{"citation":[{"name":"models.dev","license":"MIT","url":"https://models.dev/api.json","retrievedAt":"2026-10-23T02:38:47+00:00"},{"name":"LiteLLM model_prices_and_context_window.json","license":"MIT","url":"https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json","retrievedAt":"2026-10-23T02:38:47+00:00"},{"name":"ModelPriceWatch LLM Token Price History","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/modelpricewatch/llm-token-price-history","retrievedAt":"2026-10-23T02:38:47+00:00"},{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"},{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}],"generatedAt":"2026-10-23T02:38:47+00:00","data":[{"slug":"deepseek-deepseek-v4-flash","name":"DeepSeek V4 Flash","arena":{"model":"DeepSeek-V4-Flash","organization":"deepseek","licenseModel":"MIT","rating":1432.0007953071622,"ratingLower":1427.980895305358,"ratingUpper":1436.0206953089664,"votes":51959,"rank":92,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.11,"unit":"eci","model":"DeepSeek-V4-Flash","organization":"DeepSeek","date":"2026-04-24","ciLow":143.82,"ciHigh":147.99,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":102.83342755361988,"valueRaw":2937.4375},{"slug":"google-gemini-4-argon","name":"Gemini 4 Argon","arena":{"model":"Gemini 4 Argon (High)","organization":"google","licenseModel":"Proprietary","rating":1532.3049251071352,"ratingLower":1523.5204504670612,"ratingUpper":1541.0893997472092,"votes":4900,"rank":1,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":96.4015,"unit":"percent","model":"gemini-4-argon_high","organization":"Google DeepMind","date":"2026-09-30","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":166.45,"unit":"eci","model":"Gemini 4 Argon","organization":"Google DeepMind","date":"2026-09-30","ciLow":163.23,"ciHigh":171.52,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":237.58948233217905,"valueRaw":191.5381},{"slug":"meta-muse-wonder-1-0","name":"Muse Wonder","arena":{"model":"Muse Wonder (Max)","organization":"meta","licenseModel":"Proprietary","rating":1501.6949006218686,"ratingLower":1493.0250789844645,"ratingUpper":1510.3647222592724,"votes":5099,"rank":6,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":161.85,"unit":"eci","model":"Muse Wonder","organization":"Meta AI","date":"2026-10-12","ciLow":159.39,"ciHigh":165.44,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":165.5617010123184,"valueRaw":93.8559},{"slug":"mistral-mistral-large-4","name":"Mistral Large 4","arena":{"model":"Mistral Large 4","organization":"mistral","licenseModel":"Proprietary","rating":1430.779096950918,"ratingLower":1424.1179310761163,"ratingUpper":1437.4402628257196,"votes":9308,"rank":93,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":150.03,"unit":"eci","model":"Mistral Large 4","organization":"Mistral AI","date":"2026-10-06","ciLow":146.94,"ciHigh":152.74,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":61.27561120689477,"valueRaw":411.735},{"slug":"openai-gpt-6-1-sol","name":"GPT-6.1 Sol","arena":{"model":"GPT-6.1 Sol (Max)","organization":"openai","licenseModel":"Proprietary","rating":1443.40746839841,"ratingLower":1435.8698444339652,"ratingUpper":1450.9450923628544,"votes":7453,"rank":66,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":95.3914,"unit":"percent","model":"gpt-6.1-sol_max","organization":"OpenAI","date":"2026-09-29","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":168.37,"unit":"eci","model":"GPT-6.1 Sol","organization":"OpenAI","date":"2026-09-29","ciLow":165,"ciHigh":174.43,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":68.62089050047176,"valueRaw":180.4259},{"slug":"anthropic-claude-sonnet-5-5","name":"Claude Sonnet 5.5","arena":{"model":"Claude Sonnet 5.5 (xHigh)","organization":"anthropic","licenseModel":"Proprietary","rating":1472.633919472102,"ratingLower":1465.3930080142873,"ratingUpper":1479.8748309299167,"votes":8126,"rank":28,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":95.5808,"unit":"percent","model":"claude-sonnet-5-5_max","organization":"Anthropic","date":"2026-09-28","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":166.18,"unit":"eci","model":"Claude Sonnet 5.5","organization":"Anthropic","date":"2026-09-28","ciLow":163.06,"ciHigh":171.34,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":124.1719992159963,"valueRaw":184.0792},{"slug":"anthropic-claude-opus-5-5","name":"Claude Opus 5.5","arena":{"model":"Claude Opus 5.5 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1516.214193109078,"ratingLower":1509.2331722472181,"ratingUpper":1523.1952139709376,"votes":9496,"rank":2,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.5934,"unit":"percent","model":"claude-opus-5-5_max","organization":"Anthropic","date":"2026-09-22","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":168.83,"unit":"eci","model":"Claude Opus 5.5","organization":"Anthropic","date":"2026-09-22","ciLow":165.25,"ciHigh":173.95,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":193.15871555903124,"valueRaw":94.7634},{"slug":"openai-gpt-6-luna","name":"GPT-6 Luna","arena":{"model":"GPT-6 Luna (Max)","organization":"openai","licenseModel":"Proprietary","rating":1389.3743969603784,"ratingLower":1384.9985518007836,"ratingUpper":1393.750242119973,"votes":63594,"rank":167,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.4672,"unit":"percent","model":"gpt-6-luna_max","organization":"OpenAI","date":"2026-09-22","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":156.75,"unit":"eci","model":"GPT-6 Luna","organization":"OpenAI","date":"2026-09-22","ciLow":154.32,"ciHigh":159.43,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":3473.436},{"slug":"openai-gpt-6-sol","name":"GPT-6 Sol","arena":{"model":"GPT-6 Sol (Max)","organization":"openai","licenseModel":"Proprietary","rating":1398.1158649410277,"ratingLower":1391.9614721130702,"ratingUpper":1404.270257768985,"votes":13790,"rank":157,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":94.3182,"unit":"percent","model":"gpt-6-sol_max","organization":"OpenAI","date":"2026-09-22","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":163.73,"unit":"eci","model":"GPT-6 Sol","organization":"OpenAI","date":"2026-09-22","ciLow":160.92,"ciHigh":167.44,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":174.7645},{"slug":"xai-grok-4-7","name":"Grok 4.7","arena":{"model":"Grok 4.7 (xHigh)","organization":"xai","licenseModel":"Proprietary","rating":1399.0031143536319,"ratingLower":1392.8974059389363,"ratingUpper":1405.1088227683272,"votes":13489,"rank":156,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":92.7399,"unit":"percent","model":"grok-4.7_xhigh","organization":"xAI","date":"2026-09-21","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":154.37,"unit":"eci","model":"Grok 4.7","organization":"xAI","date":"2026-09-21","ciLow":152.6,"ciHigh":157.08,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":279.8006},{"slug":"nvidia-stepfun-ai-step-5-preview","name":"Step 5 Preview","arena":{"model":"Step 5 Preview","organization":"stepfun","licenseModel":"Proprietary","rating":1440.3232927002698,"ratingLower":1433.4324098530083,"ratingUpper":1447.2141755475316,"votes":8756,"rank":74,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-6-astra","name":"GPT-6 Astra","arena":{"model":"GPT-6 Astra (Max)","organization":"openai","licenseModel":"Proprietary","rating":1440.97967006192,"ratingLower":1434.8338828438714,"ratingUpper":1447.1254572799687,"votes":13293,"rank":73,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":95.7702,"unit":"percent","model":"gpt-6-astra_max","organization":"OpenAI","date":"2026-09-03","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":168.81,"unit":"eci","model":"GPT-6 Astra","organization":"OpenAI","date":"2026-09-03","ciLow":165.45,"ciHigh":174.51,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":31.854844673135634,"valueRaw":36.0245},{"slug":"google-gemini-3-8-flash","name":"Gemini 3.8 Flash","arena":{"model":"Gemini 3.8 Flash (High)","organization":"google","licenseModel":"Proprietary","rating":1498.882028339407,"ratingLower":1494.3634034530144,"ratingUpper":1503.4006532257997,"votes":41423,"rank":8,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":95.3914,"unit":"percent","model":"gemini-3.8-flash_high","organization":"Google DeepMind","date":"2026-09-02","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":157.44,"unit":"eci","model":"Gemini 3.8 Flash","organization":"Google DeepMind","date":"2026-09-02","ciLow":155.07,"ciHigh":161.08,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":193.65600993577524,"valueRaw":499.6273},{"slug":"meta-muse-spark-1-3","name":"Muse Spark 1.3","arena":{"model":"Muse Spark 1.3 (Max)","organization":"meta","licenseModel":"Proprietary","rating":1490.4580287328113,"ratingLower":1485.0443580566885,"ratingUpper":1495.8716994089343,"votes":19323,"rank":12,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":157.21,"unit":"eci","model":"Muse Spark 1.3","organization":"Meta AI","date":"2026-09-02","ciLow":155.26,"ciHigh":159.82,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":174.5649558308743,"valueRaw":425.8452},{"slug":"anthropic-claude-fable-5-1","name":"Claude Fable 5.1","arena":{"model":"Claude Fable 5.1 (Max)","organization":"anthropic","licenseModel":"Proprietary","rating":1511.9418886616315,"ratingLower":1506.0260537348445,"ratingUpper":1517.8577235884186,"votes":15623,"rank":3,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":166.49,"unit":"eci","model":"Claude Fable 5.1","organization":"Anthropic","date":"2026-09-01","ciLow":163.47,"ciHigh":171.35,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":166.73368816281902,"valueRaw":37.7985},{"slug":"nvidia-z-ai-glm-5-3-flash","name":"GLM-5.3-Flash","arena":{"model":"GLM-5.3-Flash","organization":"zai","licenseModel":"MIT","rating":1471.3570741044848,"ratingLower":1466.5937554216894,"ratingUpper":1476.12039278728,"votes":36095,"rank":29,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.1515,"unit":"percent","model":"glm-5.3-flash_max","organization":"Z.ai (Zhipu AI)","date":"2026-08-20","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":153.08,"unit":"eci","model":"GLM-5.3-Flash","organization":"Z.ai (Zhipu