{"schemaVersion":1,"evidenceVersion":"2026-09-26-11bcac73","generatedAt":"2026-09-26T20:07:06.100Z","coverageNotes":["Quality fit scores aggregate independent public leaderboards: LMArena (CC BY 4.0) and Epoch AI (CC BY 4.0). Vendor-reported benchmarks are excluded.","No speed evidence is published, so Fastest stays unavailable.","Search and scraping services have no independent comparable benchmark and are not scored."],"records":[{"id":"epoch:gpqa_diamond:anthropic-claude-haiku-4-5:2025-10-22","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2025-10-22T09:43:52.881Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.7121212121212122,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":25.4,"scoreLow":21.8,"scoreHigh":37.1,"measuredAs":"claude-haiku-4-5-20251001_32K","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:gpqa_diamond:anthropic-claude-sonnet-5:2026-08-06","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-06T22:21:47.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.803030303030303,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":41.6,"scoreLow":33.5,"scoreHigh":60.9,"measuredAs":"claude-sonnet-5_max","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:gpqa_diamond:google-gemini-3-1-pro-preview:2026-08-06","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-06T22:30:37.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.9444444444444444,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":98,"scoreLow":86.8,"scoreHigh":100,"measuredAs":"gemini-3.1-pro-preview_high","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:gpqa_diamond:google-gemini-3-5-flash-lite:2026-08-06","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-06T22:35:12.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.7575757575757576,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":35,"scoreLow":24.4,"scoreHigh":45.2,"measuredAs":"gemini-3.5-flash-lite_low","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:gpqa_diamond:google-gemini-3-8-flash:2026-09-02","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-09-02T17:15:36.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.9539141414141414,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":99.5,"scoreLow":90.4,"scoreHigh":100,"measuredAs":"gemini-3.8-flash_high","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:gpqa_diamond:openai-gpt-6-astra:2026-08-30","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-30T14:57:43.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:gpqa_diamond:2026-09-26","metricName":"GPQA diamond","value":0.9577020202020202,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":198},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:gpqa_diamond","score":100,"scoreLow":91.9,"scoreHigh":100,"measuredAs":"gpt-6-astra_max","frontierModel":"gpt-6-astra_max","frontierValue":0.9577020202020202}},{"id":"epoch:simpleqa_verified:anthropic-claude-fable-5-1:2026-09-01","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-09-01T18:31:59.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.708,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":97.5,"scoreLow":92.4,"scoreHigh":100,"measuredAs":"claude-fable-5-1_max","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"epoch:simpleqa_verified:anthropic-claude-haiku-4-5:2026-08-27","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-27T19:27:58.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.126,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":7,"scoreLow":3.8,"scoreHigh":11.4,"measuredAs":"claude-haiku-4-5-20251001_32K","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"epoch:simpleqa_verified:anthropic-claude-sonnet-5:2026-08-27","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-27T19:28:11.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.329,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":34.2,"scoreLow":25.3,"scoreHigh":46.8,"measuredAs":"claude-sonnet-5_xhigh","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"epoch:simpleqa_verified:google-gemini-3-1-pro-preview:2026-08-10","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-10T21:35:39.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.735,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":98.7,"scoreLow":97.5,"scoreHigh":100,"measuredAs":"gemini-3.1-pro-preview_high","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"epoch:simpleqa_verified:google-gemini-3-8-flash:2026-09-02","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-09-02T17:15:36.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.697,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":94.3,"scoreLow":92.4,"scoreHigh":98.7,"measuredAs":"gemini-3.8-flash_high","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"epoch:simpleqa_verified:openai-gpt-6-astra:2026-08-30","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://epoch.ai/benchmarks","sourceName":"Epoch AI","observedAt":"2026-08-30T14:57:43.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"epoch:simpleqa_verified:2026-09-26","metricName":"SimpleQA Verified","value":0.756,"higherIsBetter":true,"methodologyUrl":"https://epoch.ai/benchmarks/about","modality":"text","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks","fit":{"signalId":"epoch:simpleqa_verified","score":100,"scoreLow":98.7,"scoreHigh":100,"measuredAs":"gpt-6-astra_max","frontierModel":"gpt-6-astra_max","frontierValue":0.756}},{"id":"lmarena:agent:overall:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":0.13801278623144422,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":100,"scoreLow":100,"scoreHigh":100,"measuredAs":"Claude Fable 5.1 (Max)","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:agent:overall:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":0.047927456979043874,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":81.4,"scoreLow":60.5,"scoreHigh":86,"measuredAs":"Claude Sonnet 5 (High)","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:agent:overall:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":-0.06907041161067187,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":14,"scoreLow":9.3,"scoreHigh":20.9,"measuredAs":"Gemini 3.1 Pro Preview","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:agent:overall:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":0.04109614671954579,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":72.1,"scoreLow":60.5,"scoreHigh":83.7,"measuredAs":"Gemini 