{"category":"coding","generatedAt":"2026-10-03T19:34:30.053Z","leaderboards":[{"source":"code-arena","sourceName":"Code Arena","url":"https://arena.ai/leaderboard/code","category":"coding","fetchedAt":"2026-10-03T10:46:53.960Z","sourceUpdatedAt":"2026-10-01","entries":[{"rank":1,"model":"Claude Opus 5.5 Max","modelUrl":"https://www.anthropic.com/claude-opus-5-5","organization":"Anthropic","score":1815,"scoreUnit":"Elo","confidence":"+16/-16","votes":2062,"priceInput":4,"priceOutput":20,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":2,"model":"GPT-6 Astra Max","modelUrl":"https://openai.com/index/gpt-6-astra/","organization":"OpenAI","score":1788,"scoreUnit":"Elo","confidence":"+10/-10","votes":6123,"priceInput":10,"priceOutput":50,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":3,"model":"Claude Sonnet 5.5 xHigh","modelUrl":"https://www.anthropic.com/claude-sonnet-5-5","organization":"Anthropic","score":1786,"scoreUnit":"Elo","confidence":"+18/-18","votes":1531,"priceInput":2,"priceOutput":10,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":4,"model":"GPT-6.1 Sol Max","modelUrl":"https://openai.com/index/introducing-gpt-6-1-sol/","organization":"OpenAI","score":1758,"scoreUnit":"Elo","confidence":"+17/-17","votes":1620,"priceInput":2,"priceOutput":10,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":5,"model":"Claude Fable 5.1 Max","modelUrl":"https://www.anthropic.com/claude-fable-and-mythos-5-1","organization":"Anthropic","score":1749,"scoreUnit":"Elo","confidence":"+10/-10","votes":6318,"priceInput":10,"priceOutput":50,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":6,"model":"Claude Sonnet 5.5 High","modelUrl":"https://www.anthropic.com/claude-sonnet-5-5","organization":"Anthropic","score":1715,"scoreUnit":"Elo","confidence":"+13/-13","votes":2527,"priceInput":2,"priceOutput":10,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":7,"model":"Claude Opus 5 Max","modelUrl":"https://www.anthropic.com/news/claude-opus-5","organization":"Anthropic","score":1695,"scoreUnit":"Elo","confidence":"+6/-6","votes":16954,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":8,"model":"GPT-6 Sol Max","modelUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","organization":"OpenAI","score":1689,"scoreUnit":"Elo","confidence":"+11/-11","votes":3411,"priceInput":2,"priceOutput":10,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":9,"model":"Gemini 4 Argon High","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/","organization":"Google","score":1680,"scoreUnit":"Elo","confidence":"+13/-13","votes":2422,"priceInput":2,"priceOutput":10,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":10,"model":"Qwen 3.8 Max","modelUrl":"https://www.qwencloud.com/models/qwen3.8-max","organization":"Alibaba","score":1671,"scoreUnit":"Elo","confidence":"+12/-12","votes":3454,"priceInput":2,"priceOutput":6,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":11,"model":"Qwen 3.8 Max 0902","modelUrl":"https://www.qianwenai.com/models/qwen3.8-max-0902","organization":"Alibaba","score":1670,"scoreUnit":"Elo","confidence":"+8/-8","votes":9485,"priceInput":2,"priceOutput":6,"metadata":{"license":"proprietary"}},{"rank":12,"model":"Claude Opus 5 High","modelUrl":"https://www.anthropic.com/news/claude-opus-5","organization":"Anthropic","score":1660,"scoreUnit":"Elo","confidence":"+6/-6","votes":21506,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":13,"model":"Kimi K3 Max","modelUrl":"https://platform.kimi.ai/docs/guide/kimi-k3-quickstart","organization":"Moonshot AI","score":1658,"scoreUnit":"Elo","confidence":"+6/-6","votes":16513,"priceInput":3,"priceOutput":15,"contextWindow":1000000,"metadata":{"license":"kimi k3 license"}},{"rank":14,"model":"Muse Spark 1.3 Max","modelUrl":"https://developer.meta.com/ai/models/muse-spark/","organization":"Meta","score":1657,"scoreUnit":"Elo","confidence":"+9/-9","votes":7249,"priceInput":1.25,"priceOutput":4.25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":15,"model":"Grok 4.7 xHigh","modelUrl":"https://docs.x.ai/developers/models/grok-4.7","organization":"SpaceXAI","score":1638,"scoreUnit":"Elo","confidence":"+12/-12","votes":3216,"priceInput":2,"priceOutput":6,"contextWindow":500000,"metadata":{"license":"proprietary"}},{"rank":16,"model":"Qwen 3.8 Flash Next","modelUrl":"https://qwen.ai/blog?id=qwen3.8-flash-next","organization":"Alibaba","score":1637,"scoreUnit":"Elo","confidence":"+9/-9","votes":6193,"priceInput":0.16,"priceOutput":0.47,"contextWindow":1000000,"metadata":{"license":"qwen-community-1.0"}},{"rank":17,"model":"Hy4 Preview","modelUrl":"https://hy.tencent.ai/research/hy4-preview","organization":"Tencent","score":1633,"scoreUnit":"Elo","confidence":"+9/-9","votes":5088,"priceInput":0.83,"priceOutput":2.5,"contextWindow":1000000,"metadata":{"license":"apache 2.0"}},{"rank":18,"model":"Claude Fable 5 High","modelUrl":"https://www.anthropic.com/news/claude-fable-5-mythos-5","organization":"Anthropic","score":1625,"scoreUnit":"Elo","confidence":"+6/-6","votes":14126,"priceInput":10,"priceOutput":50,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":19,"model":"Muse Spark 1.3 (xHigh)","modelUrl":"https://developer.meta.com/ai/models/muse-spark/","organization":"Meta","score":1624,"scoreUnit":"Elo","confidence":"+9/-9","votes":6326,"priceInput":1.25,"priceOutput":4.25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":20,"model":"GLM-5.3 Max","modelUrl":"https://z.ai/blog/glm-5.3","organization":"Z.AI","score":1623,"scoreUnit":"Elo","confidence":"+8/-8","votes":7658,"priceInput":1.4,"priceOutput":4.4,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":21,"model":"DeepSeek V4.1 Flash Max","modelUrl":"https://www.deepseek.com/en/news/deepseek-v4-1-flash/","organization":"DeepSeek","score":1620,"scoreUnit":"Elo","confidence":"+10/-10","votes":3960,"priceInput":0.3,"priceOutput":1.2,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":22,"model":"GPT-5.6 Sol xHigh (codex-harness)","modelUrl":"https://openai.com/index/gpt-5-6/","organization":"OpenAI","score":1620,"scoreUnit":"Elo","confidence":"+6/-6","votes":17128,"priceInput":4,"priceOutput":20,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":23,"model":"Grok 4.6 High","modelUrl":"https://docs.x.ai/developers/models/grok-4.6","organization":"SpaceXAI","score":1620,"scoreUnit":"Elo","confidence":"+8/-8","votes":8315,"priceInput":2,"priceOutput":6,"contextWindow":500000,"metadata":{"license":"proprietary"}},{"rank":24,"model":"MiMo V2.6 Pro","modelUrl":"https://mimo.xiaomi.com/mimo-v2-6","organization":"Xiaomi","score":1618,"scoreUnit":"Elo","confidence":"+12/-12","votes":2734,"priceInput":0.43,"priceOutput":0.87,"contextWindow":1100000,"metadata":{"license":"mit"}},{"rank":25,"model":"GLM-5.3 