350m", "familyName": "Granite 4.0 350M", "variantType": "hybrid", "snapshotLabel": null, "baseFamilyModelKey": "granite-4-0-350m", "relatedModelKeys": [ "granite-4-0-350m" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 202, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 14.6 }, "coding": { "aaSciCode": 1.7 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 1, "aaGpqaDiamond": 25.7, "aaHle": 6.4, "aaOmniscienceIndex": -80.9, "omniscienceAccuracy": 3.8, "omniscienceHallucinationRate": 88.1 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 17.6 }, "math": {} } }, { "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", "id": 194, "releaseDate": "2025-08-07", "market": null, "isRegional": false, "family": { "familyKey": "gpt-5", "familyName": "GPT-5", "variantType": "nano", "snapshotLabel": null, "baseFamilyModelKey": "gpt-5-high", "relatedModelKeys": [ "gpt-5-high", "gpt-5-medium", "gpt-5-mini" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 159, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 18, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "audio-flamingo-3-7b", "canonicalModelKey": "audio-flamingo-3-7b", "model": "Audio Flamingo 3 7B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/audio-flamingo-3-7b", "markdownUrl": "https://benchlm.ai/md/models/audio-flamingo-3-7b.md", "id": 364, "releaseDate": "2025-07-10", "market": null, "isRegional": false, "family": { "familyKey": "audio-flamingo-3-7b", "familyName": "Audio Flamingo 3 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "audio-flamingo-3-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemini-2-5-flash-tts-preview", "canonicalModelKey": "gemini-2-5-flash-tts-preview", "model": "Gemini 2.5 Flash TTS Preview", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-2-5-flash-tts-preview", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-flash-tts-preview.md", "id": 315, "releaseDate": "2025-05-20", "market": null, "isRegional": false, "family": { "familyKey": "gemini-tts", "familyName": "Gemini TTS", "variantType": "flash-preview", "snapshotLabel": "2.5 Flash Preview", "baseFamilyModelKey": "gemini-2-5-flash-tts-preview", "relatedModelKeys": [ "gemini-2-5-pro-tts-preview", "gemini-3-1-flash-tts-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gemini-2-5-pro-tts-preview", "canonicalModelKey": "gemini-2-5-pro-tts-preview", "model": "Gemini 2.5 Pro TTS Preview", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-2-5-pro-tts-preview", "markdownUrl": "https://benchlm.ai/md/models/gemini-2-5-pro-tts-preview.md", "id": 310, "releaseDate": "2025-05-20", "market": null, "isRegional": false, "family": { "familyKey": "gemini-tts", "familyName": "Gemini TTS", "variantType": "pro-preview", "snapshotLabel": "2.5 Pro Preview", "baseFamilyModelKey": "gemini-2-5-flash-tts-preview", "relatedModelKeys": [ "gemini-2-5-flash-tts-preview", "gemini-3-1-flash-tts-preview" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "kimi-audio-7b", "canonicalModelKey": "kimi-audio-7b", "model": "Kimi-Audio 7B", "creator": "Moonshot AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kimi-audio-7b", "markdownUrl": "https://benchlm.ai/md/models/kimi-audio-7b.md", "id": 325, "releaseDate": "2025-04-25", "market": null, "isRegional": false, "family": { "familyKey": "kimi-audio-7b", "familyName": "Kimi-Audio 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kimi-audio-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen2-5-omni-7b", "canonicalModelKey": "qwen2-5-omni-7b", "model": "Qwen2.5-Omni 7B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen2-5-omni-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen2-5-omni-7b.md", "id": 363, "releaseDate": "2025-03-26", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-5-omni-7b", "familyName": "Qwen2.5-Omni 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-5-omni-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-4o-mini-tts", "canonicalModelKey": "gpt-4o-mini-tts", "model": "GPT-4o mini TTS", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "2K", "contextWindowTokens": 2000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-4o-mini-tts", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini-tts.md", "id": 314, "releaseDate": "2025-03-20", "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o-mini-tts", "familyName": "GPT-4o mini TTS", "variantType": "base", "snapshotLabel": "Current alias", "baseFamilyModelKey": "gpt-4o-mini-tts", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "phi-4-multimodal-instruct", "canonicalModelKey": "phi-4-multimodal-instruct", "model": "Phi-4 Multimodal Instruct", "creator": "Microsoft", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/phi-4-multimodal-instruct", "markdownUrl": "https://benchlm.ai/md/models/phi-4-multimodal-instruct.md", "id": 333, "releaseDate": "2025-03-03", "market": null, "isRegional": false, "family": { "familyKey": "phi-4-multimodal-instruct", "familyName": "Phi-4 Multimodal Instruct", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "phi-4-multimodal-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 11 }, "reasoning": {}, "multimodalGrounded": { "aaMmmuPro": 14.5 }, "knowledge": { "artificialAnalysis": 4.2, "aaGpqaDiamond": 31.5, "aaHle": 5 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "baichuan-audio", "canonicalModelKey": "baichuan-audio", "model": "Baichuan-Audio", "creator": "Baichuan", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/baichuan-audio", "markdownUrl": "https://benchlm.ai/md/models/baichuan-audio.md", "id": 330, "releaseDate": "2025-02-24", "market": null, "isRegional": false, "family": { "familyKey": "baichuan-audio", "familyName": "Baichuan-Audio", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "baichuan-audio", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-3-mini", "canonicalModelKey": "grok-3-mini", "model": "Grok 3 Mini", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-3-mini", "markdownUrl": "https://benchlm.ai/md/models/grok-3-mini.md", "id": 134, "releaseDate": "2025-02-19", "market": null, "isRegional": false, "family": { "familyKey": "grok-3-mini", "familyName": "Grok 3 