3.8 Flash (High)","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:agent:overall:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":0.10845555530468334,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":97.7,"scoreLow":93,"scoreHigh":100,"measuredAs":"GPT 6 Astra (Max)","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:agent:overall:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:agent:overall:2026-09-25","metricName":"agent_strength","value":0.07677049206107922,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"agent","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:agent:overall","score":88.4,"scoreLow":83.7,"scoreHigh":97.7,"measuredAs":"GPT 6 Sol (Max)","frontierModel":"Claude Fable 5.1 (Max)","frontierValue":0.13801278623144422}},{"id":"lmarena:document:overall:anthropic-claude-fable-5-1:2026-09-13","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-13T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:document:overall:2026-09-13","metricName":"arena_rating","value":1492.8290874460429,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"document_style_control","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:document:overall","score":88.4,"scoreLow":72.1,"scoreHigh":100,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-fable-5","frontierValue":1498.8779239411278}},{"id":"lmarena:document:overall:anthropic-claude-haiku-4-5:2026-09-13","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-13T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:document:overall:2026-09-13","metricName":"arena_rating","value":1418.7268267444001,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"document_style_control","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:document:overall","score":4.7,"scoreLow":2.3,"scoreHigh":9.3,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-fable-5","frontierValue":1498.8779239411278}},{"id":"lmarena:document:overall:anthropic-claude-sonnet-5:2026-09-13","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-13T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:document:overall:2026-09-13","metricName":"arena_rating","value":1475.6993372708034,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"document_style_control","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:document:overall","score":67.4,"scoreLow":60.5,"scoreHigh":81.4,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-fable-5","frontierValue":1498.8779239411278}},{"id":"lmarena:document:overall:google-gemini-3-1-pro-preview:2026-09-13","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-13T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:document:overall:2026-09-13","metricName":"arena_rating","value":1458.8643780484083,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"document_style_control","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:document:overall","score":39.5,"scoreLow":39.5,"scoreHigh":51.2,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-fable-5","frontierValue":1498.8779239411278}},{"id":"lmarena:document:overall:openai-gpt-6-astra:2026-09-13","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-13T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:document:overall:2026-09-13","metricName":"arena_rating","value":1472.5575370906897,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"document_style_control","profile":{"populationSize":44},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:document:overall","score":62.8,"scoreLow":39.5,"scoreHigh":83.7,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-fable-5","frontierValue":1498.8779239411278}},{"id":"lmarena:image_to_video:overall:fal-pika-2-2:2026-09-22","offerId":"fal-pika-2-2","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:image_to_video:overall:2026-09-22","metricName":"arena_rating","value":997.073436049672,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"image_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:image_to_video:overall","score":0,"scoreLow":0,"scoreHigh":2.1,"measuredAs":"pika-v2.2","frontierModel":"minimax-h3","frontierValue":1495.4129234217028}},{"id":"lmarena:image_to_video:overall:replicate-seedance-1-5-pro:2026-09-22","offerId":"replicate-seedance-1-5-pro","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:image_to_video:overall:2026-09-22","metricName":"arena_rating","value":1307.197082115737,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"image_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:image_to_video:overall","score":51.1,"scoreLow":51.1,"scoreHigh":55.3,"measuredAs":"seedance-v1.5-pro","frontierModel":"minimax-h3","frontierValue":1495.4129234217028}},{"id":"lmarena:image_to_video:overall:replicate-seedance-1-lite:2026-09-22","offerId":"replicate-seedance-1-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:image_to_video:overall:2026-09-22","metricName":"arena_rating","value":1185.3004857912556,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"image_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:image_to_video:overall","score":12.8,"scoreLow":12.8,"scoreHigh":14.9,"measuredAs":"seedance-v1-lite","frontierModel":"minimax-h3","frontierValue":1495.4129234217028}},{"id":"lmarena:text_to_image:commercial_design:fal-flux-1-dev:2026-09-24","offerId":"fal-flux-1-dev","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:commercial_design:2026-09-24","metricName":"arena_rating","value":991.5575103730212,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:commercial_design","score":5.1,"scoreLow":3.8,"scoreHigh":6.3,"measuredAs":"flux-1-dev-fp8","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1415.143401929843}},{"id":"lmarena:text_to_image:commercial_design:fal-flux-pro-1-1:2026-09-24","offerId":"fal-flux-pro-1-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:commercial_design:2026-09-24","metricName":"arena_rating","value":1012.5391378141426,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:commercial_design","score":6.3,"scoreLow":6.3,"scoreHigh":10.1,"measuredAs":"flux-1.1-pro","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1415.143401929843}},{"id":"lmarena:text_to_image:overall:fal-flux-1-dev:2026-09-24","offerId":"fal-flux-1-dev