Flash","modelUrl":"https://z.ai/blog/glm-5.3","organization":"Z.AI","score":1616,"scoreUnit":"Elo","confidence":"+8/-8","votes":10355,"priceInput":0.06,"priceOutput":0.2,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":26,"model":"GLM-5.2 Max","modelUrl":"https://huggingface.co/zai-org/GLM-5.2","organization":"Z.AI","score":1605,"scoreUnit":"Elo","confidence":"+6/-6","votes":14729,"priceInput":1.4,"priceOutput":4.4,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":27,"model":"Gemini 3.7 Flash High","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/","organization":"Google","score":1592,"scoreUnit":"Elo","confidence":"+7/-7","votes":9624,"priceInput":0.75,"priceOutput":3.75,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":28,"model":"Qwen 3.8 27B","modelUrl":"https://huggingface.co/Qwen/Qwen3.8-27B","organization":"Alibaba","score":1591,"scoreUnit":"Elo","confidence":"+7/-7","votes":12388,"priceInput":0.4,"priceOutput":3,"metadata":{"license":"apache 2.0"}},{"rank":29,"model":"Gemini 3.8 Flash High","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/","organization":"Google","score":1583,"scoreUnit":"Elo","confidence":"+8/-8","votes":8524,"priceInput":0.75,"priceOutput":3.75,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":30,"model":"DeepSeek V4 Pro High 20260813","modelUrl":"https://api-docs.deepseek.com/updates/#date-2026-08-13","organization":"DeepSeek","score":1583,"scoreUnit":"Elo","confidence":"+9/-9","votes":4882,"priceInput":1.32,"priceOutput":3.96,"metadata":{"license":"mit"}},{"rank":31,"model":"DeepSeek V4 Flash High","modelUrl":"https://api-docs.deepseek.com/updates/#date-2026-07-31","organization":"DeepSeek","score":1581,"scoreUnit":"Elo","confidence":"+9/-9","votes":5040,"priceInput":0.3,"priceOutput":1.2,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":32,"model":"GPT-6 Luna Max","modelUrl":"https://openai.com/index/introducing-gpt-6-sol-and-luna/","organization":"OpenAI","score":1579,"scoreUnit":"Elo","confidence":"+9/-9","votes":6429,"priceInput":0.1,"priceOutput":0.5,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":33,"model":"Step 5 Preview High","modelUrl":"https://stepfun.ai/","organization":"Stepfun","score":1570,"scoreUnit":"Elo","confidence":"+13/-13","votes":2506,"metadata":{"license":"proprietary"}},{"rank":34,"model":"Claude Opus 4.7 High","modelUrl":"https://www.anthropic.com/news/claude-opus-4-7","organization":"Anthropic","score":1557,"scoreUnit":"Elo","confidence":"+6/-6","votes":17982,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":35,"model":"Claude Opus 4.8 High","modelUrl":"https://www.anthropic.com/news/claude-opus-4-8","organization":"Anthropic","score":1556,"scoreUnit":"Elo","confidence":"+6/-6","votes":18908,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":36,"model":"Claude Opus 4.7","modelUrl":"https://www.anthropic.com/news/claude-opus-4-7","organization":"Anthropic","score":1555,"scoreUnit":"Elo","confidence":"+6/-6","votes":18174,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":37,"model":"Grok 4.5","modelUrl":"https://docs.x.ai/developers/models/grok-4.5","organization":"SpaceXAI","score":1552,"scoreUnit":"Elo","confidence":"+7/-7","votes":11393,"priceInput":2,"priceOutput":6,"contextWindow":500000,"metadata":{"license":"proprietary"}},{"rank":38,"model":"Claude Opus 4.6 High","modelUrl":"https://www.anthropic.com/news/claude-opus-4-6","organization":"Anthropic","score":1546,"scoreUnit":"Elo","confidence":"+5/-5","votes":19519,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":39,"model":"Muse Spark 1.1","modelUrl":"https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/","organization":"Meta","score":1542,"scoreUnit":"Elo","confidence":"+8/-8","votes":8070,"priceInput":1.25,"priceOutput":4.25,"metadata":{"license":"proprietary"}},{"rank":40,"model":"Claude Sonnet 5 High","modelUrl":"https://www.anthropic.com/news/claude-sonnet-5","organization":"Anthropic","score":1539,"scoreUnit":"Elo","confidence":"+6/-6","votes":14130,"priceInput":2,"priceOutput":10,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":41,"model":"Claude Opus 4.6","modelUrl":"https://www.anthropic.com/news/claude-opus-4-6","organization":"Anthropic","score":1537,"scoreUnit":"Elo","confidence":"+5/-5","votes":20762,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":42,"model":"Gemini 3.6 Flash High","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/","organization":"Google","score":1536,"scoreUnit":"Elo","confidence":"+7/-7","votes":8823,"priceInput":0.75,"priceOutput":3.75,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":43,"model":"Claude Opus 4.8","modelUrl":"https://www.anthropic.com/news/claude-opus-4-8","organization":"Anthropic","score":1534,"scoreUnit":"Elo","confidence":"+6/-6","votes":17880,"priceInput":5,"priceOutput":25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":44,"model":"Muse Spark 1.2 (xHigh)","modelUrl":"https://developer.meta.com/ai/models/muse-spark/","organization":"Meta","score":1532,"scoreUnit":"Elo","confidence":"+14/-14","votes":2183,"priceInput":1.25,"priceOutput":4.25,"metadata":{"license":"proprietary"}},{"rank":45,"model":"Claude Sonnet 4.6","modelUrl":"https://www.anthropic.com/news/claude-sonnet-4-6","organization":"Anthropic","score":1521,"scoreUnit":"Elo","confidence":"+5/-5","votes":22960,"priceInput":1.5,"priceOutput":7.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":46,"model":"GPT-5.6 Terra xHigh (codex-harness)","modelUrl":"https://openai.com/index/gpt-5-6/","organization":"OpenAI","score":1519,"scoreUnit":"Elo","confidence":"+7/-7","votes":12526,"priceInput":2,"priceOutput":12,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":47,"model":"GPT-5.6 Luna xHigh (codex-harness)","modelUrl":"https://openai.com/index/gpt-5-6/","organization":"OpenAI","score":1518,"scoreUnit":"Elo","confidence":"+6/-6","votes":12776,"priceInput":0.2,"priceOutput":1.2,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":48,"model":"Seed 2.1 Pro Preview","modelUrl":"https://seed.bytedance.com/en/blog/seed-2-1-preview-model-release-on-arena","organization":"Bytedance","score":1517,"scoreUnit":"Elo","confidence":"+6/-6","votes":13312,"metadata":{"license":"proprietary"}},{"rank":49,"model":"Qwen 3.7 Max 20260517","modelUrl":"https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-max-2026-05-17&serviceSite=international","organization":"Alibaba","score":1515,"scoreUnit":"Elo","confidence":"+7/-7","votes":8922,"priceInput":1.48,"priceOutput":4.42,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":50,"model":"GPT-5.5 