{"version":"configuration-source-5","evidencePolicy":"documented","snapshotId":"sha256-df858793dcb753b0f77beb223fce04e1de99a2c08f2c7b5f14534efcafa8c7c5","effortDatasetId":"sha256-1f186994047883a45f76e96fbce2f07320baf4f104506414be2bba69a334a02f+sha256-2bc644d4e2fb34bd4fecd1ef0a2a50302a9d18f3b8cd3aa0e6dfc487669f5146+sha256-b6d2e58f71798704ee9f3e6b341e3627e6b0dc1caef890fc1e08b62a226e3f36+sha256-7a7d95c40c608cc28483fb5cef9007da8c102f1e7278882ccbcc02a16078607d+sha256-99e5ccb2eac4abb63cc6d9823b591f2ffac992cdee03ac725f66bd8a5ec086a3+sha256-9fbe9729fecc9cf9232f3292684307ba1a85d69beff3920a2a7ed9e2c77bf7ef+sha256-7e00d90a437b5a33e79607a04b57b10dc14322bbaa63ce8bbe9ce1338eaf26f5","scope":"All collected observations, not a claim that every public result has been collected. Contributing means positive graph weight, not sufficient evidence for a rank.","models":[{"id":"claude-fable-5","collected":272,"contributing":94,"admittedWithoutWeight":2,"excluded":176},{"id":"claude-fable-5-1","collected":203,"contributing":134,"admittedWithoutWeight":2,"excluded":67},{"id":"claude-haiku-4-5-20251001","collected":77,"contributing":47,"admittedWithoutWeight":0,"excluded":30},{"id":"claude-opus-4-5-20251101","collected":68,"contributing":56,"admittedWithoutWeight":0,"excluded":12},{"id":"claude-opus-4-6","collected":121,"contributing":71,"admittedWithoutWeight":1,"excluded":49},{"id":"claude-opus-4-7","collected":118,"contributing":79,"admittedWithoutWeight":0,"excluded":39},{"id":"claude-opus-4-8","collected":248,"contributing":103,"admittedWithoutWeight":0,"excluded":145},{"id":"claude-opus-5","collected":259,"contributing":144,"admittedWithoutWeight":2,"excluded":113},{"id":"claude-sonnet-4-5-20250929","collected":86,"contributing":48,"admittedWithoutWeight":0,"excluded":38},{"id":"claude-sonnet-4-6","collected":151,"contributing":80,"admittedWithoutWeight":1,"excluded":70},{"id":"claude-sonnet-5","collected":150,"contributing":128,"admittedWithoutWeight":0,"excluded":22},{"id":"deepseek-r1-0528","collected":19,"contributing":13,"admittedWithoutWeight":0,"excluded":6},{"id":"deepseek-r1-0528-qwen3-8b","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"deepseek-r1-distill-llama-70b","collected":15,"contributing":12,"admittedWithoutWeight":0,"excluded":3},{"id":"deepseek-r1-distill-llama-8b","collected":7,"contributing":7,"admittedWithoutWeight":0,"excluded":0},{"id":"deepseek-r1-distill-qwen-1.5b","collected":11,"contributing":8,"admittedWithoutWeight":0,"excluded":3},{"id":"deepseek-r1-distill-qwen-14b","collected":11,"contributing":8,"admittedWithoutWeight":0,"excluded":3},{"id":"deepseek-r1-distill-qwen-32b","collected":11,"contributing":8,"admittedWithoutWeight":0,"excluded":3},{"id":"deepseek-r1-distill-qwen-7b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"deepseek-v3.2","collected":32,"contributing":27,"admittedWithoutWeight":0,"excluded":5},{"id":"deepseek-v3.2-speciale","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"deepseek-v4-flash","collected":50,"contributing":35,"admittedWithoutWeight":0,"excluded":15},{"id":"deepseek-v4-flash-vision-exp","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"deepseek-v4-pro","collected":72,"contributing":36,"admittedWithoutWeight":0,"excluded":36},{"id":"codegemma-7b-it","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"diffusiongemma-26b-a4b","collected":11,"contributing":9,"admittedWithoutWeight":0,"excluded":2},{"id":"gemini-2.5-flash","collected":52,"contributing":28,"admittedWithoutWeight":0,"excluded":24},{"id":"gemini-2.5-flash-lite","collected":29,"contributing":27,"admittedWithoutWeight":0,"excluded":2},{"id":"gemini-2.5-pro","collected":55,"contributing":26,"admittedWithoutWeight":0,"excluded":29},{"id":"gemini-3-flash-preview","collected":58,"contributing":49,"admittedWithoutWeight":0,"excluded":9},{"id":"gemini-3.1-flash-lite","collected":36,"contributing":34,"admittedWithoutWeight":0,"excluded":2},{"id":"gemini-3.1-pro","collected":184,"contributing":71,"admittedWithoutWeight":0,"excluded":113},{"id":"gemini-3.5-flash","collected":100,"contributing":89,"admittedWithoutWeight":0,"excluded":11},{"id":"gemini-3.5-flash-lite","collected":69,"contributing":64,"admittedWithoutWeight":0,"excluded":5},{"id":"gemini-3.6-flash","collected":76,"contributing":73,"admittedWithoutWeight":0,"excluded":3},{"id":"gemini-3.7-flash","collected":109,"contributing":89,"admittedWithoutWeight":0,"excluded":20},{"id":"gemini-3.8-flash","collected":117,"contributing":88,"admittedWithoutWeight":0,"excluded":29},{"id":"gemma-1-2b-it","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"gemma-1-7b-it","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"gemma-1.1-2b-it","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"gemma-1.1-7b-it","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