AI)","date":"2026-08-20","ciLow":150.76,"ciHigh":155.53,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"groq-qwen-qwen3-8-27b","name":"Qwen3.8 27B","arena":{"model":"Qwen3.8-27B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1439.6694721001836,"ratingLower":1434.715860100718,"ratingUpper":1444.6230840996493,"votes":25103,"rank":76,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":79.82063151330017,"valueRaw":449.8967},{"slug":"nvidia-z-ai-glm-5-3","name":"GLM-5.3","arena":{"model":"GLM-5.3 (Max)","organization":"zai","licenseModel":"MIT","rating":1473.6920460876765,"ratingLower":1468.6086657223661,"ratingUpper":1478.7754264529867,"votes":24035,"rank":27,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.9091,"unit":"percent","model":"glm-5.3_max","organization":"Z.ai (Zhipu AI)","date":"2026-08-14","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":155.99,"unit":"eci","model":"GLM-5.3","organization":"Z.ai (Zhipu AI)","date":"2026-08-14","ciLow":154.17,"ciHigh":158.35,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"deepseek-deepseek-v4-pro","name":"DeepSeek V4 Pro","arena":{"model":"DeepSeek-V4-Pro","organization":"deepseek","licenseModel":"MIT","rating":1451.3452341889415,"ratingLower":1447.4644927405855,"ratingUpper":1455.2259756372978,"votes":57564,"rank":49,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":89.6465,"unit":"percent","model":"deepseek-v4-pro_max","organization":"DeepSeek","date":"2026-04-24","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":77.6398,"unit":"percent","model":"deepseek-v4-pro_max","organization":"DeepSeek","date":"2026-04-24","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":149.13,"unit":"eci","model":"DeepSeek-V4-Pro","organization":"DeepSeek","date":"2026-04-24","ciLow":147.63,"ciHigh":150.87,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":115.24508483466933,"valueRaw":879.6032},{"slug":"google-gemini-3-7-flash","name":"Gemini 3.7 Flash","arena":{"model":"Gemini 3.7 Flash (High)","organization":"google","licenseModel":"Proprietary","rating":1488.5288907740603,"ratingLower":1483.7645841846697,"ratingUpper":1493.2931973634509,"votes":29177,"rank":14,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":94.8232,"unit":"percent","model":"gemini-3.7-flash_high","organization":"Google DeepMind","date":"2026-08-13","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":157.97,"unit":"eci","model":"Gemini 3.7 Flash","organization":"Google DeepMind","date":"2026-08-13","ciLow":155.92,"ciHigh":161.24,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":173.9776620929523,"valueRaw":496.1763},{"slug":"xai-grok-4-6","name":"Grok 4.6","arena":{"model":"Grok 4.6 (High)","organization":"xai","licenseModel":"Proprietary","rating":1428.5191559435914,"ratingLower":1423.779288844396,"ratingUpper":1433.259023042787,"votes":30919,"rank":98,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":94.0025,"unit":"percent","model":"grok-4.6_high","organization":"xAI","date":"2026-08-12","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":156.57,"unit":"eci","model":"Grok 4.6","organization":"xAI","date":"2026-08-12","ciLow":154.68,"ciHigh":159.19,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":49.7116658938251,"valueRaw":285.7038},{"slug":"meta-muse-spark-1-2","name":"Muse Spark 1.2","arena":{"model":"Muse Spark 1.2 (xHigh)","organization":"meta","licenseModel":"Proprietary","rating":1482.3582636672334,"ratingLower":1475.568089441872,"ratingUpper":1489.1484378925948,"votes":9578,"rank":17,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":155.05,"unit":"eci","model":"Muse Spark 1.2","organization":"Meta AI","date":"2026-08-05","ciLow":152.82,"ciHigh":157.56,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":159.16962341115587,"valueRaw":423.5309},{"slug":"alibaba-qwen3-8-max","name":"Qwen3.8 Max","arena":{"model":"Qwen3.8-Max","organization":"alibaba","licenseModel":"Proprietary","rating":1483.1832870808096,"ratingLower":1478.315869562627,"ratingUpper":1488.0507045989918,"votes":29418,"rank":15,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":92.6768,"unit":"percent","model":"qwen3.8-max_xhigh","organization":"Alibaba","date":"2026-08-02","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":155.08,"unit":"eci","model":"Qwen3.8 Max (0902)","organization":"Alibaba","date":"2026-09-01","ciLow":153.03,"ciHigh":157.19,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":153.61251529858632,"valueRaw":296.6367},{"slug":"anthropic-claude-opus-5","name":"Claude Opus 5","arena":{"model":"Claude Opus 5 (Max)","organization":"anthropic","licenseModel":"Proprietary","rating":1508.5993931223063,"ratingLower":1503.8622525803921,"ratingUpper":1513.3365336642203,"votes":33683,"rank":4,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":93.8763,"unit":"percent","model":"claude-opus-5_max","organization":"Anthropic","date":"2026-07-24","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":163.94,"unit":"eci","model":"Claude Opus 5","organization":"Anthropic","date":"2026-07-24","ciLow":161.12,"ciHigh":168.24,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":174.2274579362047,"valueRaw":75.43},{"slug":"google-gemini-3-5-flash-lite","name":"Gemini 3.5 Flash Lite","arena":{"model":"Gemini 3.5 Flash-Lite","organization":"google","licenseModel":"Proprietary","rating":1434.9936059575664,"ratingLower":1430.5355829552088,"ratingUpper":1439.4516289599242,"votes":35820,"rank":88,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":83.3333,"unit":"percent","model":"gemini-3.5-flash-lite_high","organization":"Google DeepMind","date":"2026-07-21","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":144.91,"unit":"eci","model":"Gemini 3.5 Flash-Lite","organization":"Google DeepMind","date":"2026-07-21","ciLow":142.41,"ciHigh":146.26,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":80.82811099897,"valueRaw":735.8942},{"slug":"google-gemini-3-6-flash","name":"Gemini 3.6 Flash","arena":{"model":"Gemini 3.6 Flash (High)","organization":"google","licenseModel":"Proprietary","rating":1479.5345782302822,"ratingLower":1475.1402647781904,"ratingUpper":1483.9288916823741,"votes":36079,"rank":20,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":94.1288,"unit":"percent","model":"gemini-3.6-flash_high","organization":"Google DeepMind","date":"2026-07-21","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":154.53,"unit":"eci","model":"Gemini 3.6 Flash","organization":"Google DeepMind","date":"2026-07-21","ciLow":152.85,"ciHigh":156.58,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":156.88205124779668,"valueRaw":493.1782},{"slug":"nvidia-moonshotai-kimi-k3","name":"Kimi K3","arena":{"model":"Kimi K3 (Max)","organization":"moonshot","licenseModel":"Kimi K3 license","rating":1475.7102938150656,"ratingLower":1471.2015248547273,"ratingUpper":1480.2190627754037,"votes":34325,"rank":24,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":93.1187,"unit":"percent","model":"kimi-k3_max","organization":"Moonshot","date":"2026-07-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":157.86,"unit":"eci","model":"Kimi K3","organization":"Moonshot","date":"2026-07-16","ciLow":155.11,"ciHigh":160.63,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-6-terra","name":"GPT-5.6 Terra","arena":{"model":"GPT-5.6 Terra (xHigh)","organization":"openai","licenseModel":"Proprietary","rating":1448.0702026084807,"ratingLower":1443.8921940719695,"ratingUpper":1452.248211144992,"votes":45201,"rank":56,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":93.3081,"unit":"percent","model":"gpt-5.6-terra_max","organization":"OpenAI","date":"2026-07-09","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":160.09,"unit":"eci","model":"GPT-5.6 Terra","organization":"OpenAI","date":"2026-07-09","ciLow":157.3,"ciHigh":163.31,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":74.05038564114773,"valueRaw":152.4284},{"slug":"openai-gpt-5-6-sol","name":"GPT-5.6 Sol","arena":{"model":"GPT-5.6 Sol (xHigh)","organization":"openai","licenseModel":"Proprietary","rating":1456.72532831342,"ratingLower":1452.4481572049906,"ratingUpper":1461.0024994218493,"votes":41803,"rank":43,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":93.4975,"unit":"percent","model":"gpt-5.6-sol_max","organization":"OpenAI","date":"2026-07-09","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":162.79,"unit":"eci","model":"GPT-5.6 Sol","organization":"OpenAI","date":"2026-07-09","ciLow":160.15,"ciHigh":167.06,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":80.08742998644216,"valueRaw":91.0453},{"slug":"openai-gpt-5-6-luna","name":"GPT-5.6 Luna","arena":{"model":"GPT-5.6 Luna (xHigh)","organization":"openai","licenseModel":"Proprietary","rating":1430.528898420856,"ratingLower":1426.2503078408818,"ratingUpper":1434.8074890008304,"votes":41052,"rank":94,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":91.6035,"unit":"percent","model":"gpt-5.6-luna_max","organization":"OpenAI","date":"2026-07-09","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":156.5,"unit":"eci","model":"GPT-5.6 Luna","organization":"OpenAI","date":"2026-07-09","ciLow":154.19,"ciHigh":159.26,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":86.7077856816123,"valueRaw":1505.8199},{"slug":"xai-grok-4-5","name":"Grok 4.5","arena":{"model":"Grok 4.5","organization":"xai","licenseModel":"Proprietary","rating":1447.6545203968349,"ratingLower":1443.323956623231,"ratingUpper":1451.9850841704388,"votes":39844,"rank":57,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":93.4343,"unit":"percent","model":"grok-4.5_high","organization":"xAI","date":"2026-07-08","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":154.07,"unit":"eci","model":"Grok 4.5","organization":"xAI","date":"2026-07-08","ciLow":152.36,"ciHigh":156.18,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":86.08251052265365,"valueRaw":289.5309},{"slug":"anthropic-claude-sonnet-5","name":"Claude Sonnet 5","arena":{"model":"Claude Sonnet 5 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1441.8782563543814,"ratingLower":1437.8074321013892,"ratingUpper":1445.9490806073734,"votes":50871,"rank":71,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.5303,"unit":"percent","model":"claude-sonnet-5_xhigh","organization":"Anthropic","date":"2026-06-30","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":156.88,"unit":"eci","model":"Claude