","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:overall:2026-09-24","metricName":"arena_rating","value":969.4098689006273,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:overall","score":5.1,"scoreLow":3.8,"scoreHigh":6.3,"measuredAs":"flux-1-dev-fp8","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1423.6048361955234}},{"id":"lmarena:text_to_image:overall:fal-flux-pro-1-1:2026-09-24","offerId":"fal-flux-pro-1-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:overall:2026-09-24","metricName":"arena_rating","value":1015.6473287264245,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:overall","score":11.4,"scoreLow":8.9,"scoreHigh":12.7,"measuredAs":"flux-1.1-pro","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1423.6048361955234}},{"id":"lmarena:text_to_image:photorealistic:fal-flux-1-dev:2026-09-24","offerId":"fal-flux-1-dev","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:photorealistic:2026-09-24","metricName":"arena_rating","value":990.2698292930992,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:photorealistic","score":6.3,"scoreLow":6.3,"scoreHigh":7.6,"measuredAs":"flux-1-dev-fp8","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1432.0525816644147}},{"id":"lmarena:text_to_image:photorealistic:fal-flux-pro-1-1:2026-09-24","offerId":"fal-flux-pro-1-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-24T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_image:photorealistic:2026-09-24","metricName":"arena_rating","value":1043.5509229500929,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_image","profile":{"populationSize":80},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_image:photorealistic","score":13.9,"scoreLow":12.7,"scoreHigh":17.7,"measuredAs":"flux-1.1-pro","frontierModel":"gpt-image-2.5-sunburst","frontierValue":1432.0525816644147}},{"id":"lmarena:text_to_video:overall:fal-pika-2-2:2026-09-22","offerId":"fal-pika-2-2","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_video:overall:2026-09-22","metricName":"arena_rating","value":1009.036038328957,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_video:overall","score":2.1,"scoreLow":0,"scoreHigh":4.3,"measuredAs":"pika-v2.2","frontierModel":"gemini-omni-1.1-flash","frontierValue":1516.2118921315541}},{"id":"lmarena:text_to_video:overall:replicate-seedance-1-5-pro:2026-09-22","offerId":"replicate-seedance-1-5-pro","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_video:overall:2026-09-22","metricName":"arena_rating","value":1255.9639765937768,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_video:overall","score":55.3,"scoreLow":53.2,"scoreHigh":57.4,"measuredAs":"seedance-v1.5-pro","frontierModel":"gemini-omni-1.1-flash","frontierValue":1516.2118921315541}},{"id":"lmarena:text_to_video:overall:replicate-seedance-1-lite:2026-09-22","offerId":"replicate-seedance-1-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-22T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text_to_video:overall:2026-09-22","metricName":"arena_rating","value":1112.5816050440721,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_to_video","profile":{"populationSize":48},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text_to_video:overall","score":10.6,"scoreLow":8.5,"scoreHigh":12.8,"measuredAs":"seedance-v1-lite","frontierModel":"gemini-omni-1.1-flash","frontierValue":1516.2118921315541}},{"id":"lmarena:text:coding:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1529.0805158419125,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":95,"scoreLow":90.3,"scoreHigh":98.5,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1481.5982175665354,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":74.9,"scoreLow":73.4,"scoreHigh":76.4,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1547.1280940304046,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":99,"scoreLow":93.8,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1519.260323330143,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":91.8,"scoreLow":88.3,"scoreHigh":94.5,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1520.7529788786348,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":92.6,"scoreLow":90.6,"scoreHigh":94.5,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1503.3038987723476,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":83.6,"scoreLow":80.6,"scoreHigh":86.8,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1532.1317766071393,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":96.3,"scoreLow":93.8,"scoreHigh":98,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1542.311866429462,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":98.3,"scoreLow":94.5,"scoreHigh":100,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1514.5353731888906,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":89.6,"scoreLow":80.6,"scoreHigh":96.3,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:coding:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:coding:2026-09-25","metricName":"arena_rating","value":1523.8094697717477,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":404},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:coding","score":93.8,"scoreLow":85.4,"scoreHigh":98.3,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-4-6-high","frontierValue":1551.3712215189335}},{"id":"lmarena:text:hard_prompts:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1520.437098730128,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":98.8,"scoreLow":97.1,"scoreHigh":99.5,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1441.246900351957,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":69.9,"scoreLow":69.1,"scoreHigh":71.1,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1541.2616441613704,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":100,"scoreLow":99,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1489.39181937915,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":89.5,"scoreLow":87,"scoreHigh":90.7,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1506.779543151678,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":95.8,"scoreLow":94.6,"scoreHigh":96.6,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1475.3154463929259,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":83.1,"scoreLow":81.1,"scoreHigh":85