xHigh (codex-harness)","modelUrl":"https://openai.com/index/introducing-gpt-5-5/","organization":"OpenAI","score":1512,"scoreUnit":"Elo","confidence":"+6/-6","votes":15873,"priceInput":5,"priceOutput":30,"metadata":{"license":"proprietary"}},{"rank":51,"model":"Kimi K2.6","modelUrl":"https://www.kimi.com/blog/kimi-k2-6","organization":"Moonshot AI","score":1509,"scoreUnit":"Elo","confidence":"+7/-7","votes":10208,"priceInput":0.95,"priceOutput":4,"contextWindow":262100,"metadata":{"license":"modified mit"}},{"rank":52,"model":"GLM-5.1","modelUrl":"https://huggingface.co/zai-org/GLM-5.1","organization":"Z.AI","score":1508,"scoreUnit":"Elo","confidence":"+7/-7","votes":10797,"priceInput":1.4,"priceOutput":4.4,"contextWindow":202800,"metadata":{"license":"mit"}},{"rank":53,"model":"Hy3","modelUrl":"https://huggingface.co/tencent/Hy3","organization":"Tencent","score":1507,"scoreUnit":"Elo","confidence":"+9/-9","votes":5802,"priceInput":0.13,"priceOutput":0.53,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":54,"model":"Gemini 3.5 Flash High","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/","organization":"Google","score":1499,"scoreUnit":"Elo","confidence":"+7/-7","votes":9497,"priceInput":0.75,"priceOutput":4.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":55,"model":"Claude Opus 4.5 20251101 High 32K","modelUrl":"https://www.anthropic.com/news/claude-opus-4-5","organization":"Anthropic","score":1493,"scoreUnit":"Elo","confidence":"+8/-8","votes":11034,"priceInput":5,"priceOutput":25,"contextWindow":200000,"metadata":{"license":"proprietary"}},{"rank":56,"model":"Gemini 3.5 Flash Medium","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5/","organization":"Google","score":1490,"scoreUnit":"Elo","confidence":"+7/-7","votes":12256,"priceInput":0.75,"priceOutput":4.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":57,"model":"GPT-5.5 High (codex-harness)","modelUrl":"https://openai.com/index/introducing-gpt-5-5/","organization":"OpenAI","score":1487,"scoreUnit":"Elo","confidence":"+6/-6","votes":18174,"priceInput":5,"priceOutput":30,"metadata":{"license":"proprietary"}},{"rank":58,"model":"MiniMax M3","modelUrl":"https://www.minimax.io/models/text/m3","organization":"MiniMax","score":1482,"scoreUnit":"Elo","confidence":"+6/-6","votes":17613,"priceInput":0.3,"priceOutput":1.2,"contextWindow":524300,"metadata":{"license":"minimax community license"}},{"rank":59,"model":"Qwen 3.6 Max Preview","modelUrl":"https://qwen.ai/blog?id=qwen3.6-max-preview","organization":"Alibaba","score":1482,"scoreUnit":"Elo","confidence":"+13/-13","votes":2716,"priceInput":1.03,"priceOutput":6.16,"contextWindow":262100,"metadata":{"license":"proprietary"}},{"rank":60,"model":"MiMo V2.5 Pro","modelUrl":"https://mimo.xiaomi.com/mimo-v2-5-pro/","organization":"Xiaomi","score":1478,"scoreUnit":"Elo","confidence":"+5/-5","votes":20313,"priceInput":0.43,"priceOutput":0.87,"contextWindow":1100000,"metadata":{"license":"mit"}},{"rank":61,"model":"Kimi K2.7 Code","modelUrl":"https://platform.kimi.ai/docs/guide/kimi-k2-7-code-quickstart","organization":"Moonshot AI","score":1473,"scoreUnit":"Elo","confidence":"+9/-9","votes":4993,"priceInput":0.67,"priceOutput":3.35,"contextWindow":262100,"metadata":{"license":"modified mit"}},{"rank":62,"model":"Claude Opus 4.5 20251101","modelUrl":"https://www.anthropic.com/news/claude-opus-4-5","organization":"Anthropic","score":1468,"scoreUnit":"Elo","confidence":"+7/-7","votes":13427,"priceInput":5,"priceOutput":25,"contextWindow":200000,"metadata":{"license":"proprietary"}},{"rank":63,"model":"GPT-5.4 High (codex-harness)","modelUrl":"https://platform.openai.com/docs/models/gpt-5.4","organization":"OpenAI","score":1465,"scoreUnit":"Elo","confidence":"+19/-19","votes":1351,"priceInput":2.5,"priceOutput":15,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":64,"model":"DeepSeek V4 Pro High Preview","modelUrl":"https://api-docs.deepseek.com/news/news260424","organization":"DeepSeek","score":1463,"scoreUnit":"Elo","confidence":"+6/-6","votes":13229,"priceInput":1.32,"priceOutput":3.96,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":65,"model":"Qwen 3.6 Plus","modelUrl":"https://qwen.ai/blog?id=qwen3.6","organization":"Alibaba","score":1461,"scoreUnit":"Elo","confidence":"+6/-6","votes":18688,"priceInput":0.33,"priceOutput":1.95,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":66,"model":"GPT-5.5 (codex-harness)","modelUrl":"https://openai.com/index/introducing-gpt-5-5/","organization":"OpenAI","score":1456,"scoreUnit":"Elo","confidence":"+6/-6","votes":16061,"priceInput":5,"priceOutput":30,"metadata":{"license":"proprietary"}},{"rank":67,"model":"Gemini 3.1 Pro Preview","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-pro/","organization":"Google","score":1446,"scoreUnit":"Elo","confidence":"+5/-5","votes":24347,"priceInput":1,"priceOutput":6,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":68,"model":"DeepSeek V4 Pro","modelUrl":"https://api-docs.deepseek.com/news/news260424","organization":"DeepSeek","score":1446,"scoreUnit":"Elo","confidence":"+6/-6","votes":14042,"priceInput":1.32,"priceOutput":3.96,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":69,"model":"GPT-5.4 Medium (codex-harness)","modelUrl":"https://platform.openai.com/docs/models/gpt-5.4","organization":"OpenAI","score":1444,"scoreUnit":"Elo","confidence":"+18/-18","votes":1376,"priceInput":2.5,"priceOutput":15,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":70,"model":"Gemini 3.5 Flash Lite","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-6-flash-3-5-flash-lite-3-5-flash-cyber/","organization":"Google","score":1440,"scoreUnit":"Elo","confidence":"+41/-41","votes":242,"priceInput":0.15,"priceOutput":1.25,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":71,"model":"Gemini 3 Pro","modelUrl":"http://aistudio.google.com/app/prompts/new_chat?model=gemini-3-pro-preview","organization":"Google","score":1439,"scoreUnit":"Elo","confidence":"+8/-8","votes":14092,"priceInput":2,"priceOutput":12,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":72,"model":"Gemini 3 Flash","modelUrl":"https://blog.google/products/gemini/gemini-3-flash","organization":"Google","score":1439,"scoreUnit":"Elo","confidence":"+9/-9","votes":10896,"priceInput":0.5,"priceOutput":3,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":73,"model":"MiMo V2.5","modelUrl":"https://mimo.xiaomi.com/mimo-v2-5/","organization":"Xiaomi","score":1438,"scoreUnit":"Elo","confidence":"+6/-6","votes":15018,"priceInput":0.14,"priceOutput":0.28,"contextWindow":1100000,"metadata":{"license":"mit"}},{"rank":74,"model":"Kimi