"gemma-2-27b-it","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"gemma-2-2b-it","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"gemma-2-9b-it","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"gemma-3-12b-it","collected":27,"contributing":21,"admittedWithoutWeight":0,"excluded":6},{"id":"gemma-3-1b-it","collected":18,"contributing":13,"admittedWithoutWeight":0,"excluded":5},{"id":"gemma-3-270m-it","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"gemma-3-27b-it","collected":27,"contributing":21,"admittedWithoutWeight":0,"excluded":6},{"id":"gemma-3-4b-it","collected":22,"contributing":16,"admittedWithoutWeight":0,"excluded":6},{"id":"gemma-3n-e2b-it","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"gemma-3n-e4b-it","collected":17,"contributing":15,"admittedWithoutWeight":0,"excluded":2},{"id":"gemma-4-12b-it","collected":22,"contributing":20,"admittedWithoutWeight":0,"excluded":2},{"id":"gemma-4-26b-a4b-it","collected":27,"contributing":25,"admittedWithoutWeight":0,"excluded":2},{"id":"gemma-4-31b-it","collected":38,"contributing":35,"admittedWithoutWeight":0,"excluded":3},{"id":"gemma-4-e2b-it","collected":22,"contributing":20,"admittedWithoutWeight":0,"excluded":2},{"id":"gemma-4-e4b-it","collected":22,"contributing":20,"admittedWithoutWeight":0,"excluded":2},{"id":"recurrentgemma-2b-it","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"recurrentgemma-9b-it","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"llama-3.1-405b-instruct","collected":3,"contributing":0,"admittedWithoutWeight":0,"excluded":3},{"id":"llama-3.1-70b-instruct","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"llama-3.1-8b-instruct","collected":5,"contributing":0,"admittedWithoutWeight":0,"excluded":5},{"id":"llama-3.2-11b-vision-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"llama-3.2-1b-instruct","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"llama-3.2-3b-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"llama-3.2-90b-vision-instruct","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"llama-3.3-70b-instruct","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"llama-4-maverick","collected":32,"contributing":23,"admittedWithoutWeight":0,"excluded":9},{"id":"llama-4-scout","collected":27,"contributing":22,"admittedWithoutWeight":0,"excluded":5},{"id":"muse-glimmer-30b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"muse-spark-1.1","collected":73,"contributing":46,"admittedWithoutWeight":0,"excluded":27},{"id":"muse-spark-1.2","collected":68,"contributing":52,"admittedWithoutWeight":0,"excluded":16},{"id":"muse-spark-1.3","collected":84,"contributing":62,"admittedWithoutWeight":0,"excluded":22},{"id":"codestral-2508","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"devstral-2512","collected":24,"contributing":20,"admittedWithoutWeight":0,"excluded":4},{"id":"devstral-medium-2507","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"devstral-small-2507","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"labs-devstral-small-2512","collected":24,"contributing":21,"admittedWithoutWeight":0,"excluded":3},{"id":"labs-mistral-small-creative","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"leanstral-1.5","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"magistral-medium-2509","collected":23,"contributing":16,"admittedWithoutWeight":1,"excluded":6},{"id":"magistral-small-2509","collected":22,"contributing":17,"admittedWithoutWeight":0,"excluded":5},{"id":"ministral-3-14b","collected":23,"contributing":21,"admittedWithoutWeight":0,"excluded":2},{"id":"ministral-3-3b","collected":23,"contributing":21,"admittedWithoutWeight":0,"excluded":2},{"id":"ministral-3-8b","collected":23,"contributing":21,"admittedWithoutWeight":0,"excluded":2},{"id":"ministral-3b-2410","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"ministral-8b-2410","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"mistral-large-2411","collected":3,"contributing":0,"admittedWithoutWeight":0,"excluded":3},{"id":"mistral-large-3","collected":25,"contributing":21,"admittedWithoutWeight":0,"excluded":4},{"id":"mistral-medium-2505","collected":18,"contributing":13,"admittedWithoutWeight":0,"excluded":5},{"id":"mistral-medium-2508","collected":27,"contributing":19,"admittedWithoutWeight":1,"excluded":7},{"id":"mistral-medium-3.5","collected":45,"contributing":29,"admittedWithoutWeight":0,"excluded":16},{"id":"mistral-small-2506","collected":25,"contributing":22,"admittedWithoutWeight":0,"excluded":3},{"id":"mistral-small-4","collected":34,"contributing":27,"admittedWithoutWeight":1,"excluded":6},{"id":"open-mistral-nemo-2407","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"pixtral-12b-2409","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"pixtral-large-2411","collected":9,"contributing":9,"