Mini", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-3-mini", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "step-audio", "canonicalModelKey": "step-audio", "model": "Step-Audio", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/step-audio", "markdownUrl": "https://benchlm.ai/md/models/step-audio.md", "id": 340, "releaseDate": "2025-02-17", "market": null, "isRegional": false, "family": { "familyKey": "step-audio", "familyName": "Step-Audio", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-audio", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ola-omni", "canonicalModelKey": "ola-omni", "model": "Ola", "creator": "Ola-Omni", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ola-omni", "markdownUrl": "https://benchlm.ai/md/models/ola-omni.md", "id": 334, "releaseDate": "2025-02-06", "market": null, "isRegional": false, "family": { "familyKey": "ola-omni", "familyName": "Ola", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ola-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "baichuan-omni-1-5", "canonicalModelKey": "baichuan-omni-1-5", "model": "Baichuan-Omni 1.5", "creator": "Baichuan", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/baichuan-omni-1-5", "markdownUrl": "https://benchlm.ai/md/models/baichuan-omni-1-5.md", "id": 328, "releaseDate": "2025-01-26", "market": null, "isRegional": false, "family": { "familyKey": "baichuan-omni-1-5", "familyName": "Baichuan-Omni 1.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "baichuan-omni-1-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "minicpm-o-2-6", "canonicalModelKey": "minicpm-o-2-6", "model": "MiniCPM-o 2.6", "creator": "OpenBMB", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/minicpm-o-2-6", "markdownUrl": "https://benchlm.ai/md/models/minicpm-o-2-6.md", "id": 329, "releaseDate": "2025-01-24", "market": null, "isRegional": false, "family": { "familyKey": "minicpm-o-2-6", "familyName": "MiniCPM-o 2.6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "minicpm-o-2-6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 217, "releaseDate": "2025-01-20", "market": null, "isRegional": false, "family": { "familyKey": "deepseek-r1-distill", "familyName": "DeepSeek R1 Distill", "variantType": "qwen-32b", "snapshotLabel": null, "baseFamilyModelKey": "deepseek-r1-distill-qwen-32b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 182, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": { "aaSciCode": 37.6 }, "reasoning": { "lcr": 8.3 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 10.96, "aaGpqaDiamond": 61.5, "aaHle": 4.6 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 22.9 }, "math": {} } }, { "slug": "vita-1-5", "canonicalModelKey": "vita-1-5", "model": "VITA 1.5", "creator": "VITA-MLLM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/vita-1-5", "markdownUrl": "https://benchlm.ai/md/models/vita-1-5.md", "id": 332, "releaseDate": "2025-01-03", "market": null, "isRegional": false, "family": { "familyKey": "vita-1-5", "familyName": "VITA 1.5", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "vita-1-5", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "slam-omni", "canonicalModelKey": "slam-omni", "model": "SLAM-Omni", "creator": "X-LANCE", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/slam-omni", "markdownUrl": "https://benchlm.ai/md/models/slam-omni.md", "id": 347, "releaseDate": "2024-12-20", "market": null, "isRegional": false, "family": { "familyKey": "slam-omni", "familyName": "SLAM-Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "slam-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "meralion-audiollm", "canonicalModelKey": "meralion-audiollm", "model": "MERaLiON-AudioLLM", "creator": "AI Singapore", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/meralion-audiollm", "markdownUrl": "https://benchlm.ai/md/models/meralion-audiollm.md", "id": 331, "releaseDate": "2024-12-13", "market": null, "isRegional": false, "family": { "familyKey": "meralion-audiollm", "familyName": "MERaLiON-AudioLLM", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "meralion-audiollm", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lyra-base", "canonicalModelKey": "lyra-base", "model": "Lyra Base", "creator": "DVL Lab", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lyra-base", "markdownUrl": "https://benchlm.ai/md/models/lyra-base.md", "id": 335, "releaseDate": "2024-12-12", "market": null, "isRegional": false, "family": { "familyKey": "lyra-base", "familyName": "Lyra Base", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lyra-base", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lyra-mini", "canonicalModelKey": "lyra-mini", "model": "Lyra Mini", "creator": "DVL Lab", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lyra-mini", "markdownUrl": "https://benchlm.ai/md/models/lyra-mini.md", "id": 343, "releaseDate": "2024-12-12", "market": null, "isRegional": false, "family": { "familyKey": "lyra-mini", "familyName": "Lyra Mini", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "lyra-mini", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "glm-4-voice", "canonicalModelKey": "glm-4-voice", "model": "GLM-4-Voice", "creator": "Zhipu AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-4-voice", "markdownUrl": "https://benchlm.ai/md/models/glm-4-voice.md", "id": 338, "releaseDate": "2024-12-03", "market": null, "isRegional": false, "family": { "familyKey": "glm-4-voice", "familyName": "GLM-4-Voice", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-4-voice", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "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", "id": 141, "releaseDate": "2024-12-01", "market": null, "isRegional": false, "family": { "familyKey": "o1", "familyName": "o1", "variantType": "pro", "snapshotLabel": null, "baseFamilyModelKey": "o1", "relatedModelKeys": [ "o1", "o1-preview" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": 162, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": { "gpqa": 79, "artificialAnalysis": 19.12 }, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ichigo", "canonicalModelKey": "ichigo", "model": "Ichigo", "creator": "Jan", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ichigo", "markdownUrl": "https://benchlm.ai/md/models/ichigo.md", "id": 