Sonnet 5","organization":"Anthropic","date":"2026-06-30","ciLow":154.1,"ciHigh":159.65,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":65.7142965971365,"valueRaw":180.2348},{"slug":"alibaba-glm-5-2","name":"GLM-5.2","arena":{"model":"GLM-5.2 (Max)","organization":"zai","licenseModel":"MIT","rating":1470.3641370966138,"ratingLower":1466.2499403522163,"ratingUpper":1474.4783338410116,"votes":51221,"rank":32,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":91.8561,"unit":"percent","model":"glm-5.2_max","organization":"Z.ai (Zhipu AI)","date":"2026-06-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":78.7,"unit":"percent","model":"glm-5.2_max","organization":"Z.ai (Zhipu AI)","date":"2026-06-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":151.94,"unit":"eci","model":"GLM-5.2","organization":"Z.ai (Zhipu AI)","date":"2026-06-16","ciLow":149.99,"ciHigh":154.1,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":135.53391325572488,"valueRaw":402.8395},{"slug":"anthropic-claude-fable-5","name":"Claude Fable 5","arena":{"model":"Claude Fable 5 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1491.2846003921193,"ratingLower":1487.0413236982192,"ratingUpper":1495.5278770860193,"votes":43399,"rank":10,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":83.3333,"unit":"percent","model":"claude-fable-5_high","organization":"Anthropic","date":"2026-06-09","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":163.42,"unit":"eci","model":"Claude Fable 5","organization":"Anthropic","date":"2026-06-09","ciLow":160.53,"ciHigh":168.18,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":127.47010246320083,"valueRaw":37.2821},{"slug":"alibaba-qwen3-7-plus","name":"Qwen3.7 Plus","arena":{"model":"Qwen3.7-Plus","organization":"alibaba","licenseModel":"Proprietary","rating":1454.499639660167,"ratingLower":1450.1831585071307,"ratingUpper":1458.8161208132035,"votes":42030,"rank":45,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":87.8788,"unit":"percent","model":"qwen3.7-plus","organization":"Alibaba","date":"2026-06-02","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":147,"unit":"eci","model":"Qwen3.7-Plus","organization":"Alibaba","date":"2026-06-02","ciLow":145.25,"ciHigh":148.82,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":126.00340657293599,"valueRaw":1118.8459},{"slug":"anthropic-claude-opus-4-8","name":"Claude Opus 4.8","arena":{"model":"Claude Opus 4.8 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1460.8504622933615,"ratingLower":1456.9813246843687,"ratingUpper":1464.719599902354,"votes":64063,"rank":40,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":91.0354,"unit":"percent","model":"claude-opus-4-8_max","organization":"Anthropic","date":"2026-05-28","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":159.01,"unit":"eci","model":"Claude Opus 4.8","organization":"Anthropic","date":"2026-05-28","ciLow":156.89,"ciHigh":161.95,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":83.47042278196365,"valueRaw":73.0425},{"slug":"alibaba-qwen3-7-max","name":"Qwen3.7 Max","arena":{"model":"Qwen3.7-Max-Preview","organization":"alibaba","licenseModel":"Proprietary","rating":1474.9104676359475,"ratingLower":1465.2496475813714,"ratingUpper":1484.5712876905234,"votes":3942,"rank":25,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.9091,"unit":"percent","model":"qwen3.7-max","organization":"Alibaba","date":"2026-05-19","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":77.2727,"unit":"percent","model":"qwen3.7-max","organization":"Alibaba","date":"2026-05-19","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":154.04,"unit":"eci","model":"Qwen3.7-Max","organization":"Alibaba","date":"2026-05-19","ciLow":152.3,"ciHigh":156.5,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":133.43055123996496,"valueRaw":235.9857},{"slug":"google-gemini-3-5-flash","name":"Gemini 3.5 Flash","arena":{"model":"Gemini 3.5 Flash (High)","organization":"google","licenseModel":"Proprietary","rating":1481.983653833525,"ratingLower":1478.1173211730365,"ratingUpper":1485.8499864940134,"votes":48479,"rank":18,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":92.803,"unit":"percent","model":"gemini-3.5-flash_high","organization":"Google DeepMind","date":"2026-05-19","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":79.3388,"unit":"percent","model":"gemini-3.5-flash_high","organization":"Google DeepMind","date":"2026-05-19","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":154.88,"unit":"eci","model":"Gemini 3.5 Flash","organization":"Google DeepMind","date":"2026-05-19","ciLow":152.91,"ciHigh":157.41,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":144.25711968705517,"valueRaw":207.9977},{"slug":"google-gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite","arena":{"model":"Gemini 3.1 Flash-Lite Preview","organization":"google","licenseModel":"Proprietary","rating":1415.7886462306226,"ratingLower":1412.1746967330123,"ratingUpper":1419.4025957282329,"votes":64188,"rank":131,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":74.2424,"unit":"percent","model":"gemini-3.1-flash-lite_low","organization":"Google","date":"2026-03-03","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":144.26,"unit":"eci","model":"Gemini 3.1 Flash-Lite","organization":"Google","date":"2026-03-03","ciLow":142.31,"ciHigh":145.73,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":1192.2431},{"slug":"mistral-mistral-medium-2604","name":"Mistral Medium 3.5","arena":{"model":"Mistral Medium 3.5","organization":"mistral","licenseModel":"Modified MIT","rating":1420.874599859863,"ratingLower":1414.4993997859438,"ratingUpper":1427.2497999337827,"votes":11785,"rank":113,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":141.36,"unit":"eci","model":"Mistral Medium 3.5","organization":"Mistral AI","date":"2026-04-28","ciLow":138.5,"ciHigh":144.33,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":236.8124},{"slug":"mistral-mistral-medium-latest","name":"Mistral Medium (latest)","arena":{"model":"Mistral Medium","organization":"mistral","licenseModel":"Proprietary","rating":1165.161913908152,"ratingLower":1159.7425359935035,"ratingUpper":1170.5812918228003,"votes":34550,"rank":337,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":194.1937},{"slug":"openai-gpt-5-5","name":"GPT-5.5","arena":{"model":"GPT-5.5 (High)","organization":"openai","licenseModel":"Proprietary","rating":1471.3531520551614,"ratingLower":1467.6630516186046,"ratingUpper":1475.0432524917182,"votes":69340,"rank":30,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.6566,"unit":"percent","model":"gpt-5.5_low","organization":"OpenAI","date":"2026-04-23","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":159.68,"unit":"eci","model":"GPT-5.5","organization":"OpenAI","date":"2026-04-23","ciLow":157.33,"ciHigh":163.67,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":100,"valueRaw":61.9517},{"slug":"nvidia-moonshotai-kimi-k2-6","name":"Kimi K2.6","arena":{"model":"Kimi K2.6","organization":"moonshot","licenseModel":"Modified MIT","rating":1455.465643908377,"ratingLower":1451.0568613881362,"ratingUpper":1459.8744264286177,"votes":40014,"rank":44,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.7828,"unit":"percent","model":"kimi-k2.6","organization":"Moonshot","date":"2026-04-20","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":76.6529,"unit":"percent","model":"kimi-k2.6","organization":"Moonshot","date":"2026-04-20","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":150.94,"unit":"eci","model":"Kimi K2.6","organization":"Moonshot","date":"2026-04-20","ciLow":149.04,"ciHigh":152.72,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-6-max-preview","name":"Qwen3.6 Max Preview","arena":{"model":"Qwen3.6-Max-Preview","organization":"alibaba","licenseModel":"Proprietary","rating":1446.6248542209469,"ratingLower":1438.4631496897603,"ratingUpper":1454.7865587521335,"votes":5427,"rank":58,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":87.3737,"unit":"percent","model":"qwen3.6-max-preview","organization":"Alibaba","date":"2026-04-20","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":76.6529,"unit":"percent","model":"qwen3.6-max-preview","organization":"Alibaba","date":"2026-04-20","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":null,"valueIndex":79.90887744138539,"valueRaw":234.2712},{"slug":"xai-grok-4-3","name":"Grok 4.3","arena":{"model":"Grok 4.3","organization":"xai","licenseModel":"Proprietary","rating":1396.8338505555755,"ratingLower":1393.2241275297029,"ratingUpper":1400.443573581448,"votes":71347,"rank":160,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":88.8258,"unit":"percent","model":"grok-4.3_high","organization":"xAI","date":"2026-04-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":638.5526},{"slug":"anthropic-claude-opus-4-7","name":"Claude Opus 4.7","arena":{"model":"Claude Opus 4.7 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1489.6856820412977,"ratingLower":1485.9475479420455,"ratingUpper":1493.42381614055,"votes":65131,"rank":13,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":90.1515,"unit":"percent","model":"claude-opus-4-7_xhigh","organization":"Anthropic","date":"2026-04-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":83.4711,"unit":"percent","model":"claude-opus-4-7_max","organization":"Anthropic","date":"2026-04-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":156.79,"unit":"eci","model":"Claude Opus 4.7","organization":"Anthropic","date":"2026-04-16","ciLow":154.91,"ciHigh":159.19,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":138.27791285370614,"valueRaw":74.4843},{"slug":"meta-muse-spark-1-1","name":"Muse Spark 1.1","arena":{"model":"Muse Spark 1.1","organization":"meta","licenseModel":"Proprietary","rating":1478.3153249630336,"ratingLower":1474.1606988041824,"ratingUpper":1482.4699511218848,"votes":44815,"rank":22,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":154.05,"unit":"eci","model":"Muse Spark 1.1","organization":"Meta AI","date":"2026-07-09","ciLow":151.73,"ciHigh":156.18,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":151.48515542970586,"valueRaw":422.3758},{"slug":"alibaba-qwen3-6-plus","name":"Qwen3.6 