K2.5 Thinking","modelUrl":"https://www.kimi.com/blog/kimi-k2-5.html","organization":"Moonshot AI","score":1436,"scoreUnit":"Elo","confidence":"+5/-5","votes":20149,"priceInput":0.6,"priceOutput":3,"metadata":{"license":"modified mit"}},{"rank":75,"model":"GLM-4.7","modelUrl":"https://huggingface.co/zai-org/GLM-4.7","organization":"Z.AI","score":1434,"scoreUnit":"Elo","confidence":"+12/-12","votes":4007,"priceInput":0.6,"priceOutput":2.2,"contextWindow":204800,"metadata":{"license":"mit"}},{"rank":76,"model":"GLM-5","modelUrl":"https://huggingface.co/zai-org/GLM-5","organization":"Z.AI","score":1434,"scoreUnit":"Elo","confidence":"+8/-8","votes":7504,"priceInput":1,"priceOutput":3.2,"contextWindow":202800,"metadata":{"license":"mit"}},{"rank":77,"model":"MiMo V2 Pro","modelUrl":"https://mimo.xiaomi.com/mimo-v2-pro","organization":"Xiaomi","score":1433,"scoreUnit":"Elo","confidence":"+8/-8","votes":7253,"priceInput":1.1,"priceOutput":3.3,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":78,"model":"DeepSeek V4 Flash High Preview","modelUrl":"https://api-docs.deepseek.com/news/news260424","organization":"DeepSeek","score":1430,"scoreUnit":"Elo","confidence":"+7/-7","votes":10158,"priceInput":0.3,"priceOutput":1.2,"contextWindow":1000000,"metadata":{"license":"mit"}},{"rank":79,"model":"GPT-5 Medium","modelUrl":"https://platform.openai.com/docs/models/gpt-5","organization":"OpenAI","score":1417,"scoreUnit":"Elo","confidence":"+16/-16","votes":3091,"priceInput":1.25,"priceOutput":10,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":80,"model":"GPT-5.2","modelUrl":"https://openai.com/index/introducing-gpt-5-2","organization":"OpenAI","score":1415,"scoreUnit":"Elo","confidence":"+22/-22","votes":1082,"priceInput":0.88,"priceOutput":7,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":81,"model":"Inkling","modelUrl":"https://thinkingmachines.ai/news/introducing-inkling/","organization":"Thinking Machines","score":1413,"scoreUnit":"Elo","confidence":"+6/-6","votes":13705,"priceInput":0.95,"priceOutput":4.05,"contextWindow":524300,"metadata":{"license":"apache 2.0"}},{"rank":82,"model":"Inkling Small","modelUrl":"https://thinkingmachines.ai/news/inkling-small/","organization":"Thinking Machines","score":1408,"scoreUnit":"Elo","confidence":"+9/-9","votes":5421,"priceInput":0.45,"priceOutput":1.2,"contextWindow":524300,"metadata":{"license":"apache 2.0"}},{"rank":83,"model":"GPT-5.3 Codex (codex-harness)","modelUrl":"https://openai.com/index/introducing-gpt-5-3-codex/","organization":"OpenAI","score":1408,"scoreUnit":"Elo","confidence":"+14/-14","votes":2643,"priceInput":1.75,"priceOutput":14,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":84,"model":"Kimi K2.5 Instant","modelUrl":"https://www.kimi.com/blog/kimi-k2-5.html","organization":"Moonshot AI","score":1404,"scoreUnit":"Elo","confidence":"+12/-12","votes":3271,"priceInput":0.45,"priceOutput":2.25,"contextWindow":262100,"metadata":{"license":"modified mit"}},{"rank":85,"model":"GLM-5v Turbo","modelUrl":"https://docs.z.ai/guides/vlm/glm-5v-turbo","organization":"Z.AI","score":1400,"scoreUnit":"Elo","confidence":"+13/-13","votes":2416,"priceInput":1.2,"priceOutput":4,"contextWindow":202800,"metadata":{"license":"proprietary"}},{"rank":86,"model":"Qwen 3.5 397B A17B","modelUrl":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","organization":"Alibaba","score":1399,"scoreUnit":"Elo","confidence":"+5/-5","votes":21280,"priceInput":0.55,"priceOutput":3.5,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":87,"model":"GPT-5.4 Mini High","modelUrl":"https://openai.com/index/introducing-gpt-5-4-mini-and-nano/","organization":"OpenAI","score":1397,"scoreUnit":"Elo","confidence":"+7/-7","votes":11998,"priceInput":0.75,"priceOutput":4.5,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":88,"model":"MiniMax M2.7","modelUrl":"https://www.minimax.io/news/minimax-m27-en","organization":"MiniMax","score":1397,"scoreUnit":"Elo","confidence":"+6/-6","votes":16074,"priceInput":0.3,"priceOutput":1.2,"contextWindow":204800,"metadata":{"license":"modified mit"}},{"rank":89,"model":"GPT-5.4","modelUrl":"https://platform.openai.com/docs/models/gpt-5.4","organization":"OpenAI","score":1395,"scoreUnit":"Elo","confidence":"+11/-11","votes":3801,"priceInput":2.5,"priceOutput":15,"contextWindow":1100000,"metadata":{"license":"proprietary"}},{"rank":90,"model":"GPT-5.1 Medium","modelUrl":"https://openai.com/index/gpt-5-1/","organization":"OpenAI","score":1395,"scoreUnit":"Elo","confidence":"+11/-11","votes":4911,"priceInput":0.63,"priceOutput":5,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":91,"model":"Claude Sonnet 4.5 20250929 High 32K","modelUrl":"https://www.anthropic.com/news/claude-sonnet-4-5","organization":"Anthropic","score":1393,"scoreUnit":"Elo","confidence":"+8/-8","votes":13253,"priceInput":3,"priceOutput":15,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":92,"model":"Claude Opus 4.1 20250805","modelUrl":"https://www.anthropic.com/news/claude-opus-4-1","organization":"Anthropic","score":1389,"scoreUnit":"Elo","confidence":"+11/-11","votes":6926,"priceInput":7.5,"priceOutput":37.5,"contextWindow":200000,"metadata":{"license":"proprietary"}},{"rank":93,"model":"MiniMax M2.5","modelUrl":"https://www.minimax.io/news/minimax-m25","organization":"MiniMax","score":1386,"scoreUnit":"Elo","confidence":"+8/-8","votes":7637,"priceInput":0.27,"priceOutput":1.08,"contextWindow":204800,"metadata":{"license":"modified mit"}},{"rank":94,"model":"Claude Sonnet 4.5 20250929","modelUrl":"https://www.anthropic.com/news/claude-sonnet-4-5","organization":"Anthropic","score":1384,"scoreUnit":"Elo","confidence":"+7/-7","votes":15722,"priceInput":3,"priceOutput":15,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":95,"model":"Gemini 3 Flash (thinking-minimal)","modelUrl":"https://blog.google/products/gemini/gemini-3-flash","organization":"Google","score":1384,"scoreUnit":"Elo","confidence":"+5/-5","votes":22213,"priceInput":0.5,"priceOutput":3,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":96,"model":"MiniMax M2.1 Preview","modelUrl":"https://www.minimax.io/news/minimax-m21","organization":"MiniMax","score":1384,"scoreUnit":"Elo","confidence":"+10/-10","votes":7644,"priceInput":0.3,"priceOutput":1.2,"contextWindow":204800,"metadata":{"license":"mit"}},{"rank":97,"model":"Grok 4.20 Beta 0309 Reasoning","modelUrl":"https://docs.x.ai/developers/models/grok-4.20-beta-0309-reasoning","organization":"SpaceXAI","score":1374,"scoreUnit":"Elo","confidence":"+6/-6","votes":15503,"priceInput":1.25,"priceOutput":2.