admittedWithoutWeight":0,"excluded":0},{"id":"voxtral-mini-2507","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"voxtral-small","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"kimi-dev-72b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"kimi-k2.6","collected":132,"contributing":33,"admittedWithoutWeight":0,"excluded":99},{"id":"kimi-k2.7-code","collected":30,"contributing":19,"admittedWithoutWeight":0,"excluded":11},{"id":"kimi-k3","collected":151,"contributing":70,"admittedWithoutWeight":0,"excluded":81},{"id":"kimi-linear-48b-a3b-instruct","collected":9,"contributing":9,"admittedWithoutWeight":0,"excluded":0},{"id":"kimi-vl-a3b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"kimi-vl-a3b-thinking-2506","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"nemotron-3-ultra","collected":72,"contributing":20,"admittedWithoutWeight":0,"excluded":52},{"id":"nvidia-nemotron-3-nano-30b-a3b-bf16","collected":35,"contributing":32,"admittedWithoutWeight":0,"excluded":3},{"id":"nvidia-nemotron-3-nano-4b-bf16","collected":11,"contributing":10,"admittedWithoutWeight":0,"excluded":1},{"id":"nvidia-nemotron-3-super-120b-a12b-bf16","collected":21,"contributing":20,"admittedWithoutWeight":0,"excluded":1},{"id":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","collected":16,"contributing":15,"admittedWithoutWeight":0,"excluded":1},{"id":"nvidia-nemotron-nano-12b-v2","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"nvidia-nemotron-nano-12b-v2-vl-bf16","collected":26,"contributing":24,"admittedWithoutWeight":0,"excluded":2},{"id":"nvidia-nemotron-nano-9b-v2","collected":24,"contributing":22,"admittedWithoutWeight":0,"excluded":2},{"id":"nvidia-nemotron-nano-9b-v2-japanese","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"gpt-3.5-turbo","collected":3,"contributing":3,"admittedWithoutWeight":0,"excluded":0},{"id":"gpt-3.5-turbo-1106","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"gpt-3.5-turbo-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"gpt-4","collected":8,"contributing":6,"admittedWithoutWeight":0,"excluded":2},{"id":"gpt-4-turbo","collected":6,"contributing":4,"admittedWithoutWeight":0,"excluded":2},{"id":"gpt-4.1","collected":17,"contributing":13,"admittedWithoutWeight":0,"excluded":4},{"id":"gpt-4.1-mini","collected":19,"contributing":16,"admittedWithoutWeight":0,"excluded":3},{"id":"gpt-4.1-nano","collected":18,"contributing":16,"admittedWithoutWeight":0,"excluded":2},{"id":"gpt-4o","collected":43,"contributing":5,"admittedWithoutWeight":0,"excluded":38},{"id":"gpt-4o-mini","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"gpt-5","collected":103,"contributing":81,"admittedWithoutWeight":0,"excluded":22},{"id":"gpt-5-mini","collected":78,"contributing":57,"admittedWithoutWeight":0,"excluded":21},{"id":"gpt-5-nano","collected":45,"contributing":41,"admittedWithoutWeight":0,"excluded":4},{"id":"gpt-5-pro","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"gpt-5.1","collected":54,"contributing":34,"admittedWithoutWeight":0,"excluded":20},{"id":"gpt-5.2","collected":77,"contributing":71,"admittedWithoutWeight":0,"excluded":6},{"id":"gpt-5.2-pro","collected":3,"contributing":2,"admittedWithoutWeight":0,"excluded":1},{"id":"gpt-5.3-codex","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"gpt-5.3-codex-spark","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"gpt-5.4","collected":110,"contributing":73,"admittedWithoutWeight":0,"excluded":37},{"id":"gpt-5.4-mini","collected":91,"contributing":87,"admittedWithoutWeight":0,"excluded":4},{"id":"gpt-5.4-nano","collected":81,"contributing":77,"admittedWithoutWeight":0,"excluded":4},{"id":"gpt-5.4-pro","collected":3,"contributing":2,"admittedWithoutWeight":0,"excluded":1},{"id":"gpt-5.5","collected":307,"contributing":167,"admittedWithoutWeight":0,"excluded":140},{"id":"gpt-5.5-pro","collected":6,"contributing":5,"admittedWithoutWeight":0,"excluded":1},{"id":"gpt-5.6-luna","collected":221,"contributing":165,"admittedWithoutWeight":0,"excluded":56},{"id":"gpt-5.6-sol","collected":435,"contributing":192,"admittedWithoutWeight":0,"excluded":243},{"id":"gpt-5.6-terra","collected":246,"contributing":176,"admittedWithoutWeight":0,"excluded":70},{"id":"gpt-6-astra","collected":220,"contributing":146,"admittedWithoutWeight":0,"excluded":74},{"id":"gpt-oss-120b","collected":48,"contributing":43,"admittedWithoutWeight":0,"excluded":5},{"id":"gpt-oss-20b","collected":46,"contributing":43,"admittedWithoutWeight":0,"excluded":3},{"id":"o1","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"o1-pro","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"o3","collected":22,"contributing":17,"admittedWithoutWeight":0,"excluded":5},{"id":"o3-mini","collected":35,"contributing":31,"admittedWithoutWeight":0,"excluded":4},{"id":"o3-pro","collected