.8,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1515.8048534413463,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":97.5,"scoreLow":96.6,"scoreHigh":99,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1502.1347016353584,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":94.1,"scoreLow":90.4,"scoreHigh":97.1,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1468.0794649544682,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":80.6,"scoreLow":76,"scoreHigh":85,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:hard_prompts:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:hard_prompts:2026-09-25","metricName":"arena_rating","value":1485.3531679455375,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:hard_prompts","score":87,"scoreLow":82.6,"scoreHigh":91.7,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-5.5-high","frontierValue":1541.2616441613704}},{"id":"lmarena:text:instruction_following:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1497.2757759545025,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":98.8,"scoreLow":96.8,"scoreHigh":99.5,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1415.2345799726613,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":72.3,"scoreLow":69.9,"scoreHigh":73.8,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1516.3907218497893,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":100,"scoreLow":98.5,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1466.7347164622315,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":91.2,"scoreLow":89,"scoreHigh":92.9,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1479.375246480055,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":95.8,"scoreLow":94.6,"scoreHigh":96.6,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1443.8276652574468,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":82.6,"scoreLow":81.4,"scoreHigh":86,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1488.1010534874358,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":97.3,"scoreLow":96.3,"scoreHigh":98.5,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1473.3254243783945,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":93.6,"scoreLow":89,"scoreHigh":96.8,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1443.319211914869,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":82.1,"scoreLow":77.9,"scoreHigh":88,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:instruction_following:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:instruction_following:2026-09-25","metricName":"arena_rating","value":1446.7262693899233,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:instruction_following","score":84.3,"scoreLow":78.9,"scoreHigh":89.2,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-5.5-high","frontierValue":1516.3907218497893}},{"id":"lmarena:text:longer_query:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1510.972258646147,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":98.7,"scoreLow":97.4,"scoreHigh":99.5,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1436.6541993950714,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":71.2,"scoreLow":69.4,"scoreHigh":72.3,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1530.2578586022394,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":100,"scoreLow":99,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1481.6931826536518,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":90.7,"scoreLow":87.6,"scoreHigh":93,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1498.801368029449,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":96.6,"scoreLow":95.3,"scoreHigh":97.7,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1462.4598836893058,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":82.1,"scoreLow":80.3,"scoreHigh":85.5,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1509.114457662975,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":98.4,"scoreLow":97.7,"scoreHigh":99.2,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1488.357932967436,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":93.5,"scoreLow":88.1,"scoreHigh":97.2,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1460.6497449895212,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":81.6,"scoreLow":76.9,"scoreHigh":87,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:longer_query:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:longer_query:2026-09-25","metricName":"arena_rating","value":1467.0605326550124,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":387},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:longer_query","score":85,"scoreLow":80.1,"scoreHigh":89.4,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-5.5-high","frontierValue":1530.2578586022394}},{"id":"lmarena:text:multi_turn:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1485.0298515572097,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":94.1,"scoreLow":85.7,"scoreHigh":98.3,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1425.497351930287,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":70.9,"scoreLow":69.7,"scoreHigh":72.4,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1518.518424824055,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":99.8,"scoreLow":94.1,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1473.0818161822094,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":87.7,"scoreLow":84,"scoreHigh":90.9,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1496.0356293974085,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":97.3,"scoreLow":95.6,"scoreHigh":98.3,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1466.0108297695588,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":84.5,"scoreLow":82,"scoreHigh":89.2,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1504.8019154566975,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":98.3,"scoreLow":96.1,"scoreHigh":99,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1494.845706178771,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":96.6,"scoreLow":89.4,"scoreHigh":98.8,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1447.3431632059835,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":77.8,"scoreLow":70.4,"scoreHigh":86.2,