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":98,"model":"GPT-5.3 Codex (codex-harness)","modelUrl":"https://openai.com/index/introducing-gpt-5-3-codex/","organization":"OpenAI","score":1371,"scoreUnit":"Elo","confidence":"+11/-11","votes":3657,"priceInput":1.75,"priceOutput":14,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":99,"model":"Solar Pro4","modelUrl":"https://www.upstage.ai/blog/en/solar-pro-4","organization":"Upstage","score":1370,"scoreUnit":"Elo","confidence":"+10/-10","votes":4945,"priceInput":0.09,"priceOutput":0.36,"contextWindow":524300,"metadata":{"license":"proprietary"}},{"rank":100,"model":"Gemma 4 31B","modelUrl":"https://aistudio.google.com/app/prompts/new_chat?model=gemma-4-31b-it","organization":"Google","score":1365,"scoreUnit":"Elo","confidence":"+6/-6","votes":13325,"priceInput":0.99,"priceOutput":1.49,"contextWindow":131100,"metadata":{"license":"apache 2.0"}},{"rank":101,"model":"DeepSeek V3.2 Thinking","modelUrl":"https://api-docs.deepseek.com/news/news250929","organization":"DeepSeek","score":1362,"scoreUnit":"Elo","confidence":"+9/-9","votes":6921,"priceInput":0.28,"priceOutput":0.42,"contextWindow":163800,"metadata":{"license":"mit"}},{"rank":102,"model":"Qwen 3.5 122B A10B","modelUrl":"https://huggingface.co/Qwen/Qwen3.5-122B-A10B","organization":"Alibaba","score":1360,"scoreUnit":"Elo","confidence":"+8/-8","votes":8249,"priceInput":0.26,"priceOutput":2.08,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":103,"model":"Gemma 4 26B A4B","modelUrl":"https://aistudio.google.com/app/prompts/new_chat?model=gemma-4-26b-a4b-it","organization":"Google","score":1358,"scoreUnit":"Elo","confidence":"+17/-17","votes":1502,"metadata":{"license":"apache 2.0"}},{"rank":104,"model":"Qwen 3.5 27B","modelUrl":"https://huggingface.co/Qwen/Qwen3.5-27B","organization":"Alibaba","score":1357,"scoreUnit":"Elo","confidence":"+8/-8","votes":7794,"priceInput":0.2,"priceOutput":1.56,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":105,"model":"Grok 4.3","modelUrl":"https://docs.x.ai/developers/models/grok-4.3","organization":"SpaceXAI","score":1357,"scoreUnit":"Elo","confidence":"+6/-6","votes":15057,"priceInput":1.25,"priceOutput":2.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":106,"model":"Hunyuan Hy3 Preview","modelUrl":"https://huggingface.co/tencent/Hy3-preview","organization":"Tencent","score":1356,"scoreUnit":"Elo","confidence":"+17/-17","votes":1455,"metadata":{"license":"tencent-hunyuan-community"}},{"rank":107,"model":"Muse Glimmer","modelUrl":"https://research.meta.ai/blog/introducing-muse-glimmer-open-agentic-model","organization":"Meta","score":1355,"scoreUnit":"Elo","confidence":"+16/-16","votes":1663,"metadata":{"license":"apache-2.0"}},{"rank":108,"model":"Laguna M.1","modelUrl":"https://poolside.ai/blog/introducing-laguna-xs2-m1","organization":"Poolside","score":1348,"scoreUnit":"Elo","confidence":"+9/-9","votes":5418,"priceInput":0.2,"priceOutput":0.4,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":109,"model":"GPT-5.1","modelUrl":"https://openai.com/index/gpt-5-1/","organization":"OpenAI","score":1341,"scoreUnit":"Elo","confidence":"+8/-8","votes":10718,"priceInput":0.63,"priceOutput":5,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":110,"model":"GLM-4.6","modelUrl":"https://docs.z.ai/guides/llm/glm-4.6","organization":"Z.AI","score":1339,"scoreUnit":"Elo","confidence":"+11/-11","votes":6780,"priceInput":0.43,"priceOutput":1.75,"contextWindow":204800,"metadata":{"license":"mit"}},{"rank":111,"model":"GPT-5.2 Codex","modelUrl":"https://openai.com/index/introducing-gpt-5-2-codex","organization":"OpenAI","score":1339,"scoreUnit":"Elo","confidence":"+9/-9","votes":6722,"priceInput":1.75,"priceOutput":14,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":112,"model":"GPT-5.1 Codex","modelUrl":"https://platform.openai.com/docs/models/gpt-5.1-codex","organization":"OpenAI","score":1337,"scoreUnit":"Elo","confidence":"+12/-12","votes":5005,"priceInput":1.25,"priceOutput":10,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":113,"model":"MiMo V2 Flash (non-thinking)","modelUrl":"https://mimo.xiaomi.com/blog/mimo-v2-flash","organization":"Xiaomi","score":1330,"scoreUnit":"Elo","confidence":"+10/-10","votes":5692,"priceInput":0.1,"priceOutput":0.3,"contextWindow":262100,"metadata":{"license":"mit"}},{"rank":114,"model":"Claude Haiku 4.5 20251001","modelUrl":"https://www.anthropic.com/news/claude-haiku-4-5","organization":"Anthropic","score":1329,"scoreUnit":"Elo","confidence":"+5/-5","votes":29184,"priceInput":1,"priceOutput":5,"contextWindow":200000,"metadata":{"license":"proprietary"}},{"rank":115,"model":"DeepSeek V3.2","modelUrl":"https://api-docs.deepseek.com/news/news250929","organization":"DeepSeek","score":1325,"scoreUnit":"Elo","confidence":"+8/-8","votes":9387,"priceInput":0.28,"priceOutput":0.42,"contextWindow":163800,"metadata":{"license":"mit"}},{"rank":116,"model":"Kimi K2 Thinking Turbo","modelUrl":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","organization":"Moonshot AI","score":1321,"scoreUnit":"Elo","confidence":"+7/-7","votes":13093,"priceInput":0.57,"priceOutput":2.3,"contextWindow":131100,"metadata":{"license":"modified mit"}},{"rank":117,"model":"Laguna Xs.2","modelUrl":"https://poolside.ai/blog/introducing-laguna-xs2-m1","organization":"Poolside","score":1302,"scoreUnit":"Elo","confidence":"+11/-11","votes":4256,"priceInput":0.1,"priceOutput":0.2,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":118,"model":"MiniMax M2","modelUrl":"https://www.minimax.io/news/minimax-m2","organization":"MiniMax","score":1297,"scoreUnit":"Elo","confidence":"+11/-11","votes":6714,"priceInput":0.3,"priceOutput":1.2,"contextWindow":204800,"metadata":{"license":"apache 2.0"}},{"rank":119,"model":"MiMo V2 Flash (thinking)","modelUrl":"https://mimo.xiaomi.com/blog/mimo-v2-flash","organization":"Xiaomi","score":1292,"scoreUnit":"Elo","confidence":"+16/-16","votes":1688,"priceInput":0.1,"priceOutput":0.3,"contextWindow":262100,"metadata":{"license":"mit"}},{"rank":120,"model":"Qwen 3 Coder 480B A35B Instruct","modelUrl":"https://qwenlm.github.io/blog/qwen3-coder/","organization":"Alibaba","score":1274,"scoreUnit":"Elo","confidence":"+8/-8","votes":12719,"priceInput":0.65,"priceOutput":3.25,"contextWindow":1000000,"metadata":{"license":"apache 2.0"}},{"rank":121,"model":"DeepSeek V3.2 Exp","modelUrl":"https://api-docs.deepseek.com/news/news250929","organization":"DeepSeek","score":1272,"scoreUnit":"Elo","confidence":"+13/-13","votes":3972,"priceInput":0.27,"priceOutput":0.41,"contextWindow":163800,"metadata":{"license":"mit"}},{"rank":122,"model":"Mistral Medium 