342, "releaseDate": "2024-10-20", "market": null, "isRegional": false, "family": { "familyKey": "ichigo", "familyName": "Ichigo", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ichigo", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mini-omni2", "canonicalModelKey": "mini-omni2", "model": "Mini-Omni2", "creator": "gpt-omni", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mini-omni2", "markdownUrl": "https://benchlm.ai/md/models/mini-omni2.md", "id": 348, "releaseDate": "2024-10-15", "market": null, "isRegional": false, "family": { "familyKey": "mini-omni2", "familyName": "Mini-Omni2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mini-omni2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "diva-llama-3-v0-8b", "canonicalModelKey": "diva-llama-3-v0-8b", "model": "DiVA Llama 3 8B", "creator": "DiVA authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/diva-llama-3-v0-8b", "markdownUrl": "https://benchlm.ai/md/models/diva-llama-3-v0-8b.md", "id": 337, "releaseDate": "2024-10-03", "market": null, "isRegional": false, "family": { "familyKey": "diva-llama-3-v0-8b", "familyName": "DiVA Llama 3 8B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "diva-llama-3-v0-8b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "moshi-7b", "canonicalModelKey": "moshi-7b", "model": "Moshi 7B", "creator": "Kyutai", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/moshi-7b", "markdownUrl": "https://benchlm.ai/md/models/moshi-7b.md", "id": 371, "releaseDate": "2024-09-17", "market": null, "isRegional": false, "family": { "familyKey": "moshi-7b", "familyName": "Moshi 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "moshi-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "llama-omni", "canonicalModelKey": "llama-omni", "model": "LLaMA-Omni", "creator": "ICTNLP", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/llama-omni", "markdownUrl": "https://benchlm.ai/md/models/llama-omni.md", "id": 345, "releaseDate": "2024-09-10", "market": null, "isRegional": false, "family": { "familyKey": "llama-omni", "familyName": "LLaMA-Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "llama-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mini-omni", "canonicalModelKey": "mini-omni", "model": "Mini-Omni 0.5B", "creator": "gpt-omni", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mini-omni", "markdownUrl": "https://benchlm.ai/md/models/mini-omni.md", "id": 349, "releaseDate": "2024-08-29", "market": null, "isRegional": false, "family": { "familyKey": "mini-omni", "familyName": "Mini-Omni 0.5B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mini-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "vita-1-0", "canonicalModelKey": "vita-1-0", "model": "VITA 1.0", "creator": "VITA-MLLM", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/vita-1-0", "markdownUrl": "https://benchlm.ai/md/models/vita-1-0.md", "id": 346, "releaseDate": "2024-08-09", "market": null, "isRegional": false, "family": { "familyKey": "vita-1-0", "familyName": "VITA 1.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "vita-1-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen2-audio-7b-instruct", "canonicalModelKey": "qwen2-audio-7b-instruct", "model": "Qwen2-Audio 7B Instruct", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen2-audio-7b-instruct", "markdownUrl": "https://benchlm.ai/md/models/qwen2-audio-7b-instruct.md", "id": 339, "releaseDate": "2024-07-15", "market": null, "isRegional": false, "family": { "familyKey": "qwen2-audio-7b-instruct", "familyName": "Qwen2-Audio 7B Instruct", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen2-audio-7b-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "skt-ax", "canonicalModelKey": "skt-ax", "model": "A.X series", "creator": "SK Telecom", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/skt-ax", "markdownUrl": "https://benchlm.ai/md/models/skt-ax.md", "id": 212, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "skt-ax", "familyName": "A.X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "skt-ax", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "amazon-nova-2-sonic", "canonicalModelKey": "amazon-nova-2-sonic", "model": "Amazon Nova 2 Sonic", "creator": "Amazon", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/amazon-nova-2-sonic", "markdownUrl": "https://benchlm.ai/md/models/amazon-nova-2-sonic.md", "id": 358, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "amazon-nova-2-sonic", "familyName": "Amazon Nova 2 Sonic", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "amazon-nova-2-sonic", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "bland-speech-v3", "canonicalModelKey": "bland-speech-v3", "model": "Bland Speech v3", "creator": "Bland AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/bland-speech-v3", "markdownUrl": "https://benchlm.ai/md/models/bland-speech-v3.md", "id": 307, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "bland-speech", "familyName": "Bland Speech", "variantType": "v3", "snapshotLabel": "v3", "baseFamilyModelKey": "bland-speech-v3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "blsp-7b", "canonicalModelKey": "blsp-7b", "model": "BLSP 7B", "creator": "BLSP authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/blsp-7b", "markdownUrl": "https://benchlm.ai/md/models/blsp-7b.md", "id": 373, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "blsp-7b", "familyName": "BLSP 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "blsp-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "cartesia-ink-whisper", "canonicalModelKey": "cartesia-ink-whisper", "model": "Cartesia Ink-Whisper", "creator": "Cartesia", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/cartesia-ink-whisper", "markdownUrl": "https://benchlm.ai/md/models/cartesia-ink-whisper.md", "id": 377, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "cartesia-ink-whisper", "familyName": "Cartesia Ink-Whisper", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "cartesia-ink-whisper", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "cartesia-sonic-3", "canonicalModelKey": "cartesia-sonic-3", "model": "Cartesia Sonic 