Plus","arena":{"model":"Qwen3.6-Plus","organization":"alibaba","licenseModel":"Proprietary","rating":1436.3075246226429,"ratingLower":1432.1969853527721,"ratingUpper":1440.4180638925136,"votes":48129,"rank":84,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":88.3838,"unit":"percent","model":"qwen3.6-plus","organization":"Alibaba","date":"2026-03-31","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":57.8512,"unit":"percent","model":"qwen3.6-plus","organization":"Alibaba","date":"2026-03-31","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":null,"valueIndex":79.3866973774216,"valueRaw":604.7611},{"slug":"openai-gpt-5-4-mini","name":"GPT-5.4 mini","arena":{"model":"GPT-5.4 mini (High)","organization":"openai","licenseModel":"Proprietary","rating":1411.594766571372,"ratingLower":1407.8779238409222,"ratingUpper":1415.311609301822,"votes":63442,"rank":138,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":148.7,"unit":"eci","model":"GPT-5.4 Mini","organization":"OpenAI","date":"2026-03-17","ciLow":146.87,"ciHigh":150.47,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":396.2371},{"slug":"openai-gpt-5-4-nano","name":"GPT-5.4 nano","arena":{"model":"GPT-5.4 nano (High)","organization":"openai","licenseModel":"Proprietary","rating":1371.9997760467822,"ratingLower":1368.2449087851498,"ratingUpper":1375.7546433084146,"votes":62384,"rank":183,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.03,"unit":"eci","model":"GPT-5.4 Nano","organization":"OpenAI","date":"2026-03-17","ciLow":143.63,"ciHigh":148.15,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":1389.3669},{"slug":"openai-gpt-5-4","name":"GPT-5.4","arena":{"model":"GPT-5.4 (High)","organization":"openai","licenseModel":"Proprietary","rating":1469.062922020157,"ratingLower":1465.328097529004,"ratingUpper":1472.7977465113102,"votes":64755,"rank":33,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":157.31,"unit":"eci","model":"GPT-5.4","organization":"OpenAI","date":"2026-03-05","ciLow":155.38,"ciHigh":159.8,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":109.49382497272313,"valueRaw":123.7106},{"slug":"alibaba-qwen3-5-122b-a10b","name":"Qwen3.5 122B-A10B","arena":{"model":"Qwen3.5-122B-A10B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1417.464261180235,"ratingLower":1413.2044230538945,"ratingUpper":1421.7240993065755,"votes":29731,"rank":124,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":566.9857},{"slug":"alibaba-qwen3-5-27b","name":"Qwen3.5 27B","arena":{"model":"Qwen3.5-27B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1408.906793675864,"ratingLower":1404.6378655668948,"ratingUpper":1413.1757217848333,"votes":28663,"rank":142,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":751.417},{"slug":"alibaba-qwen3-5-flash","name":"Qwen3.5 Flash","arena":{"model":"Qwen3.5-Flash","organization":"alibaba","licenseModel":"Proprietary","rating":1396.9459127365144,"ratingLower":1393.2992803265713,"ratingUpper":1400.5925451464573,"votes":61778,"rank":159,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":82.3232,"unit":"percent","model":"qwen3.5-flash","organization":"Alibaba","date":"2026-02-25","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":4298.2951},{"slug":"alibaba-qwen3-5-35b-a3b","name":"Qwen3.5 35B-A3B","arena":{"model":"Qwen3.5-35B-A3B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1394.610252258565,"ratingLower":1390.4069606330902,"ratingUpper":1398.8135438840397,"votes":30472,"rank":163,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":83.4596,"unit":"percent","model":"qwen3.5-35b-a3b","organization":"Alibaba","date":"2026-02-24","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":142.49,"unit":"eci","model":"Qwen3.5-35B-A3B","organization":"Alibaba","date":"2026-02-24","ciLow":140.42,"ciHigh":144.98,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":892.5506},{"slug":"google-gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","arena":{"model":"Gemini 3.1 Pro Preview","organization":"google","licenseModel":"Proprietary","rating":1480.065736470125,"ratingLower":1477.1374902637838,"ratingUpper":1482.9939826764664,"votes":129523,"rank":19,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":94.1,"unit":"percent","model":"gemini-3.1-pro-preview","organization":"Google DeepMind","date":"2026-02-19","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":155.34,"unit":"eci","model":"Gemini 3.1 Pro","organization":"Google DeepMind","date":"2026-02-19","ciLow":153.32,"ciHigh":158.13,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":134.86472726195967,"valueRaw":155.7964},{"slug":"google-gemini-pro-latest","name":"Gemini Pro Latest","arena":{"model":"Gemini Pro (Dev API)","organization":"google","licenseModel":"Proprietary","rating":1148.8717109161578,"ratingLower":1141.678757397636,"ratingUpper":1156.0646644346796,"votes":18354,"rank":345,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":120.9339},{"slug":"anthropic-claude-sonnet-4-6","name":"Claude Sonnet 4.6","arena":{"model":"Claude Sonnet 4.6","organization":"anthropic","licenseModel":"Proprietary","rating":1457.747662688473,"ratingLower":1454.2524958818224,"ratingUpper":1461.2428294951233,"votes":70931,"rank":41,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":83.3333,"unit":"percent","model":"claude-sonnet-4-6_medium","organization":"Anthropic","date":"2026-02-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":75.2066,"unit":"percent","model":"claude-sonnet-4-6","organization":"Anthropic","date":"2026-02-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":152.79,"unit":"eci","model":"Claude Sonnet 4.6","organization":"Anthropic","date":"2026-02-17","ciLow":150.2,"ciHigh":155.06,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":87.77757577803422,"valueRaw":121.479},{"slug":"alibaba-qwen3-5-397b-a17b","name":"Qwen3.5 397B-A17B","arena":{"model":"Qwen3.5-397B-A17B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1437.4909107334572,"ratingLower":1434.438319282118,"ratingUpper":1440.5435021847964,"votes":95123,"rank":81,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":85.8586,"unit":"percent","model":"qwen3.5-397b-a17b","organization":"Alibaba","date":"2026-02-13","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.8,"unit":"eci","model":"Qwen3.5 397B-A17B","organization":"Alibaba","date":"2026-02-13","ciLow":145.24,"ciHigh":148.86,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":77.99376521304663,"valueRaw":504.3828},{"slug":"anthropic-claude-opus-4-6","name":"Claude Opus 4.6","arena":{"model":"Claude Opus 4.6 (High)","organization":"anthropic","licenseModel":"Proprietary","rating":1501.2307833641096,"ratingLower":1497.9449480275705,"ratingUpper":1504.5166187006487,"votes":82619,"rank":7,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":88.3838,"unit":"percent","model":"claude-opus-4-6_max","organization":"Anthropic","date":"2026-02-05","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":75.6198,"unit":"percent","model":"claude-opus-4-6","organization":"Anthropic","date":"2026-02-05","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":155.66,"unit":"eci","model":"Claude Opus 4.6","organization":"Anthropic","date":"2026-02-05","ciLow":153.82,"ciHigh":158.07,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":160.22184224486546,"valueRaw":75.0615},{"slug":"google-gemini-3-flash-preview","name":"Gemini 3 Flash Preview","arena":{"model":"Gemini 3 Flash","organization":"google","licenseModel":"Proprietary","rating":1465.6825049647325,"ratingLower":1461.3673677739346,"ratingUpper":1469.9976421555305,"votes":31311,"rank":36,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":83.2071,"unit":"percent","model":"gemini-3-flash-preview","organization":"Google DeepMind","date":"2025-12-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":75.4132,"unit":"percent","model":"gemini-3-flash-preview","organization":"Google DeepMind","date":"2025-12-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":151.88,"unit":"eci","model":"Gemini 3 Flash","organization":"Google DeepMind","date":"2025-12-17","ciLow":150.44,"ciHigh":153.64,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":135.22011767143337,"valueRaw":617.1295},{"slug":"openai-gpt-5-2","name":"GPT-5.2","arena":{"model":"GPT-5.2 Chat (20260210)","organization":"openai","licenseModel":"Proprietary","rating":1438.315501204859,"ratingLower":1434.3195281137228,"ratingUpper":1442.3114742959954,"votes":35991,"rank":79,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":153.66,"unit":"eci","model":"GPT-5.2","organization":"OpenAI","date":"2025-12-11","ciLow":152.05,"ciHigh":155.42,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":52.69464661399539,"valueRaw":131.5031},{"slug":"anthropic-claude-opus-4-5","name":"Claude Opus 4.5 (latest)","arena":{"model":"Claude Opus 4.5 (20251101)","organization":"anthropic","licenseModel":"Proprietary","rating":1450.9727066490896,"ratingLower":1447.8660699443176,"ratingUpper":1454.0793433538613,"votes":72863,"rank":50,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":150.11,"unit":"eci","model":"Claude Opus 4.5","organization":"Anthropic","date":"2025-11-24","ciLow":147.81,"ciHigh":153.01,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":64.69563975145527,"valueRaw":72.5486},{"slug":"openai-gpt-5-1","name":"GPT-5.1","arena":{"model":"GPT-5.1 (High)","organization":"openai","licenseModel":"Proprietary","rating":1442.8107619597724,"ratingLower":1439.1378210477494,"ratingUpper":1446.4837028717955,"votes":41651,"rank":67,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":149.76,"unit":"eci","model":"GPT-5.1","organization":"OpenAI","date":"2025-11-13","ciLow":148.36,"ciHigh":151.74,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":67.96050399769835,"valueRaw":184.6798},{"slug":"anthropic-claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","arena":{"model":"Claude Haiku 4.5 (20251001)","organization":"anthropic","licenseModel":"Proprietary","rating":1396.9803937795095,"ratingLower":1394.593518391101,"ratingUpper":1399.3672691679178,"votes":151130,"rank":158,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":142.15,"unit":"eci","model":"Claude