3.5","modelUrl":"https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04","organization":"Mistral","score":1263,"scoreUnit":"Elo","confidence":"+15/-15","votes":2322,"priceInput":0.75,"priceOutput":3.75,"contextWindow":262100,"metadata":{"license":"modified mit"}},{"rank":123,"model":"Gemini 3.1 Flash Lite Preview","modelUrl":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-lite","organization":"Google","score":1256,"scoreUnit":"Elo","confidence":"+7/-7","votes":14417,"priceInput":0.25,"priceOutput":1.5,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":124,"model":"KAT Coder Pro V1","modelUrl":"https://www.streamlake.ai/product/kat-coder","organization":"Unknown","score":1255,"scoreUnit":"Elo","confidence":"+19/-19","votes":1504,"priceInput":0.21,"priceOutput":0.83,"contextWindow":256000,"metadata":{"license":"proprietary"}},{"rank":125,"model":"Qwen 3.5 35B A3B","modelUrl":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","organization":"Alibaba","score":1253,"scoreUnit":"Elo","confidence":"+17/-17","votes":1617,"priceInput":0.15,"priceOutput":1,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":126,"model":"GPT-5.1 Codex Mini","modelUrl":"https://platform.openai.com/docs/models/gpt-5.1-codex","organization":"OpenAI","score":1244,"scoreUnit":"Elo","confidence":"+22/-22","votes":1155,"priceInput":0.25,"priceOutput":2,"contextWindow":400000,"metadata":{"license":"proprietary"}},{"rank":127,"model":"Qwen 3.5 Flash","modelUrl":"https://modelstudio.console.alibabacloud.com/ap-southeast-1/?tab=doc#/doc/?type=model&url=2840914_2&modelId=group-qwen3.5-flash","organization":"Alibaba","score":1243,"scoreUnit":"Elo","confidence":"+20/-20","votes":1329,"metadata":{"license":"proprietary"}},{"rank":128,"model":"Grok 4.1 Fast Reasoning","modelUrl":"https://x.ai/news/grok-4-1-fast","organization":"SpaceXAI","score":1241,"scoreUnit":"Elo","confidence":"+11/-11","votes":5491,"priceInput":0.2,"priceOutput":0.5,"contextWindow":128000,"metadata":{"license":"proprietary"}},{"rank":129,"model":"Trinity Large Thinking","modelUrl":"https://www.arcee.ai/blog/trinity-large-thinking","organization":"Arcee AI","score":1238,"scoreUnit":"Elo","confidence":"+20/-20","votes":1362,"priceInput":0.25,"priceOutput":0.8,"contextWindow":262100,"metadata":{"license":"apache 2.0"}},{"rank":130,"model":"Mistral Large 3","modelUrl":"https://mistral.ai/news/mistral-3","organization":"Mistral","score":1230,"scoreUnit":"Elo","confidence":"+25/-25","votes":840,"priceInput":0.5,"priceOutput":1.5,"metadata":{"license":"apache 2.0"}},{"rank":131,"model":"Gemini 2.5 Pro","modelUrl":"http://aistudio.google.com/app/prompts/new_chat?model=gemini-2.5-pro","organization":"Google","score":1227,"scoreUnit":"Elo","confidence":"+16/-16","votes":2729,"priceInput":1.25,"priceOutput":10,"contextWindow":1000000,"metadata":{"license":"proprietary"}},{"rank":132,"model":"Grok 4.1 Thinking","modelUrl":"https://x.ai/news/grok-4-1","organization":"SpaceXAI","score":1214,"scoreUnit":"Elo","confidence":"+25/-25","votes":961,"metadata":{"license":"proprietary"}},{"rank":133,"model":"Devstral 2","modelUrl":"https://mistral.ai/news/devstral-2-vibe-cli","organization":"Mistral","score":1196,"scoreUnit":"Elo","confidence":"+21/-21","votes":1182,"metadata":{"license":"modified mit"}},{"rank":134,"model":"Granite 4.1 8B","modelUrl":"https://research.ibm.com/blog/granite-4-1-ai-foundation-models","organization":"IBM","score":1190,"scoreUnit":"Elo","confidence":"+18/-18","votes":1786,"priceInput":0.05,"priceOutput":0.1,"contextWindow":131100,"metadata":{"license":"apache 2.0"}},{"rank":135,"model":"Mercury 2","modelUrl":"https://www.inceptionlabs.ai/blog/introducing-mercury-2","organization":"Inception AI","score":1170,"scoreUnit":"Elo","confidence":"+24/-24","votes":955,"priceInput":0.25,"priceOutput":0.75,"contextWindow":128000,"metadata":{"license":"proprietary"}},{"rank":136,"model":"Grok Code Fast 1","modelUrl":"https://x.ai/news/grok-code-fast-1","organization":"SpaceXAI","score":1167,"scoreUnit":"Elo","confidence":"+28/-28","votes":789,"priceInput":0.2,"priceOutput":1.5,"metadata":{"license":"proprietary"}},{"rank":137,"model":"Grok 4 Fast Reasoning","modelUrl":"https://x.ai/news/grok-4-fast","organization":"SpaceXAI","score":1159,"scoreUnit":"Elo","confidence":"+27/-27","votes":742,"priceInput":0.2,"priceOutput":0.5,"metadata":{"license":"proprietary"}},{"rank":138,"model":"Devstral Medium 2507","modelUrl":"https://mistral.ai/news/devstral-2507","organization":"Mistral","score":1076,"scoreUnit":"Elo","confidence":"+31/-31","votes":842,"priceInput":0.4,"priceOutput":2,"contextWindow":128000,"metadata":{"license":"proprietary"}}]},{"source":"livebench-coding","sourceName":"LiveBench Coding","url":"https://livebench.ai","category":"coding","fetchedAt":"2026-10-03T10:46:59.478Z","sourceUpdatedAt":"2026-06-25","entries":[{"rank":1,"model":"Claude 5.5 Opus Thinking Max Effort","organization":"Anthropic","score":89.3,"scoreUnit":"%","metadata":{"reasoning":92.2,"coding":89.3,"agenticCoding":71.7,"math":97.1,"dataAnalysis":80.3,"language":86.3,"instructionFollowing":65.7,"costPerTask":0.799}},{"rank":2,"model":"Claude Sonnet 5.5 xHigh Effort","organization":"Anthropic","score":88.9,"scoreUnit":"%","metadata":{"reasoning":86.8,"coding":88.9,"agenticCoding":39.3,"math":96.7,"dataAnalysis":78.6,"language":83.4,"instructionFollowing":70.5,"costPerTask":0.141}},{"rank":3,"model":"Claude Fable 5.1 Max Effort","organization":"Anthropic","score":86.4,"scoreUnit":"%","metadata":{"reasoning":91.7,"coding":86.4,"agenticCoding":66.1,"math":97,"dataAnalysis":80.3,"language":89.5,"instructionFollowing":73,"costPerTask":1.212}},{"rank":4,"model":"Claude Fable 5 Max Effort","organization":"Anthropic","score":86,"scoreUnit":"%","metadata":{"reasoning":89.7,"coding":86,"agenticCoding":62.2,"math":96,"dataAnalysis":80.5,"language":90.7,"instructionFollowing":75.8,"costPerTask":1.439}},{"rank":5,"model":"GPT-5.6 Sol Max Effort","organization":"OpenAI","score":83.9,"scoreUnit":"%","metadata":{"reasoning":91.7,"coding":83.9,"agenticCoding":56.2,"math":96.2,"dataAnalysis":79.8,"language":87.7,"instructionFollowing":71.8,"costPerTask":0.515}},{"rank":6,"model":"GPT-5.2 Codex","organization":"OpenAI","score":83.6,"scoreUnit":"%","metadata":{"reasoning":77.7,"coding":83.6,"agenticCoding":49.4,"math":88.8,"dataAnalysis":78.2,"language":73.7,"instructionFollowing":66.4,"costPerTask":0.187}},{"rank":7,"model":"GPT-5.6 Luna Max Effort","organization":"OpenAI","score":82.9,"scoreUnit":"%","metadata":{"reasoning":85.6,"coding":82.9,"agenticCoding":48.4,"math":87.2,"dataAnalysis":78,"language":72.6,"instructionFollowing":60.1,"costPerTask":0.169}},{"rank":8,"model":"GPT-5.5 Thinking