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:multi_turn:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:multi_turn:2026-09-25","metricName":"arena_rating","value":1460.7339024684238,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":407},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:multi_turn","score":82.8,"scoreLow":74.6,"scoreHigh":92.4,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-4-6-high","frontierValue":1518.9747610021277}},{"id":"lmarena:text:overall:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1501.293611997489,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":99,"scoreLow":98.3,"scoreHigh":100,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1413.9274399763758,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":66.7,"scoreLow":65.9,"scoreHigh":68.4,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1508.5538218355593,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":100,"scoreLow":98.8,"scoreHigh":100,"measuredAs":"claude-opus-5.5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1461.5259908728863,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":87,"scoreLow":85.5,"scoreHigh":89,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1486.6776290065297,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":96.1,"scoreLow":95.8,"scoreHigh":97.3,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1456.0256628530637,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":84.3,"scoreLow":82.4,"scoreHigh":86.8,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1492.3909065738185,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":97.8,"scoreLow":96.3,"scoreHigh":99,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1477.7238481553331,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":93.9,"scoreLow":89.7,"scoreHigh":95.8,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1442.4231003499538,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":79.2,"scoreLow":75.2,"scoreHigh":82.4,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:text:overall:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:text:overall:2026-09-25","metricName":"arena_rating","value":1457.482176999627,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"text_style_control","profile":{"populationSize":409},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:text:overall","score":85.5,"scoreLow":81.4,"scoreHigh":89,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-5.5-high","frontierValue":1508.5538218355593}},{"id":"lmarena:webdev:overall:anthropic-claude-fable-5-1:2026-09-25","offerId":"anthropic-claude-fable-5-1","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1751.4867509630722,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":98.5,"scoreLow":98.5,"scoreHigh":99.2,"measuredAs":"claude-fable-5.1-max","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:anthropic-claude-haiku-4-5:2026-09-25","offerId":"anthropic-claude-haiku-4-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1329.545619927862,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":18,"scoreLow":17.3,"scoreHigh":19.5,"measuredAs":"claude-haiku-4-5-20251001","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:anthropic-claude-opus-5-5:2026-09-25","offerId":"anthropic-claude-opus-5-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1826.7306745084245,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":100,"scoreLow":100,"scoreHigh":100,"measuredAs":"claude-opus-5.5-max","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:anthropic-claude-sonnet-5:2026-09-25","offerId":"anthropic-claude-sonnet-5","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1538.9131567383743,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":73.7,"scoreLow":71.4,"scoreHigh":75.2,"measuredAs":"claude-sonnet-5-high","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:google-gemini-3-1-pro-preview:2026-09-25","offerId":"google-gemini-3-1-pro-preview","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1446.3145134914955,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":53.4,"scoreLow":51.9,"scoreHigh":54.1,"measuredAs":"gemini-3.1-pro-preview","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:google-gemini-3-5-flash-lite:2026-09-25","offerId":"google-gemini-3-5-flash-lite","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1439.255207668645,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":51.1,"scoreLow":39.1,"scoreHigh":59.4,"measuredAs":"gemini-3.5-flash-lite","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:google-gemini-3-8-flash:2026-09-25","offerId":"google-gemini-3-8-flash","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1579.9571506411203,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":79.7,"scoreLow":79.7,"scoreHigh":82,"measuredAs":"gemini-3.8-flash-high","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:openai-gpt-6-astra:2026-09-25","offerId":"openai-gpt-6-astra","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1791.6525596749589,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":99.2,"scoreLow":99.2,"scoreHigh":100,"measuredAs":"gpt-6-astra-max","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:openai-gpt-6-luna:2026-09-25","offerId":"openai-gpt-6-luna","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1592.646721210178,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":82.7,"scoreLow":79.7,"scoreHigh":85,"measuredAs":"gpt-6-luna-max","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}},{"id":"lmarena:webdev:overall:openai-gpt-6-sol:2026-09-25","offerId":"openai-gpt-6-sol","dimension":"quality","sourceUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","sourceName":"LMArena","observedAt":"2026-09-25T00:00:00.000Z","retrievedAt":"2026-09-26T20:04:54.444Z","cohortId":"lmarena:webdev:overall:2026-09-25","metricName":"arena_rating","value":1680.9724563881532,"higherIsBetter":true,"methodologyUrl":"https://arena.ai/blog/arena-leaderboard-dataset","modality":"webdev","profile":{"populationSize":134},"evidenceType":"benchmark","license":"CC BY 4.0","attribution":"LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset)","fit":{"signalId":"lmarena:webdev:overall","score":97,"scoreLow":96.2,"scoreHigh":98.5,"measuredAs":"gpt-6-sol-max","frontierModel":"claude-opus-5.5-max","frontierValue":1826.7306745084245}}]}