3", "creator": "Cartesia", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/cartesia-sonic-3", "markdownUrl": "https://benchlm.ai/md/models/cartesia-sonic-3.md", "id": 378, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "cartesia-sonic-3", "familyName": "Cartesia Sonic 3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "cartesia-sonic-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "cohere-transcribe-03-2026", "canonicalModelKey": "cohere-transcribe-03-2026", "model": "Cohere Transcribe 03-2026", "creator": "Cohere", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/cohere-transcribe-03-2026", "markdownUrl": "https://benchlm.ai/md/models/cohere-transcribe-03-2026.md", "id": 375, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "cohere-transcribe-03-2026", "familyName": "Cohere Transcribe 03-2026", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "cohere-transcribe-03-2026", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "dbrx-instruct", "canonicalModelKey": "dbrx-instruct", "model": "DBRX Instruct", "creator": "Databricks", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/dbrx-instruct", "markdownUrl": "https://benchlm.ai/md/models/dbrx-instruct.md", "id": 154, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "dbrx", "familyName": "DBRX", "variantType": "instruct", "snapshotLabel": null, "baseFamilyModelKey": "dbrx-instruct", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepgram-aura-2", "canonicalModelKey": "deepgram-aura-2", "model": "Deepgram Aura-2", "creator": "Deepgram", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepgram-aura-2", "markdownUrl": "https://benchlm.ai/md/models/deepgram-aura-2.md", "id": 382, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepgram-aura-2", "familyName": "Deepgram Aura-2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepgram-aura-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "deepgram-nova-3", "canonicalModelKey": "deepgram-nova-3", "model": "Deepgram Nova-3", "creator": "Deepgram", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/deepgram-nova-3", "markdownUrl": "https://benchlm.ai/md/models/deepgram-nova-3.md", "id": 379, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "deepgram-nova-3", "familyName": "Deepgram Nova-3", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "deepgram-nova-3", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "dna-1-0", "canonicalModelKey": "dna-1-0", "model": "DNA 1.0 8B", "creator": "Community", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/dna-1-0", "markdownUrl": "https://benchlm.ai/md/models/dna-1-0.md", "id": 215, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "dna-1-0", "familyName": "DNA 1.0", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "dna-1-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "exaone-4-0-1-2b", "canonicalModelKey": "exaone-4-0-1-2b", "model": "Exaone 4.0 1.2B", "creator": "LG AI Research", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/exaone-4-0-1-2b", "markdownUrl": "https://benchlm.ai/md/models/exaone-4-0-1-2b.md", "id": 205, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-4", "familyName": "Exaone 4.0", "variantType": "1-2b", "snapshotLabel": null, "baseFamilyModelKey": "exaone-4-0-32b", "relatedModelKeys": [ "exaone-4-0-32b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 20.5 }, "coding": { "aaSciCode": 7.4 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 2.37, "aaGpqaDiamond": 42.4, "aaHle": 5.7, "aaOmniscienceIndex": -82.1, "omniscienceAccuracy": 5, "omniscienceHallucinationRate": 91.7 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 25.3 }, "math": {}, "korean": {} } }, { "slug": "gemini-3-1-flash-live-preview", "canonicalModelKey": "gemini-3-1-flash-live-preview", "model": "Gemini 3.1 Flash Live Preview", "creator": "Google", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gemini-3-1-flash-live-preview", "markdownUrl": "https://benchlm.ai/md/models/gemini-3-1-flash-live-preview.md", "id": 354, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gemini-3-1-flash-live-preview", "familyName": "Gemini 3.1 Flash Live Preview", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gemini-3-1-flash-live-preview", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "glm-realtime-air", "canonicalModelKey": "glm-realtime-air", "model": "GLM Realtime Air", "creator": "Zhipu AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-realtime-air", "markdownUrl": "https://benchlm.ai/md/models/glm-realtime-air.md", "id": 360, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "glm-realtime-air", "familyName": "GLM Realtime Air", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-realtime-air", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "glm-realtime-flash", "canonicalModelKey": "glm-realtime-flash", "model": "GLM Realtime Flash", "creator": "Zhipu AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/glm-realtime-flash", "markdownUrl": "https://benchlm.ai/md/models/glm-realtime-flash.md", "id": 359, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "glm-realtime-flash", "familyName": "GLM Realtime Flash", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "glm-realtime-flash", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-realtime", "canonicalModelKey": "gpt-realtime", "model": "GPT Realtime", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-realtime", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime.md", "id": 356, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gpt-realtime", "familyName": "GPT Realtime", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-realtime", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-realtime-2", "canonicalModelKey": "gpt-realtime-2", "model": "GPT Realtime 2", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-realtime-2", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-2.md", "id": 357, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gpt-realtime-2", "familyName": "GPT Realtime 2", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-realtime-2", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-realtime-mini", "canonicalModelKey": "gpt-realtime-mini", "model": "GPT Realtime