xHigh Effort","organization":"OpenAI","score":82.1,"scoreUnit":"%","metadata":{"reasoning":89.7,"coding":82.1,"agenticCoding":54,"math":95.9,"dataAnalysis":81.6,"language":87.4,"instructionFollowing":70.7,"costPerTask":0.435}},{"rank":9,"model":"Claude 4.7 Opus Thinking xHigh Effort","organization":"Anthropic","score":82.1,"scoreUnit":"%","metadata":{"reasoning":87.2,"coding":82.1,"agenticCoding":50.7,"math":92.9,"dataAnalysis":78.3,"language":77.9,"instructionFollowing":66.7,"costPerTask":0.528}},{"rank":10,"model":"GPT-6 Sol Max Effort","organization":"OpenAI","score":81.8,"scoreUnit":"%","metadata":{"reasoning":88.7,"coding":81.8,"agenticCoding":52.9,"math":96.4,"dataAnalysis":81.2,"language":85.3,"instructionFollowing":68.6,"costPerTask":0.268}},{"rank":11,"model":"Claude 4.8 Opus Thinking Max Effort","organization":"Anthropic","score":81.8,"scoreUnit":"%","metadata":{"reasoning":89.2,"coding":81.8,"agenticCoding":50.5,"math":94.3,"dataAnalysis":66,"language":79.7,"instructionFollowing":72,"costPerTask":0.983}},{"rank":12,"model":"Claude 5 Opus Thinking Max Effort","organization":"Anthropic","score":81.4,"scoreUnit":"%","metadata":{"reasoning":91.2,"coding":81.4,"agenticCoding":65.2,"math":95.7,"dataAnalysis":74.6,"language":88.7,"instructionFollowing":63.8,"costPerTask":0.699}},{"rank":13,"model":"Kimi K3","organization":"Moonshot AI","score":81.4,"scoreUnit":"%","metadata":{"reasoning":90.7,"coding":81.4,"agenticCoding":62.2,"math":84.4,"dataAnalysis":78.7,"language":85.5,"instructionFollowing":71.4,"costPerTask":0.348,"license":"open"}},{"rank":14,"model":"Muse Spark 1.3 xHigh Effort","organization":"Meta","score":81.1,"scoreUnit":"%","metadata":{"reasoning":89.7,"coding":81.1,"agenticCoding":64.1,"math":95.9,"dataAnalysis":79.6,"language":82.8,"instructionFollowing":78,"costPerTask":0.219}},{"rank":15,"model":"Claude Sonnet 5 xHigh Effort","organization":"Anthropic","score":80.7,"scoreUnit":"%","metadata":{"reasoning":88.7,"coding":80.7,"agenticCoding":59.4,"math":92.9,"dataAnalysis":71.7,"language":75,"instructionFollowing":63.9,"costPerTask":0.505}},{"rank":16,"model":"GPT-6 Astra Max Effort","organization":"OpenAI","score":80.4,"scoreUnit":"%","metadata":{"reasoning":92.7,"coding":80.4,"agenticCoding":57.3,"math":96.8,"dataAnalysis":83,"language":89.4,"instructionFollowing":75.6,"costPerTask":0.736}},{"rank":17,"model":"GPT-6.1 Sol Max Effort","organization":"OpenAI","score":80.4,"scoreUnit":"%","metadata":{"reasoning":92.6,"coding":80.4,"agenticCoding":54.5,"math":96.8,"dataAnalysis":82.7,"language":90.1,"instructionFollowing":74.2,"costPerTask":0.142}},{"rank":18,"model":"DeepSeek V4.1 Flash Max Effort","organization":"DeepSeek","score":80,"scoreUnit":"%","metadata":{"reasoning":86.7,"coding":80,"agenticCoding":77.3,"math":93.3,"dataAnalysis":79.3,"language":81.2,"instructionFollowing":70,"costPerTask":0.029,"license":"open"}},{"rank":19,"model":"GLM-5.2","organization":"Z.AI","score":79.7,"scoreUnit":"%","metadata":{"reasoning":78.6,"coding":79.7,"agenticCoding":51.8,"math":89.8,"dataAnalysis":73.7,"language":76.2,"instructionFollowing":62.3,"costPerTask":0.225,"license":"open"}},{"rank":20,"model":"Claude 4.5 Opus Thinking High Effort","organization":"Anthropic","score":79.7,"scoreUnit":"%","metadata":{"reasoning":80.1,"coding":79.7,"agenticCoding":39.7,"math":90.4,"dataAnalysis":74.4,"language":81.3,"instructionFollowing":62.5,"costPerTask":0.61}},{"rank":21,"model":"Claude 4.6 Sonnet Thinking Medium Effort","organization":"Anthropic","score":79.3,"scoreUnit":"%","metadata":{"reasoning":84.8,"coding":79.3,"agenticCoding":42.6,"math":87,"dataAnalysis":77.9,"language":76.1,"instructionFollowing":63.2,"costPerTask":0.306}},{"rank":22,"model":"GLM-5.3","organization":"Z.AI","score":79,"scoreUnit":"%","metadata":{"reasoning":85.8,"coding":79,"agenticCoding":60.9,"math":87.9,"dataAnalysis":70.2,"language":79.9,"instructionFollowing":69.3,"costPerTask":0.45,"license":"open"}},{"rank":23,"model":"GPT-6 Luna Max Effort","organization":"OpenAI","score":79,"scoreUnit":"%","metadata":{"reasoning":81.8,"coding":79,"agenticCoding":51.2,"math":89.1,"dataAnalysis":73.4,"language":73.8,"instructionFollowing":55.9,"costPerTask":0.026}},{"rank":24,"model":"GLM-5.3 Flash","organization":"Z.AI","score":79,"scoreUnit":"%","metadata":{"reasoning":77.6,"coding":79,"agenticCoding":56.8,"math":81.2,"dataAnalysis":76.4,"language":77.3,"instructionFollowing":52.8,"costPerTask":0.031,"license":"open"}},{"rank":25,"model":"Gemini 3.7 Flash High","organization":"Google","score":78.9,"scoreUnit":"%","metadata":{"reasoning":87.8,"coding":78.9,"agenticCoding":58.3,"math":93.5,"dataAnalysis":68,"language":85.5,"instructionFollowing":79.9,"costPerTask":0.157}},{"rank":26,"model":"Kimi K2.6 Thinking","organization":"Moonshot AI","score":78.6,"scoreUnit":"%","metadata":{"reasoning":79.4,"coding":78.6,"agenticCoding":46.9,"math":84.3,"dataAnalysis":65.1,"language":75.1,"instructionFollowing":64.4,"costPerTask":0.169,"license":"open"}},{"rank":27,"model":"GPT-5.6 Terra Max Effort","organization":"OpenAI","score":78.2,"scoreUnit":"%","metadata":{"reasoning":90.6,"coding":78.2,"agenticCoding":54.9,"math":94.9,"dataAnalysis":79.3,"language":82.9,"instructionFollowing":64.6,"costPerTask":0.352}},{"rank":28,"model":"Gemini 3.5 Flash High","organization":"Google","score":78.2,"scoreUnit":"%","metadata":{"reasoning":82,"coding":78.2,"agenticCoding":49,"math":88.2,"dataAnalysis":64.9,"language":84.6,"instructionFollowing":75.6,"costPerTask":0.249}},{"rank":29,"model":"Claude 4.6 Opus Thinking High Effort","organization":"Anthropic","score":78.2,"scoreUnit":"%","metadata":{"reasoning":88.7,"coding":78.2,"agenticCoding":49,"math":89.3,"dataAnalysis":69.9,"language":83.3,"instructionFollowing":63.3,"costPerTask":0.404}},{"rank":30,"model":"Qwen 3.6 Plus","organization":"Alibaba","score":78.2,"scoreUnit":"%","metadata":{"reasoning":75.8,"coding":78.2,"agenticCoding":41.4,"math":83.7,"dataAnalysis":69.9,"language":75,"instructionFollowing":58.3,"costPerTask":0.227}},{"rank":31,"model":"Gemini 3.6 Flash High","organization":"Google","score":77.9,"scoreUnit":"%","metadata":{"reasoning":85.1,"coding":77.9,"agenticCoding":43.4,"math":86.4,"dataAnalysis":63,"language":83.9,"instructionFollowing":75.4,"costPerTask":0.235}},{"rank":32,"model":"GPT-5.4 Thinking xHigh Effort","organization":"OpenAI","score":77.5,"scoreUnit":"%","metadata":{"reasoning":88.1,"coding":77.5,"agenticCoding":53.8,"math":94.1,"dataAnalysis":79.3,"language":82.6,"instructionFollowing":70.2,"costPerTask":0.387}},{"rank":33,"model":"Muse Spark 1.2 xHigh