Haiku 4.5","organization":"Anthropic","date":"2025-10-15","ciLow":139.4,"ciHigh":144.06,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":349.2451},{"slug":"anthropic-claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","arena":{"model":"Claude Sonnet 4.5 (20250929)","organization":"anthropic","licenseModel":"Proprietary","rating":1438.4915581165496,"ratingLower":1435.6408928019787,"ratingUpper":1441.3422234311206,"votes":82669,"rank":78,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.74,"unit":"eci","model":"Claude Sonnet 4.5","organization":"Anthropic","date":"2025-09-29","ciLow":145.03,"ciHigh":148.31,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":51.17723878141203,"valueRaw":119.8743},{"slug":"alibaba-qwen3-max","name":"Qwen3 Max","arena":{"model":"Qwen3-Max-Preview","organization":"alibaba","licenseModel":"Proprietary","rating":1438.9548456924094,"ratingLower":1434.448942320851,"ratingUpper":1443.460749063968,"votes":27375,"rank":77,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":142.33,"unit":"eci","model":"Qwen3-Max","organization":"Alibaba","date":"2025-09-24","ciLow":140.11,"ciHigh":145.21,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":70.36241657018273,"valueRaw":299.7823},{"slug":"alibaba-qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","arena":{"model":"Qwen3-Next-80B-A3B-Instruct","organization":"alibaba","licenseModel":"Apache 2.0","rating":1417.0036960942543,"ratingLower":1412.270213474437,"ratingUpper":1421.7371787140714,"votes":22763,"rank":127,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":872.0023},{"slug":"cohere-command-a-reasoning-08-2025","name":"Command A Reasoning","arena":{"model":"Command A (03-2025)","organization":"cohere","licenseModel":"CC-BY-NC-4.0","rating":1330.970709042806,"ratingLower":1327.5219263752335,"ratingUpper":1334.4194917103785,"votes":55769,"rank":226,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":163.8118},{"slug":"mistral-mistral-medium-2508","name":"Mistral Medium 3.1","arena":{"model":"Mistral Medium 3.1 (2508)","organization":"mistral","licenseModel":"Proprietary","rating":1424.220255518691,"ratingLower":1421.6571201775575,"ratingUpper":1426.7833908598243,"votes":95291,"rank":108,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":64.30299373993256,"valueRaw":890.1377},{"slug":"openai-gpt-5-mini","name":"GPT-5 Mini","arena":{"model":"GPT-5 mini (High)","organization":"openai","licenseModel":"Proprietary","rating":1373.2698448489189,"ratingLower":1368.7134667846703,"ratingUpper":1377.8262229131676,"votes":26805,"rank":181,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":145.34,"unit":"eci","model":"GPT-5 mini","organization":"OpenAI","date":"2025-08-07","ciLow":143.33,"ciHigh":147.11,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":878.8927},{"slug":"openai-gpt-5","name":"GPT-5","arena":{"model":"GPT-5 (High)","organization":"openai","licenseModel":"Proprietary","rating":1406.1896566185533,"ratingLower":1401.7699027852443,"ratingUpper":1410.609410451862,"votes":31717,"rank":147,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":150,"unit":"eci","model":"GPT-5","organization":"OpenAI","date":"2025-08-07","ciLow":null,"ciHigh":null,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":179.9923},{"slug":"openai-gpt-5-nano","name":"GPT-5 Nano","arena":{"model":"GPT-5 nano (High)","organization":"openai","licenseModel":"Proprietary","rating":1319.7920379748032,"ratingLower":1312.9468398298236,"ratingUpper":1326.6372361197828,"votes":8135,"rank":233,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":139.21,"unit":"eci","model":"GPT-5 nano","organization":"OpenAI","date":"2025-08-07","ciLow":134.11,"ciHigh":141.2,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":4223.3345},{"slug":"groq-openai-gpt-oss-120b","name":"GPT OSS 120B","arena":{"model":"gpt-oss-120b","organization":"openai","licenseModel":"Apache 2.0","rating":1365.5508637784203,"ratingLower":1361.2047732817482,"ratingUpper":1369.8969542750926,"votes":30213,"rank":193,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":139.79,"unit":"eci","model":"gpt-oss-120b","organization":"OpenAI","date":"2025-08-05","ciLow":135.57,"ciHigh":142.12,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":2801.13},{"slug":"nvidia-openai-gpt-oss-20b","name":"GPT OSS 20B","arena":{"model":"gpt-oss-20b","organization":"openai","licenseModel":"Apache 2.0","rating":1287.560241922985,"ratingLower":1281.1718742803828,"ratingUpper":1293.948609565587,"votes":10417,"rank":261,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":45.9596,"unit":"percent","model":"gpt-oss-20b_high","organization":"OpenAI","date":"2025-08-05","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":137.7,"unit":"eci","model":"gpt-oss-20b","organization":"OpenAI","date":"2025-08-05","ciLow":132.2,"ciHigh":139.58,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"mistral-mistral-small-2506","name":"Mistral Small 3.2","arena":{"model":"Mistral Small 3.2 (2506)","organization":"mistral","licenseModel":"Apache 2.0","rating":1338.2266889521263,"ratingLower":1333.0383634032798,"ratingUpper":1343.4150145009726,"votes":17459,"rank":218,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":5352.9068},{"slug":"google-gemini-2-5-flash","name":"Gemini 2.5 Flash","arena":{"model":"Gemini 2.5 Flash","organization":"google","licenseModel":"Proprietary","rating":1416.9270591291302,"ratingLower":1414.5238494006003,"ratingUpper":1419.3302688576603,"votes":125492,"rank":128,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":139.84,"unit":"eci","model":"Gemini 2.5 Flash (Apr 2025)","organization":"Google DeepMind","date":"2025-04-17","ciLow":135.83,"ciHigh":141.9,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":726.6293},{"slug":"google-gemini-2-5-pro","name":"Gemini 2.5 Pro","arena":{"model":"Gemini 2.5 Pro","organization":"google","licenseModel":"Proprietary","rating":1457.7356179759422,"ratingLower":1455.301389467933,"ratingUpper":1460.1698464839515,"votes":125320,"rank":42,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":85.2904,"unit":"percent","model":"gemini-2.5-pro","organization":"Google DeepMind","date":"2025-06-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":57.5569,"unit":"percent","model":"gemini-2.5-pro","organization":"Google DeepMind","date":"2025-06-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":142.15,"unit":"eci","model":"Gemini 2.5 Pro (May 2025)","organization":"Google DeepMind","date":"2025-05-06","ciLow":138.39,"ciHigh":145.09,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":96.32837859962353,"valueRaw":186.5902},{"slug":"google-gemini-2-5-flash-lite","name":"Gemini 2.5 Flash-Lite","arena":{"model":"Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)","organization":"google","licenseModel":"Proprietary","rating":1379.3020689414195,"ratingLower":1375.907134955563,"ratingUpper":1382.6970029272761,"votes":47428,"rank":175,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":133.82,"unit":"eci","model":"Gemini 2.5 Flash-Lite (Jun 2025)","organization":"Google DeepMind","date":"2025-06-17","ciLow":130.27,"ciHigh":136.17,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":4244.0064},{"slug":"nvidia-mistralai-mistral-medium-3-instruct","name":"Mistral Medium 3","arena":{"model":"Mistral Medium 3 (2505)","organization":"mistral","licenseModel":"Proprietary","rating":1370.180976447334,"ratingLower":1365.4959306382061,"ratingUpper":1374.8660222564617,"votes":32783,"rank":185,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":134.02,"unit":"eci","model":"Mistral Medium 3","organization":"Mistral AI","date":"2025-05-07","ciLow":130.38,"ciHigh":135.36,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"openai-o3","name":"o3","arena":{"model":"o3 (2025-04-16)","organization":"openai","licenseModel":"Proprietary","rating":1409.950725318527,"ratingLower":1406.3441792074827,"ratingUpper":1413.5572714295713,"votes":58903,"rank":141,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.73,"unit":"eci","model":"o3","organization":"OpenAI","date":"2025-04-16","ciLow":144.83,"ciHigh":148.52,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":216.9155},{"slug":"openai-o4-mini","name":"o4-mini","arena":{"model":"o4-mini (2025-04-16)","organization":"openai","licenseModel":"Proprietary","rating":1353.35861147047,"ratingLower":1349.402693836287,"ratingUpper":1357.3145291046528,"votes":44847,"rank":205,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":145.46,"unit":"eci","model":"o4-mini","organization":"OpenAI","date":"2025-04-16","ciLow":142.9,"ciHigh":147.21,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":378.5618},{"slug":"nvidia-nvidia-llama-3-1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","arena":{"model":"Llama 3.1 Nemotron 70B Instruct","organization":"nvidia","licenseModel":"Llama 3.1","rating":1282.6790891670053,"ratingLower":1274.9760690349124,"ratingUpper":1290.3821092990981,"votes":7140,"rank":267,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-4-1","name":"GPT-4.1","arena":{"model":"GPT-4.1 (2025-04-14)","organization":"openai","licenseModel":"Proprietary","rating":1382.8488028357738,"ratingLower":1379.1560338920256,"ratingUpper":1386.5415717795217,"votes":50293,"rank":173,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":136.65,"unit":"eci","model":"GPT-4.1","organization":"OpenAI","date":"2025-04-14","ciLow":133.57,"ciHigh":138.34,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":212.746},{"slug":"openai-gpt-4-1-mini","name":"GPT-4.1 mini","arena":{"model":"GPT-4.1 mini (2025-04-14)","organization":"openai","licenseModel":"Proprietary","rating":1340.5666157244068,"ratingLower":1336.2628252697548,"ratingUpper":1344.870406179059,"votes":38697,"rank":212,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":134.89,"unit":"eci","model":"GPT-4.1 mini","organization":"OpenAI","date":"2025-04-14","ciLow":130.97,"ciHigh":136.49,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":1031.2051},{"slug":"openai-gpt-4-1-nano","name":"GPT-4.1 nano","arena":{"model":"GPT-4.1 nano (2025-04-14)","organization":"openai","licenseModel":"Proprietary","rating":1284.8261977306229,"ratingLower":1277.1848248287668,"ratingUpper":1292.467570632479,"votes":6103,"rank":265,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":129.54,"unit":"eci","model":"GPT-4.1 