mini", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-realtime-mini", "markdownUrl": "https://benchlm.ai/md/models/gpt-realtime-mini.md", "id": 362, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gpt-realtime-mini", "familyName": "GPT Realtime mini", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-realtime-mini", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-4o-audio", "canonicalModelKey": "gpt-4o-audio", "model": "GPT-4o Audio", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-4o-audio", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-audio.md", "id": 321, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o-audio", "familyName": "GPT-4o Audio", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o-audio", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "gpt-4o-mini-audio", "canonicalModelKey": "gpt-4o-mini-audio", "model": "GPT-4o mini Audio", "creator": "OpenAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/gpt-4o-mini-audio", "markdownUrl": "https://benchlm.ai/md/models/gpt-4o-mini-audio.md", "id": 322, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "gpt-4o-mini-audio", "familyName": "GPT-4o mini Audio", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "gpt-4o-mini-audio", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-realtime", "canonicalModelKey": "grok-realtime", "model": "Grok Realtime", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-realtime", "markdownUrl": "https://benchlm.ai/md/models/grok-realtime.md", "id": 352, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "grok-realtime", "familyName": "Grok Realtime", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-realtime", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-voice-think-fast-1-0", "canonicalModelKey": "grok-voice-think-fast-1-0", "model": "Grok Voice Think Fast 1.0", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-voice-think-fast-1-0", "markdownUrl": "https://benchlm.ai/md/models/grok-voice-think-fast-1-0.md", "id": 353, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "grok-voice-think-fast-1-0", "familyName": "Grok Voice Think Fast 1.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-voice-think-fast-1-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "grok-voice-think-fast-2-0", "canonicalModelKey": "grok-voice-think-fast-2-0", "model": "Grok Voice Think Fast 2.0", "creator": "xAI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/grok-voice-think-fast-2-0", "markdownUrl": "https://benchlm.ai/md/models/grok-voice-think-fast-2-0.md", "id": 350, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "grok-voice-think-fast-2-0", "familyName": "Grok Voice Think Fast 2.0", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "grok-voice-think-fast-2-0", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "holotron-12b", "canonicalModelKey": "holotron-12b", "model": "Holotron-12B", "creator": "H Company", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/holotron-12b", "markdownUrl": "https://benchlm.ai/md/models/holotron-12b.md", "id": 222, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "holotron", "familyName": "Holotron", "variantType": "12b", "snapshotLabel": null, "baseFamilyModelKey": "holotron-12b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "hyperclova-x-dash", "canonicalModelKey": "hyperclova-x-dash", "model": "HyperClova X Dash", "creator": "Naver Cloud", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hyperclova-x-dash", "markdownUrl": "https://benchlm.ai/md/models/hyperclova-x-dash.md", "id": 207, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "hyperclova", "familyName": "HyperClova X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "hyperclova-x-think", "relatedModelKeys": [ "hyperclova-x-think", "hyperclova-x-seed-8b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "hyperclova-x-think", "canonicalModelKey": "hyperclova-x-think", "model": "HyperClova X Think 32B", "creator": "Naver Cloud", "sourceType": "Open Weight", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/hyperclova-x-think", "markdownUrl": "https://benchlm.ai/md/models/hyperclova-x-think.md", "id": 206, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "hyperclova", "familyName": "HyperClova X", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "hyperclova-x-think", "relatedModelKeys": [ "hyperclova-x-dash", "hyperclova-x-seed-8b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "k-exaone", "canonicalModelKey": "k-exaone", "model": "K-Exaone", "creator": "LG AI Research", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "256K", "contextWindowTokens": 256000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/k-exaone", "markdownUrl": "https://benchlm.ai/md/models/k-exaone.md", "id": 131, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "exaone-frontier", "familyName": "K-Exaone", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "k-exaone", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 74.3, "gdpvalAaNormalized": 4.6, "gdpvalAa": 592 }, "coding": { "aaSciCode": 35.6, "aaCodingIndex": 32.11 }, "reasoning": { "lcr": 59.3, "critpt": 1.1 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 22.47, "aaGpqaDiamond": 78.3, "aaHle": 13.9, "aaOmniscienceIndex": -58, "omniscienceAccuracy": 16.4, "omniscienceHallucinationRate": 88.8 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 64.7 }, "math": {}, "korean": {} } }, { "slug": "kalpa-tts-beta-v0-1", "canonicalModelKey": "kalpa-tts-beta-v0-1", "model": "Kalpa TTS Beta v0.1", "creator": "Kalpa Labs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kalpa-tts-beta-v0-1", "markdownUrl": "https://benchlm.ai/md/models/kalpa-tts-beta-v0-1.md", "id": 418, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "kalpa-tts", "familyName": "Kalpa TTS", "variantType": "beta-v0-1", "snapshotLabel": "Beta v0.1", "baseFamilyModelKey": "kalpa-tts-beta-v0-1", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "kanana-essence", "canonicalModelKey": "kanana-essence", "model": "Kanana Essence", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-essence", "markdownUrl": "https://benchlm.ai/md/models/kanana-essence.md", "id": 210, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-flag", "kanana-nano" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kanana-flag", "canonicalModelKey": "kanana-flag", "model": "Kanana Flag", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-flag", "markdownUrl": "https://benchlm.ai/md/models/kanana-flag.md", "id": 209, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-essence", "kanana-nano" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kanana-nano", "canonicalModelKey": "kanana-nano", "model": "Kanana Nano", "creator": "Kakao", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kanana-nano", "markdownUrl": "https://benchlm.ai/md/models/kanana-nano.md", "id": 211, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "kanana", "familyName": "Kanana", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "kanana-flag", "relatedModelKeys": [ "kanana-flag", "kanana-essence" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "kokoro-82m", "canonicalModelKey": "kokoro-82m", "model": "Kokoro 82M", "creator": "hexgrad", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/kokoro-82m", "markdownUrl": "https://benchlm.ai/md/models/kokoro-82m.md", "id": 380, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "kokoro-82m", "familyName": "Kokoro 82M", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "kokoro-82m", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "lightning-v3-1-pro", "canonicalModelKey": "lightning-v3-1-pro", "model": "Lightning v3.1 Pro", "creator": "Smallest AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/lightning-v3-1-pro", "markdownUrl": "https://benchlm.ai/md/models/lightning-v3-1-pro.md", "id": 316, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "smallest-lightning", "familyName": "Smallest AI Lightning", "variantType": "pro", "snapshotLabel": "v3.1 Pro", "baseFamilyModelKey": "lightning-v3-1-pro", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "mair-hub-0-5b-omni", "canonicalModelKey": "mair-hub-0-5b-omni", "model": "Mair-hub 0.5B Omni", "creator": "Mair Hub", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/mair-hub-0-5b-omni", "markdownUrl": "https://benchlm.ai/md/models/mair-hub-0-5b-omni.md", "id": 344, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "mair-hub-0-5b-omni", "familyName": "Mair-hub 0.5B Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "mair-hub-0-5b-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "megrez-3b-omni", "canonicalModelKey": "megrez-3b-omni", "model": "Megrez-3B-Omni", "creator": "Infinigence AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/megrez-3b-omni", "markdownUrl": "https://benchlm.ai/md/models/megrez-3b-omni.md", "id": 341, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "megrez-3b-omni", "familyName": "Megrez-3B-Omni", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "megrez-3b-omni", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "minimax-speech-02-hd", "canonicalModelKey": "minimax-speech-02-hd", "model": "MiniMax Speech-02 HD", "creator": "MiniMax", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/minimax-speech-02-hd", "markdownUrl": "https://benchlm.ai/md/models/minimax-speech-02-hd.md", "id": 312, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "minimax-speech", "familyName": "MiniMax Speech", "variantType": "hd", "snapshotLabel": "Speech-02 HD", "baseFamilyModelKey": "minimax-speech-02-hd", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "next-gpt-7b", "canonicalModelKey": "next-gpt-7b", "model": "NExT-GPT 7B", "creator": "NExT-GPT authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/next-gpt-7b", "markdownUrl": "https://benchlm.ai/md/models/next-gpt-7b.md", "id": 366, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "next-gpt-7b", "familyName": "NExT-GPT 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "next-gpt-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "orion-mistral-24b", "canonicalModelKey": "orion-mistral-24b", "model": "OriOn-Mistral-24B", "creator": "LightOn", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "344K", "contextWindowTokens": 344000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/orion-mistral-24b", "markdownUrl": "https://benchlm.ai/md/models/orion-mistral-24b.md", "id": 221, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "orion", "familyName": "OriOn", "variantType": "mistral-24b", "snapshotLabel": null, "baseFamilyModelKey": "orion-qwen-32b", "relatedModelKeys": [ "orion-qwen-32b" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "orion-qwen-32b", "canonicalModelKey": "orion-qwen-32b", "model": "OriOn-Qwen-32B", "creator": "LightOn", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "262K", "contextWindowTokens": 262000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/orion-qwen-32b", "markdownUrl": "https://benchlm.ai/md/models/orion-qwen-32b.md", "id": 220, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "orion", "familyName": "OriOn", "variantType": "qwen-32b", "snapshotLabel": null, "baseFamilyModelKey": "orion-qwen-32b", "relatedModelKeys": [ "orion-mistral-24b" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "pandagpt-7b", "canonicalModelKey": "pandagpt-7b", "model": "PandaGPT 7B", "creator": "PandaGPT authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pandagpt-7b", "markdownUrl": "https://benchlm.ai/md/models/pandagpt-7b.md", "id": 365, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "pandagpt-7b", "familyName": "PandaGPT 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "pandagpt-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "parakeet-ctc-1-1b", "canonicalModelKey": "parakeet-ctc-1-1b", "model": "Parakeet CTC 1.1B", "creator": "NVIDIA", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/parakeet-ctc-1-1b", "markdownUrl": "https://benchlm.ai/md/models/parakeet-ctc-1-1b.md", "id": 383, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "parakeet-ctc-1-1b", "familyName": "Parakeet CTC 1.1B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "parakeet-ctc-1-1b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "pharia-1-llm-7b-control", "canonicalModelKey": "pharia-1-llm-7b-control", "model": "Pharia-1-LLM-7B-control", "creator": "Aleph Alpha", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pharia-1-llm-7b-control", "markdownUrl": "https://benchlm.ai/md/models/pharia-1-llm-7b-control.md", "id": 218, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "pharia-1-llm-7b", "familyName": "Pharia-1-LLM-7B", "variantType": "control", "snapshotLabel": null, "baseFamilyModelKey": "pharia-1-llm-7b-control", "relatedModelKeys": [ "pharia-1-llm-7b-control-aligned" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "pharia-1-llm-7b-control-aligned", "canonicalModelKey": "pharia-1-llm-7b-control-aligned", "model": "Pharia-1-LLM-7B-control-aligned", "creator": "Aleph Alpha", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "8K", "contextWindowTokens": 8000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/pharia-1-llm-7b-control-aligned", "markdownUrl": "https://benchlm.ai/md/models/pharia-1-llm-7b-control-aligned.md", "id": 219, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "pharia-1-llm-7b", "familyName": "Pharia-1-LLM-7B", "variantType": "control-aligned", "snapshotLabel": null, "baseFamilyModelKey": "pharia-1-llm-7b-control", "relatedModelKeys": [ "pharia-1-llm-7b-control" ], "isCanonicalFamilyEntry": false, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen-audio-7b", "canonicalModelKey": "qwen-audio-7b", "model": "Qwen-Audio 7B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen-audio-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen-audio-7b.md", "id": 367, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "qwen-audio-7b", "familyName": "Qwen-Audio 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen-audio-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "qwen-audio-chat-7b", "canonicalModelKey": "qwen-audio-chat-7b", "model": "Qwen-Audio-Chat 7B", "creator": "Alibaba", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/qwen-audio-chat-7b", "markdownUrl": "https://benchlm.ai/md/models/qwen-audio-chat-7b.md", "id": 369, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "qwen-audio-chat-7b", "familyName": "Qwen-Audio-Chat 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "qwen-audio-chat-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "salmonn-13b", "canonicalModelKey": "salmonn-13b", "model": "SALMONN 13B", "creator": "SALMONN authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/salmonn-13b", "markdownUrl": "https://benchlm.ai/md/models/salmonn-13b.md", "id": 372, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "salmonn-13b", "familyName": "SALMONN 13B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "salmonn-13b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "salmonn-7b", "canonicalModelKey": "salmonn-7b", "model": "SALMONN 7B", "creator": "SALMONN authors", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/salmonn-7b", "markdownUrl": "https://benchlm.ai/md/models/salmonn-7b.md", "id": 368, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "salmonn-7b", "familyName": "SALMONN 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "salmonn-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "scribe-v2-2-realtime", "canonicalModelKey": "scribe-v2-2-realtime", "model": "Scribe v2.2 Realtime", "creator": "ElevenLabs", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/scribe-v2-2-realtime", "markdownUrl": "https://benchlm.ai/md/models/scribe-v2-2-realtime.md", "id": 376, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "scribe-v2-2-realtime", "familyName": "Scribe v2.2 Realtime", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "scribe-v2-2-realtime", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "solar-pro-2", "canonicalModelKey": "solar-pro-2", "model": "Solar Pro 2", "creator": "Upstage", "sourceType": "Proprietary", "reasoningType": "Reasoning", "contextWindow": "128K", "contextWindowTokens": 128000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/solar-pro-2", "markdownUrl": "https://benchlm.ai/md/models/solar-pro-2.md", "id": 208, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "solar", "familyName": "Solar", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "solar-pro-2", "relatedModelKeys": [ "solar-wbl" ], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 31.9 }, "coding": { "aaSciCode": 24.8 }, "reasoning": { "lcr": 0, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 7.57, "aaGpqaDiamond": 56.1, "aaHle": 3.7, "aaOmniscienceIndex": -62, "omniscienceAccuracy": 16.1, "omniscienceHallucinationRate": 93 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 33.7 }, "math": {}, "korean": {} } }, { "slug": "speechgpt-7b", "canonicalModelKey": "speechgpt-7b", "model": "SpeechGPT 7B", "creator": "OpenMOSS", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/speechgpt-7b", "markdownUrl": "https://benchlm.ai/md/models/speechgpt-7b.md", "id": 370, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "speechgpt-7b", "familyName": "SpeechGPT 7B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "speechgpt-7b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "step-audio-chat-130b", "canonicalModelKey": "step-audio-chat-130b", "model": "Step-Audio-Chat 130B", "creator": "StepFun", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/step-audio-chat-130b", "markdownUrl": "https://benchlm.ai/md/models/step-audio-chat-130b.md", "id": 374, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "step-audio-chat-130b", "familyName": "Step-Audio-Chat 130B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "step-audio-chat-130b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "thunder-llm", "canonicalModelKey": "thunder-llm", "model": "Thunder-LLM 8B", "creator": "Academic", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "32K", "contextWindowTokens": 32000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/thunder-llm", "markdownUrl": "https://benchlm.ai/md/models/thunder-llm.md", "id": 214, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "thunder-llm", "familyName": "Thunder-LLM", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "thunder-llm", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "ultravox-glm-4p6", "canonicalModelKey": "ultravox-glm-4p6", "model": "Ultravox GLM-4P6", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-glm-4p6", "markdownUrl": "https://benchlm.ai/md/models/ultravox-glm-4p6.md", "id": 320, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-glm-4p6", "familyName": "Ultravox GLM-4P6", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-glm-4p6", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ultravox-glm-4p7", "canonicalModelKey": "ultravox-glm-4p7", "model": "Ultravox GLM-4P7", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-glm-4p7", "markdownUrl": "https://benchlm.ai/md/models/ultravox-glm-4p7.md", "id": 319, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-glm-4p7", "familyName": "Ultravox GLM-4P7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-glm-4p7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ultravox-v0-4-1-llama-3-1-8b", "canonicalModelKey": "ultravox-v0-4-1-llama-3-1-8b", "model": "Ultravox v0.4.1 Llama 3.1 8B", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-v0-4-1-llama-3-1-8b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-4-1-llama-3-1-8b.md", "id": 327, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-v0-4-1-llama-3-1-8b", "familyName": "Ultravox v0.4.1 Llama 3.1 8B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-v0-4-1-llama-3-1-8b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ultravox-v0-5-llama-3-1-8b", "canonicalModelKey": "ultravox-v0-5-llama-3-1-8b", "model": "Ultravox v0.5 Llama 3.1 8B", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-v0-5-llama-3-1-8b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-5-llama-3-1-8b.md", "id": 326, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-v0-5-llama-3-1-8b", "familyName": "Ultravox v0.5 Llama 3.1 8B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-v0-5-llama-3-1-8b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ultravox-v0-5-llama-3-2-1b", "canonicalModelKey": "ultravox-v0-5-llama-3-2-1b", "model": "Ultravox v0.5 Llama 3.2 1B", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-v0-5-llama-3-2-1b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-5-llama-3-2-1b.md", "id": 336, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-v0-5-llama-3-2-1b", "familyName": "Ultravox v0.5 Llama 3.2 1B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-v0-5-llama-3-2-1b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "ultravox-v0-6-llama-3-3-70b", "canonicalModelKey": "ultravox-v0-6-llama-3-3-70b", "model": "Ultravox v0.6 Llama 3.3 70B", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-v0-6-llama-3-3-70b", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-6-llama-3-3-70b.md", "id": 323, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-v0-6-llama-3-3-70b", "familyName": "Ultravox v0.6 Llama 3.3 70B", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-v0-6-llama-3-3-70b", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": { "tau2Bench": 26.6, "gdpvalAaNormalized": 0, "gdpvalAa": 98 }, "coding": { "aaCodingIndex": 11.93, "aaSciCode": 26 }, "reasoning": { "lcr": 15.7, "critpt": 0 }, "multimodalGrounded": {}, "knowledge": { "artificialAnalysis": 9.26, "aaGpqaDiamond": 49.8, "aaHle": 3.6, "aaOmniscienceIndex": -54.2, "omniscienceAccuracy": 19, "omniscienceHallucinationRate": 90.2 }, "multilingual": {}, "instructionFollowing": { "aaIfBench": 47.1 }, "math": {} } }, { "slug": "ultravox-v0-7", "canonicalModelKey": "ultravox-v0-7", "model": "Ultravox v0.7", "creator": "Fixie AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/ultravox-v0-7", "markdownUrl": "https://benchlm.ai/md/models/ultravox-v0-7.md", "id": 351, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "ultravox-v0-7", "familyName": "Ultravox v0.7", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "ultravox-v0-7", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } }, { "slug": "varco", "canonicalModelKey": "varco", "model": "Varco", "creator": "NC AI", "sourceType": "Proprietary", "reasoningType": "Non-Reasoning", "contextWindow": "64K", "contextWindowTokens": 64000, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/varco", "markdownUrl": "https://benchlm.ai/md/models/varco.md", "id": 213, "releaseDate": null, "market": "Korea", "isRegional": true, "family": { "familyKey": "varco", "familyName": "Varco", "variantType": null, "snapshotLabel": null, "baseFamilyModelKey": "varco", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {}, "korean": {} } }, { "slug": "voxtral-4b-tts-2603", "canonicalModelKey": "voxtral-4b-tts-2603", "model": "Voxtral 4B TTS 2603", "creator": "Mistral AI", "sourceType": "Open Weight", "reasoningType": "Non-Reasoning", "contextWindow": "N/A", "contextWindowTokens": 0, "displayScore": null, "provisionalDisplayScore": 0, "publicRankingMode": "bench-align-v5", "evidenceStatus": null, "scoreInterval90": null, "rankingEligible": false, "overallRank": null, "url": "https://benchlm.ai/models/voxtral-4b-tts-2603", "markdownUrl": "https://benchlm.ai/md/models/voxtral-4b-tts-2603.md", "id": 381, "releaseDate": null, "market": null, "isRegional": false, "family": { "familyKey": "voxtral-4b-tts-2603", "familyName": "Voxtral 4B TTS 2603", "variantType": "base", "snapshotLabel": null, "baseFamilyModelKey": "voxtral-4b-tts-2603", "relatedModelKeys": [], "isCanonicalFamilyEntry": true, "supersedesModelKey": null }, "scores": { "displayScore": 0, "overallScore": 0, "rawOverallScore": 0, "verifiedDisplayScore": null, "displayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null }, "verifiedDisplayCategoryScores": { "agentic": null, "coding": null, "reasoning": null, "multimodalGrounded": null, "knowledge": null, "multilingual": null, "instructionFollowing": null, "math": null } }, "ranking": { "rankingEligible": false, "verifiedRankingEligible": false, "overallRank": null, "categoryRanks": {}, "categoryRankingEligible": { "agentic": false, "coding": false, "reasoning": false, "multimodalGrounded": false, "knowledge": false, "multilingual": false, "instructionFollowing": false, "math": false } }, "coverage": { "trustedBenchmarkCount": 0, "verifiedBenchmarkCount": 0, "rankableBenchmarkCount": 0, "generatedBenchmarkCount": 0, "scoreConfidence": 1 }, "benchmarks": { "agentic": {}, "coding": {}, "reasoning": {}, "multimodalGrounded": {}, "knowledge": {}, "multilingual": {}, "instructionFollowing": {}, "math": {} } } ] }