Effort","organization":"Meta","score":77.5,"scoreUnit":"%","metadata":{"reasoning":90,"coding":77.5,"agenticCoding":57.6,"math":91.2,"dataAnalysis":76.5,"language":78.6,"instructionFollowing":74.3,"costPerTask":0.375}},{"rank":34,"model":"DeepSeek V4 Pro 0813","organization":"DeepSeek","score":77.2,"scoreUnit":"%","metadata":{"reasoning":85.8,"coding":77.2,"agenticCoding":54.9,"math":95.1,"dataAnalysis":79.2,"language":82.1,"instructionFollowing":67.7,"costPerTask":0.044,"license":"open"}},{"rank":35,"model":"Grok 4.7 xHigh","organization":"xAI","score":77.2,"scoreUnit":"%","metadata":{"reasoning":82.7,"coding":77.2,"agenticCoding":54,"math":95.7,"dataAnalysis":76.9,"language":80.1,"instructionFollowing":75.3,"costPerTask":0.718}},{"rank":36,"model":"Muse Spark 1.1 xHigh Effort","organization":"Meta","score":77.2,"scoreUnit":"%","metadata":{"reasoning":87.7,"coding":77.2,"agenticCoding":58.5,"math":87.1,"dataAnalysis":72.5,"language":74.3,"instructionFollowing":69.6,"costPerTask":0.198}},{"rank":37,"model":"Grok 4.6 xHigh","organization":"xAI","score":76.8,"scoreUnit":"%","metadata":{"reasoning":90.5,"coding":76.8,"agenticCoding":57,"math":92.6,"dataAnalysis":73.9,"language":83.7,"instructionFollowing":71.9,"costPerTask":0.207}},{"rank":38,"model":"Gemini 3.1 Pro Preview High","organization":"Google","score":76.5,"scoreUnit":"%","metadata":{"reasoning":84,"coding":76.5,"agenticCoding":44.1,"math":91,"dataAnalysis":78.5,"language":85.4,"instructionFollowing":79.1,"costPerTask":0.286}},{"rank":39,"model":"GPT-5.2 High","organization":"OpenAI","score":76.1,"scoreUnit":"%","metadata":{"reasoning":83.2,"coding":76.1,"agenticCoding":50.3,"math":93.2,"dataAnalysis":78.2,"language":79.8,"instructionFollowing":61.8,"costPerTask":0.234}},{"rank":40,"model":"Gemini 3.5 Flash-Lite High","organization":"Google","score":76.1,"scoreUnit":"%","metadata":{"reasoning":60.2,"coding":76.1,"agenticCoding":45.3,"math":73.7,"dataAnalysis":53.2,"language":71.8,"instructionFollowing":67.2,"costPerTask":0.069}},{"rank":41,"model":"Ox Alpha Max","organization":"Stealth","score":75.8,"scoreUnit":"%","metadata":{"reasoning":76.6,"coding":75.8,"agenticCoding":52.6,"math":77.5,"dataAnalysis":75.8,"language":66.1,"instructionFollowing":60.3,"costPerTask":0}},{"rank":42,"model":"Qwen3.8 27B","organization":"Alibaba","score":75.7,"scoreUnit":"%","metadata":{"reasoning":80,"coding":75.7,"agenticCoding":61.4,"math":86.2,"dataAnalysis":76.6,"language":74.3,"instructionFollowing":72.7,"costPerTask":0.094,"license":"open"}},{"rank":43,"model":"DeepSeek V4 Flash 0731","organization":"DeepSeek","score":75,"scoreUnit":"%","metadata":{"reasoning":86.6,"coding":75,"agenticCoding":46.8,"math":86.8,"dataAnalysis":79.3,"language":79.2,"instructionFollowing":65.5,"costPerTask":0.06,"license":"open"}},{"rank":44,"model":"Qwen 3.7 Max","organization":"Alibaba","score":74.2,"scoreUnit":"%","metadata":{"reasoning":83.3,"coding":74.2,"agenticCoding":43.6,"math":85.2,"dataAnalysis":71.8,"language":79.7,"instructionFollowing":74,"costPerTask":0.182}},{"rank":45,"model":"Kimi K2.7 Code","organization":"Moonshot AI","score":74,"scoreUnit":"%","metadata":{"reasoning":82.8,"coding":74,"agenticCoding":45.7,"math":79.6,"dataAnalysis":62.7,"language":77.9,"instructionFollowing":56.3,"costPerTask":0.1,"license":"open"}},{"rank":46,"model":"Qwen 3.8 Max","organization":"Alibaba","score":72.9,"scoreUnit":"%","metadata":{"reasoning":88.2,"coding":72.9,"agenticCoding":64.6,"math":91.3,"dataAnalysis":78.4,"language":79.7,"instructionFollowing":74.1,"costPerTask":0.275,"license":"open"}},{"rank":47,"model":"Qwen 3.8 Flash Next","organization":"Alibaba","score":72.6,"scoreUnit":"%","metadata":{"reasoning":87.4,"coding":72.6,"agenticCoding":61.6,"math":85.8,"dataAnalysis":74.2,"language":74.6,"instructionFollowing":77.1,"costPerTask":0.042,"license":"open"}},{"rank":48,"model":"Gemini 3.8 Flash High","organization":"Google","score":72.5,"scoreUnit":"%","metadata":{"reasoning":89.3,"coding":72.5,"agenticCoding":54.2,"math":91.6,"dataAnalysis":54,"language":87.8,"instructionFollowing":81.4,"costPerTask":0.307}},{"rank":49,"model":"Qwen 3.6 27B","organization":"Alibaba","score":71.8,"scoreUnit":"%","metadata":{"reasoning":70.3,"coding":71.8,"agenticCoding":39.3,"math":79.9,"dataAnalysis":70.4,"language":63.3,"instructionFollowing":53.2,"costPerTask":0.202,"license":"open"}},{"rank":50,"model":"GPT-5.4 Mini xHigh","organization":"OpenAI","score":71.6,"scoreUnit":"%","metadata":{"reasoning":71.3,"coding":71.6,"agenticCoding":41.7,"math":78.5,"dataAnalysis":70.8,"language":71,"instructionFollowing":59.8,"costPerTask":0.334}},{"rank":51,"model":"Inkling xHigh Effort","organization":"Thinking Machines","score":71,"scoreUnit":"%","metadata":{"reasoning":78.3,"coding":71,"agenticCoding":49.4,"math":88.4,"dataAnalysis":72.8,"language":73.5,"instructionFollowing":70.1,"costPerTask":0.31,"license":"open"}},{"rank":52,"model":"GPT-5.4 Nano xHigh","organization":"OpenAI","score":70.8,"scoreUnit":"%","metadata":{"reasoning":81.1,"coding":70.8,"agenticCoding":46.8,"math":91,"dataAnalysis":67.6,"language":62.5,"instructionFollowing":67.2,"costPerTask":0.091}},{"rank":53,"model":"Nemotron 3 Ultra 550B A55B","organization":"NVIDIA","score":70.7,"scoreUnit":"%","metadata":{"reasoning":74.7,"coding":70.7,"agenticCoding":38.7,"math":88.7,"dataAnalysis":54.5,"language":70.8,"instructionFollowing":73.4,"costPerTask":0.371,"license":"open"}},{"rank":54,"model":"Grok 4.3","organization":"xAI","score":69.9,"scoreUnit":"%","metadata":{"reasoning":70.8,"coding":69.9,"agenticCoding":18.5,"math":84.3,"dataAnalysis":55.8,"language":73.6,"instructionFollowing":62.8,"costPerTask":0.061}},{"rank":55,"model":"Grok 4.5","organization":"xAI","score":68.6,"scoreUnit":"%","metadata":{"reasoning":87.2,"coding":68.6,"agenticCoding":56.5,"math":90.8,"dataAnalysis":73,"language":82.8,"instructionFollowing":71.5,"costPerTask":0.131}},{"rank":56,"model":"DeepSeek V4 Flash Vision Exp","organization":"DeepSeek","score":68.2,"scoreUnit":"%","metadata":{"reasoning":85.4,"coding":68.2,"agenticCoding":65.1,"math":87.8,"dataAnalysis":79.5,"language":80.4,"instructionFollowing":71,"costPerTask":0.051,"license":"open"}},{"rank":57,"model":"Minimax M3","organization":"MiniMax","score":68.2,"scoreUnit":"%","metadata":{"reasoning":74.5,"coding":68.2,"agenticCoding":40.7,"math":76.9,"dataAnalysis":76.2,"language":76.8,"instructionFollowing":57.5,"costPerTask":0.06}},{"rank":58,"model":"Grok Build 0.1","organization":"xAI","score":65.4,"scoreUnit":"%","metadata":{"reasoning":76.4,"coding":65.4,"agenticCoding":45.8,"math":78.4,"dataAnalysis":70.8,"language":72.5,"instructionFollowing":65.2,"costPerTask":0.024}}]}]}