nano","organization":"OpenAI","date":"2025-04-14","ciLow":123.33,"ciHigh":131.82,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":3953.3114},{"slug":"alibaba-qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","arena":{"model":"Qwen3-VL-235B-A22B-Instruct","organization":"alibaba","licenseModel":"Apache 2.0","rating":1420.0290643658057,"ratingLower":1413.528219529607,"ratingUpper":1426.5299092020043,"votes":11317,"rank":115,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":624.1886},{"slug":"alibaba-qwen3-32b","name":"Qwen3 32B","arena":{"model":"Qwen3-32B","organization":"alibaba","licenseModel":"Apache 2.0","rating":1340.1211630634632,"ratingLower":1330.8118827943065,"ratingUpper":1349.43044333262,"votes":3926,"rank":214,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":65.7197,"unit":"percent","model":"Qwen3-32B","organization":"Alibaba","date":"2025-04-29","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":138.42,"unit":"eci","model":"Qwen3-32B","organization":"Alibaba","date":"2025-04-29","ciLow":134.68,"ciHigh":140.22,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":589.0642},{"slug":"alibaba-qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","arena":{"model":"Qwen3-Coder-480B-A35B-Instruct","organization":"alibaba","licenseModel":"Apache 2.0","rating":1356.5419145541011,"ratingLower":1351.5510315335002,"ratingUpper":1361.5327975747023,"votes":25190,"rank":201,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":226.0903},{"slug":"alibaba-qwen3-235b-a22b","name":"Qwen3 235B-A22B","arena":{"model":"Qwen3-235B-A22B-Instruct (2507)","organization":"alibaba","licenseModel":"Apache 2.0","rating":1419.1840966116722,"ratingLower":1416.6497888734414,"ratingUpper":1421.7184043499028,"votes":98119,"rank":120,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":70.7071,"unit":"percent","model":"qwen3-235b-a22b","organization":"Alibaba","date":"2025-04-29","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":138.78,"unit":"eci","model":"Qwen3-235B-A22B-Instruct (Jul 2025)","organization":"Alibaba","date":"2025-07-25","ciLow":135.49,"ciHigh":140.82,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":623.8172},{"slug":"mistral-magistral-medium-latest","name":"Magistral Medium (latest)","arena":{"model":"Magistral Medium (2506)","organization":"mistral","licenseModel":"Proprietary","rating":1254.9337276187853,"ratingLower":1248.4967800173674,"ratingUpper":1261.370675220203,"votes":11510,"rank":295,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":295.2785},{"slug":"nvidia-google-gemma-3-4b-it","name":"Gemma 3 4B IT","arena":{"model":"Gemma 3 4B IT","organization":"google","licenseModel":"Gemma","rating":1290.8320521334824,"ratingLower":1281.6054314664968,"ratingUpper":1300.058672800468,"votes":4171,"rank":256,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":23.2323,"unit":"percent","model":"gemma-3-4b-it","organization":"Google DeepMind","date":"2025-03-12","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-google-gemma-3-12b-it","name":"Gemma 3 12B IT","arena":{"model":"Gemma 3 12B IT","organization":"google","licenseModel":"Gemma","rating":1334.249202931214,"ratingLower":1324.8758064220112,"ratingUpper":1343.622599440417,"votes":3829,"rank":222,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":39.4571,"unit":"percent","model":"gemma-3-12b-it","organization":"Google DeepMind","date":"2025-03-12","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-o3-mini","name":"o3-mini","arena":{"model":"o3-mini (High)","organization":"openai","licenseModel":"Proprietary","rating":1336.609614028419,"ratingLower":1331.362824346854,"ratingUpper":1341.8564037099839,"votes":18589,"rank":220,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":140.2,"unit":"eci","model":"o3-mini","organization":"OpenAI","date":"2025-01-31","ciLow":137.03,"ciHigh":141.8,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":373.8768},{"slug":"groq-llama-3-3-70b-versatile","name":"Llama 3.3 70B","arena":{"model":"Llama 3.3 70B Instruct","organization":"meta","licenseModel":"Llama-3.3","rating":1274.285965923836,"ratingLower":1270.804413562172,"ratingUpper":1277.7675182855005,"votes":54495,"rank":277,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":47.4432,"unit":"percent","model":"Llama-3.3-70B-Instruct","organization":"Meta AI","date":"2024-12-06","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":{"metric":"livebench","score":50.16,"unit":"score","model":"Llama-3.3-70B-Instruct","organization":"Meta AI","date":"2024-12-06","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"sweBench":null,"eci":{"metric":"eci","score":127.33,"unit":"eci","model":"Llama 3.3 70B","organization":"Meta AI","date":"2024-12-06","ciLow":122.51,"ciHigh":129.38,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":1722.0081},{"slug":"openai-o1","name":"o1","arena":{"model":"o1 (2024-12-17)","organization":"openai","licenseModel":"Proprietary","rating":1365.845173695522,"ratingLower":1361.3713620712633,"ratingUpper":1370.3189853197805,"votes":27807,"rank":192,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":134.57,"unit":"eci","model":"o1-preview","organization":"OpenAI","date":"2024-09-12","ciLow":130.76,"ciHigh":137.92,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":28.0173},{"slug":"openai-gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","arena":{"model":"GPT-4o (2024-05-13)","organization":"openai","licenseModel":"Proprietary","rating":1300.4601444573561,"ratingLower":1297.0266566232942,"ratingUpper":1303.893632291418,"votes":112881,"rank":248,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":128.69,"unit":"eci","model":"GPT-4o (Nov 2024)","organization":"OpenAI","date":"2024-11-20","ciLow":123.9,"ciHigh":131,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":160.0566},{"slug":"mistral-mistral-large-latest","name":"Mistral Large (latest)","arena":{"model":"Mistral Large (2411)","organization":"mistral","licenseModel":"MRL","rating":1265.3413076221038,"ratingLower":1260.9053129525098,"ratingUpper":1269.7773022916977,"votes":28073,"rank":285,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":122.12,"unit":"eci","model":"Mistral Large","organization":"Mistral AI","date":"2024-02-26","ciLow":114.75,"ciHigh":124.74,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":1012.273},{"slug":"mistral-mistral-large-2512","name":"Mistral Large 3","arena":{"model":"Mistral Large 3","organization":"mistral","licenseModel":"Apache 2.0","rating":1428.5392708938346,"ratingLower":1425.7278233831605,"ratingUpper":1431.3507184045088,"votes":85822,"rank":97,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":77.44369066807151,"valueRaw":1142.8314},{"slug":"cohere-c4ai-aya-expanse-32b","name":"Aya Expanse 32B","arena":{"model":"Aya Expanse 32B","organization":"cohere","licenseModel":"CC-BY-NC-4.0","rating":1224.032390706222,"ratingLower":1219.175078847811,"ratingUpper":1228.889702564633,"votes":27124,"rank":310,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":979.2259},{"slug":"mistral-ministral-8b-latest","name":"Ministral 8B (latest)","arena":{"model":"Ministral 8B (2410)","organization":"mistral","licenseModel":"MRL","rating":1190.9424248090766,"ratingLower":1181.9701570607867,"ratingUpper":1199.9146925573664,"votes":4781,"rank":325,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":7939.6162},{"slug":"cohere-command-r-plus-08-2024","name":"Command R+","arena":{"model":"Command R+ (08-2024)","organization":"cohere","licenseModel":"CC-BY-NC-4.0","rating":1228.922849655004,"ratingLower":1222.382026626237,"ratingUpper":1235.4636726837712,"votes":9866,"rank":303,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":119.2,"unit":"eci","model":"Command R+","organization":"Cohere,Cohere Labs (formerly Cohere for AI)","date":"2024-08-30","ciLow":110.3,"ciHigh":125.03,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":151.252},{"slug":"groq-llama-3-1-8b-instant","name":"Llama 3.1 8B","arena":{"model":"Llama 3.1 8B Instruct","organization":"meta","licenseModel":"Llama 3.1 Community","rating":1186.6021036613665,"ratingLower":1182.5024750324665,"ratingUpper":1190.7017322902666,"votes":49605,"rank":328,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":{"metric":"gpqa_diamond","score":26.9571,"unit":"percent","model":"Llama-3.1-8B-Instruct","organization":"Meta AI","date":"2024-07-23","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":116.47,"unit":"eci","model":"Llama 3.1-8B","organization":"Meta AI","date":"2024-07-23","ciLow":105.92,"ciHigh":121.64,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":16366.9256},{"slug":"openai-gpt-4o-mini","name":"GPT-4o mini","arena":{"model":"GPT-4o mini (2024-07-18)","organization":"openai","licenseModel":"Proprietary","rating":1286.4028017329636,"ratingLower":1282.881761799285,"ratingUpper":1289.923841666642,"votes":68705,"rank":264,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":126.46,"unit":"eci","model":"GPT-4o mini","organization":"OpenAI","date":"2024-07-18","ciLow":120.11,"ciHigh":128.49,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":2638.775},{"slug":"alibaba-qwen-max","name":"Qwen Max","arena":{"model":"Qwen-Max (0919)","organization":"alibaba","licenseModel":"Qwen","rating":1281.9062345544703,"ratingLower":1276.2351639281446,"ratingUpper":1287.577305180796,"votes":16478,"rank":269,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":246.5204},{"slug":"alibaba-qwen-plus","name":"Qwen Plus","arena":{"model":"Qwen-Plus (0125)","organization":"alibaba","licenseModel":"Proprietary","rating":1326.431463936993,"ratingLower":1318.1498261679906,"ratingUpper":1334.7131017059955,"votes":5819,"rank":231,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":1326.4315},{"slug":"openai-gpt-4-turbo","name":"GPT-4 Turbo","arena":{"model":"GPT-4 Turbo (2024-04-09)","organization":"openai","licenseModel":"Proprietary","rating":1271.7159794688914,"ratingLower":1267.8223279419603,"ratingUpper":1275.6096309958225,"votes":98114,"rank":280,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":126.43,"unit":"eci","model":"GPT-4 Turbo (Nov 2023)","organization":"OpenAI","date":"2024-01-25","ciLow":121.25,"ciHigh":128.46,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":50.8686},{"slug":"openai-gpt-4","name":"GPT-4","arena":{"model":"GPT-4 (0314)","organization":"openai","licenseModel":"Proprietary","rating":1206.0325771364037,"ratingLower":1201.302070116824,"ratingUpper":1210.7630841559835,"votes":54173,"rank":318,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":123.09,"unit":"eci","model":"GPT-4 (Jun 2023)","organization":"OpenAI","date":"2023-06-13","ciLow":116.85,"ciHigh":126.92,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":22.972},{"slug":"openai-gpt-3-5-turbo","name":"GPT-3.5-turbo","arena":{"model":"GPT-3.5 Turbo (0125)","organization":"openai","licenseModel":"Proprietary","rating":1124.9436605087742,"ratingLower":1120.2791553934087,"ratingUpper":1129.6081656241397,"votes":66207,"rank":355,"category":"overall","publishDate":"2026-10-20","source":{"name":"LMArena leaderboard dataset","license":"CC-BY-4.0","url":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","retrievedAt":"2026-10-23T02:38:47+00:00"}},"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":113.22,"unit":"eci","model":"GPT-3.5 Turbo (Jun 2023)","organization":"OpenAI","date":"2023-06-13","ciLow":105.21,"ciHigh":117.6,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":899.9549},{"slug":"deepseek-deepseek-flash","name":"DeepSeek V4.1 Flash 1017","arena":null,"gpqa":{"metric":"gpqa_diamond","score":93.1818,"unit":"percent","model":"deepseek-v4.1-flash-1017_max","organization":"DeepSeek","date":"2026-10-17","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"deepseek-deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-3-5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"anthropic-claude-haiku-5-5","name":"Claude Haiku 5.5","arena":null,"gpqa":{"metric":"gpqa_diamond","score":89.6465,"unit":"percent","model":"claude-haiku-5-5_max","organization":"Anthropic","date":"2026-10-07","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":159.32,"unit":"eci","model":"Claude Haiku 5.5","organization":"Anthropic","date":"2026-10-07","ciLow":156.19,"ciHigh":162.47,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-8-omni-flash","name":"Qwen3.8 Omni Flash","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-deepseek-ai-deepseek-v4-1-flash","name":"DeepSeek V4.1 Flash","arena":null,"gpqa":{"metric":"gpqa_diamond","score":89.8359,"unit":"percent","model":"deepseek-v4.1-flash_max","organization":"DeepSeek","date":"2026-09-09","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":155.93,"unit":"eci","model":"DeepSeek V4.1 Flash","organization":"DeepSeek","date":"2026-09-09","ciLow":153.68,"ciHigh":158.59,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"cohere-north-small-translate-09-2026","name":"North Small Translate","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"meta-muse-spark-1-3-contributor","name":"Muse Spark 1.3 Contributor","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-8-flash","name":"Qwen3.8 Flash","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-flash-latest","name":"Gemini Flash Latest","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-3-5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-meta-muse-glimmer-30b","name":"Muse Glimmer 30B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-daybreak-blue-latest","name":"Daybreak Blue","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-daybreak-red-latest","name":"Daybreak Red","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"meta-muse-spark-1-2-contributor","name":"Muse Spark 1.2 Contributor","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","arena":null,"gpqa":{"metric":"gpqa_diamond","score":91.0354,"unit":"percent","model":"deepseek-v4-flash-0731_max","organization":"DeepSeek","date":"2026-07-31","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":154.76,"unit":"eci","model":"DeepSeek V4 Flash 0731","organization":"DeepSeek","date":"2026-07-31","ciLow":152.06,"ciHigh":156.86,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-7-flash","name":"Qwen3.7 Flash","arena":null,"gpqa":{"metric":"gpqa_diamond","score":82.3232,"unit":"percent","model":"qwen3.7-flash","organization":"Alibaba","date":"2026-07-27","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":144.05,"unit":"eci","model":"Qwen3.7 Flash","organization":"Alibaba","date":"2026-07-27","ciLow":141.89,"ciHigh":145.92,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-6","name":"GPT-5.6","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-realtime-2-1","name":"GPT-Realtime-2.1","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-poolside-laguna-xs-2-1","name":"Laguna XS 2.1","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-1-flash-lite-image","name":"Nano Banana 2 Lite","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-labs-leanstral-1-5-1","name":"Leanstral 1.5","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-google-diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-north-mini-code-1-0","name":"North Mini Code","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-3-5-content-safety","name":"Nemotron 3.5 Content Safety","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-1-flash-image","name":"Nano Banana 2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-pro-image","name":"Nano Banana Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-command-a-plus-05-2026","name":"Command A Plus","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-6-flash","name":"Qwen3.6 Flash","arena":null,"gpqa":{"metric":"gpqa_diamond","score":83.3333,"unit":"percent","model":"qwen3.6-flash","organization":"Alibaba","date":"2026-04-27","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-5-pro","name":"GPT-5.5 Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":162.91,"unit":"eci","model":"GPT-5.5 Pro","organization":"OpenAI","date":"2026-04-23","ciLow":160.04,"ciHigh":166.6,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"groq-qwen-qwen3-6-27b","name":"Qwen3.6 27B","arena":null,"gpqa":{"metric":"gpqa_diamond","score":85.8586,"unit":"percent","model":"qwen3.6-27b","organization":"Alibaba","date":"2026-04-22","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":146.23,"unit":"eci","model":"Qwen3.6 27B","organization":"Alibaba","date":"2026-04-22","ciLow":144.13,"ciHigh":147.65,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-embedding-2","name":"Gemini Embedding 2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-image-2","name":"gpt-image-2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-deep-research-max-preview-04-2026","name":"Deep Research Max Preview (Apr-21-2026)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-6-35b-a3b","name":"Qwen3.6 35B-A3B","arena":null,"gpqa":{"metric":"gpqa_diamond","score":83.8384,"unit":"percent","model":"qwen3.6-35b-a3b","organization":"Alibaba","date":"2026-04-14","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"xai-grok-build-0-1","name":"Grok Build 0.1","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-synthetic-video-detector","name":"synthetic-video-detector","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-active-speaker-detection","name":"Active Speaker Detection","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-google-gemma-4-31b-it","name":"Gemma-4-31B-IT","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":142.99,"unit":"eci","model":"Gemma 4 31B IT","organization":"Google DeepMind","date":"2026-04-02","ciLow":140.34,"ciHigh":145.75,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-lyria-3-pro-preview","name":"Lyria 3 Pro Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-lyria-3-clip-preview","name":"Lyria 3 Clip Preview","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-mistral-small-latest","name":"Mistral Small (latest)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-mistral-small-2603","name":"Mistral Small 4","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-nemotron-voicechat","name":"nemotron-voicechat","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"xai-grok-4-20-0309-reasoning","name":"Grok 4.20 (Reasoning)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":152.11,"unit":"eci","model":"Grok 4.20","organization":"xAI","date":"2026-02-17","ciLow":149.57,"ciHigh":154.54,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"xai-grok-4-20-multi-agent-0309","name":"Grok 4.20 Multi-Agent","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-4-pro","name":"GPT-5.4 Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":159.57,"unit":"eci","model":"GPT-5.4 Pro","organization":"OpenAI","date":"2026-03-05","ciLow":157.1,"ciHigh":162.7,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-cosmos-transfer2-5-2b","name":"cosmos-transfer2.5-2b","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-3-1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-5-plus","name":"Qwen3.5 Plus","arena":null,"gpqa":{"metric":"gpqa_diamond","score":84.8485,"unit":"percent","model":"qwen3.5-plus","organization":"Alibaba","date":"2026-02-16","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-3-codex","name":"GPT-5.3 Codex","arena":null,"gpqa":null,"livebench":null,"sweBench":{"metric":"swe_bench_verified","score":74.7934,"unit":"percent","model":"gpt-5.3-codex_high","organization":"OpenAI","date":"2026-02-05","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"eci":{"metric":"eci","score":157.09,"unit":"eci","model":"GPT-5.3 Codex","organization":"OpenAI","date":"2026-02-05","ciLow":153.56,"ciHigh":161.38,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-3-codex-spark","name":"GPT-5.3 Codex Spark","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-black-forest-labs-flux-2-klein-4b","name":"FLUX.2 Klein 4B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"ai21-jamba-mini","name":"Jamba Mini","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-usdcode","name":"usdcode","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-llama-nemotron-embed-vl-1b-v2","name":"llama-nemotron-embed-vl-1b-v2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-llama-nemotron-rerank-vl-1b-v2","name":"llama-nemotron-rerank-vl-1b-v2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-riva-translate-4b-instruct-v1-1","name":"riva-translate-4b-instruct-v1_1","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-2-pro","name":"GPT-5.2 Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":156.33,"unit":"eci","model":"GPT-5.2 Pro","organization":"OpenAI","date":"2025-12-11","ciLow":153.89,"ciHigh":159.98,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"mistral-devstral-2512","name":"Devstral 2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-labs-devstral-small-2512","name":"Devstral Small 2","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-ministral-14b-2512","name":"Ministral 3 14B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-ministral-3b-2512","name":"Ministral 3 3B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-ministral-8b-2512","name":"Ministral 3 8B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-cosmos-reason2-8b","name":"Cosmos Reason2 8B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-streampetr","name":"streampetr","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"groq-openai-gpt-oss-safeguard-20b","name":"Safety GPT OSS 20B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-llama-3-1-nemotron-safety-guard-8b-v3","name":"llama-3.1-nemotron-safety-guard-8b-v3","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-2-5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview 10-2025","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-gpt-5-pro","name":"GPT-5 Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":150.59,"unit":"eci","model":"GPT-5 Pro","organization":"OpenAI","date":"2025-10-07","ciLow":148.94,"ciHigh":154.18,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-vl-plus","name":"Qwen3-VL Plus","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-livetranslate-flash-realtime","name":"Qwen3-LiveTranslate Flash Realtime","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-omni-flash","name":"Qwen3-Omni Flash","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-command-a-translate-08-2025","name":"Command A Translate","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-2-5-flash-image","name":"Nano Banana","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-qwen-qwen-image-edit","name":"Qwen Image Edit","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-qwen-qwen-image","name":"Qwen Image","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-command-a-vision-07-2025","name":"Command A Vision","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-codestral-2508","name":"Codestral 25.08","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-coder-flash","name":"Qwen3 Coder Flash","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-flash","name":"Qwen Flash","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-coder-plus","name":"Qwen3 Coder Plus","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-voxtral-small-2507","name":"Voxtral Small","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"ai21-jamba-large","name":"Jamba Large","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-o3-pro","name":"o3-pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":147.33,"unit":"eci","model":"o3-pro","organization":"OpenAI","date":"2025-06-10","ciLow":145.56,"ciHigh":150.1,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"nvidia-mistralai-magistral-small-2506","name":"Magistral Small 2506","arena":null,"gpqa":{"metric":"gpqa_diamond","score":56.0606,"unit":"percent","model":"magistral-small-2506","organization":"Mistral AI","date":"2025-06-10","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-black-forest-labs-flux-1-kontext-dev","name":"FLUX.1-Kontext-dev","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-magpie-tts-zeroshot","name":"magpie-tts-zeroshot","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-embedding-001","name":"Gemini Embedding 001","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-2-5-pro-preview-tts","name":"Gemini 2.5 Pro Preview TTS","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"google-gemini-2-5-flash-preview-tts","name":"Gemini 2.5 Flash Preview TTS","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-meta-llama-guard-4-12b","name":"Llama Guard 4 12B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"groq-meta-llama-llama-prompt-guard-2-22m","name":"Llama Prompt Guard 2 22M","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"groq-meta-llama-llama-prompt-guard-2-86m","name":"Prompt Guard 2 86M","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-llama-3-1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-8b","name":"Qwen3 8B","arena":null,"gpqa":{"metric":"gpqa_diamond","score":56.7551,"unit":"percent","model":"qwen3-8b","organization":"Alibaba","date":"2025-04-28","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":136.06,"unit":"eci","model":"Qwen3-8B","organization":"Alibaba","date":"2025-04-28","ciLow":129.92,"ciHigh":138.29,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen3-14b","name":"Qwen3 14B","arena":null,"gpqa":{"metric":"gpqa_diamond","score":63.7626,"unit":"percent","model":"qwen3-14b","organization":"Alibaba","date":"2025-04-29","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":138.15,"unit":"eci","model":"Qwen3-14B","organization":"Alibaba","date":"2025-04-29","ciLow":133.24,"ciHigh":140.03,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qvq-max","name":"QVQ Max","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-o1-pro","name":"o1-pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-bevformer","name":"bevformer","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-sparsedrive","name":"sparsedrive","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwq-plus","name":"QwQ Plus","arena":null,"gpqa":{"metric":"gpqa_diamond","score":65.404,"unit":"percent","model":"qwq-plus","organization":"Alibaba","date":"2025-04-08","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-command-r7b-arabic-02-2025","name":"Command R7B Arabic","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"perplexity-sonar-deep-research","name":"Perplexity Sonar Deep Research","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"groq-allam-2-7b","name":"ALLaM-2-7b","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-omni-turbo","name":"Qwen-Omni Turbo","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-mt-turbo","name":"Qwen-MT Turbo","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-mt-plus","name":"Qwen-MT Plus","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"cohere-command-r7b-12-2024","name":"Command R7B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-turbo","name":"Qwen Turbo","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-vl-ocr","name":"Qwen-VL OCR","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-studiovoice","name":"studiovoice","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-ministral-3b-latest","name":"Ministral 3B (latest)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":118.04,"unit":"eci","model":"Ministral 3B","organization":"Mistral AI","date":"2024-10-16","ciLow":106.31,"ciHigh":121.89,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"nvidia-meta-llama-3-2-11b-vision-instruct","name":"Llama 3.2 11b Vision Instruct","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-meta-llama-3-2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","arena":null,"gpqa":{"metric":"gpqa_diamond","score":41.0354,"unit":"percent","model":"Llama-3.2-90B-Vision-Instruct","organization":"Meta AI","date":"2024-09-24","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-pixtral-12b","name":"Pixtral 12B","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-black-forest-labs-flux-1-schnell","name":"FLUX.1-schnell","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-black-forest-labs-flux-1-dev","name":"FLUX.1-dev","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-usdvalidate","name":"usdvalidate","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-open-mistral-nemo","name":"Open Mistral Nemo","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-codestral-latest","name":"Codestral (latest)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-mistralai-mistral-7b-instruct-v0-3","name":"Mistral-7B-Instruct-v0.3","arena":null,"gpqa":{"metric":"gpqa_diamond","score":15.1831,"unit":"percent","model":"Mistral-7B-Instruct-v0.3","organization":"Mistral AI","date":"2024-05-27","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"livebench":null,"sweBench":null,"eci":{"metric":"eci","score":108.88,"unit":"eci","model":"Mistral 7B v0.3","organization":"Mistral AI","date":"2024-05-27","ciLow":98.25,"ciHigh":112.6,"source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"valueIndex":null,"valueRaw":null},{"slug":"nvidia-google-google-paligemma","name":"paligemma","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-vl-max","name":"Qwen-VL Max","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-nvidia-rerank-qa-mistral-4b","name":"rerank-qa-mistral-4b","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-text-embedding-3-small","name":"text-embedding-3-small","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-text-embedding-3-large","name":"text-embedding-3-large","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-vl-plus","name":"Qwen-VL Plus","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"perplexity-sonar-reasoning-pro","name":"Sonar Reasoning Pro","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"perplexity-sonar","name":"Sonar","arena":null,"gpqa":null,"livebench":{"metric":"livebench","score":46.88,"unit":"score","model":"sonar","organization":"","date":"","source":{"name":"Epoch AI Capabilities & benchmarking","license":"CC-BY-4.0","url":"https://epoch.ai/benchmarks","retrievedAt":"2026-10-23T02:38:47+00:00"}},"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"alibaba-qwen-plus-character-ja","name":"Qwen Plus Character (Japanese)","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"mistral-mistral-embed","name":"Mistral Embed","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"nvidia-openai-whisper-large-v3","name":"Whisper Large v3","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null},{"slug":"openai-text-embedding-ada-002","name":"text-embedding-ada-002","arena":null,"gpqa":null,"livebench":null,"sweBench":null,"eci":null,"valueIndex":null,"valueRaw":null}]}