":5,"contributing":4,"admittedWithoutWeight":0,"excluded":1},{"id":"o4-mini","collected":23,"contributing":19,"admittedWithoutWeight":0,"excluded":4},{"id":"qvq-max","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qvq-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-3.8-max","collected":85,"contributing":23,"admittedWithoutWeight":0,"excluded":62},{"id":"qwen-coder-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-coder-turbo","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-flash-character","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-long","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-math-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-math-turbo","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-max","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-omni-turbo","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-plus-character","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-plus-character-ja","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-turbo","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-vl-max","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen-vl-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-0.6b","collected":26,"contributing":24,"admittedWithoutWeight":0,"excluded":2},{"id":"qwen3-1.7b","collected":31,"contributing":28,"admittedWithoutWeight":0,"excluded":3},{"id":"qwen3-14b","collected":40,"contributing":35,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3-235b-a22b","collected":30,"contributing":24,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3-235b-a22b-instruct-2507","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"qwen3-235b-a22b-thinking-2507","collected":29,"contributing":21,"admittedWithoutWeight":0,"excluded":8},{"id":"qwen3-30b-a3b","collected":33,"contributing":27,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3-30b-a3b-instruct-2507","collected":18,"contributing":13,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3-30b-a3b-thinking-2507","collected":25,"contributing":20,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3-32b","collected":36,"contributing":31,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3-4b","collected":17,"contributing":16,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-4b-instruct-2507","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"qwen3-4b-thinking-2507","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-8b","collected":40,"contributing":35,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3-coder-30b-a3b-instruct","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-coder-480b-a35b-instruct","collected":15,"contributing":12,"admittedWithoutWeight":0,"excluded":3},{"id":"qwen3-coder-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-coder-next","collected":18,"contributing":17,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-coder-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-max","collected":25,"contributing":3,"admittedWithoutWeight":0,"excluded":22},{"id":"qwen3-next-80b-a3b-instruct","collected":13,"contributing":11,"admittedWithoutWeight":0,"excluded":2},{"id":"qwen3-next-80b-a3b-thinking","collected":17,"contributing":15,"admittedWithoutWeight":0,"excluded":2},{"id":"qwen3-omni-30b-a3b-instruct","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-omni-30b-a3b-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-omni-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-vl-235b-a22b-instruct","collected":14,"contributing":12,"admittedWithoutWeight":0,"excluded":2},{"id":"qwen3-vl-235b-a22b-thinking","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-2b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-vl-2b-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-vl-30b-a3b-instruct","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-30b-a3b-thinking","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-32b-instruct","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-32b-thinking","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-4b-instruct","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-4b-thinking","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-8b-instruct","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-8b-thinking","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3-vl-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3-vl-plus","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3.5-0.8b","collected":25,"contributing":22,"admittedWithoutWeight":0,"excluded":3},{"id":"qwen3.5-122b-a10b","collected":36,"contributing":32,"admittedWithoutWeight":0,"excluded":4},{"id":"qwen3.5-27b","collected":25,"contributing":21,"admittedWithoutWeight":0,"excluded":4},{"id":"qwen3.5-2b","collected":26,"contributing":23,"admittedWithoutWeight":0,"excluded":3},{"id":"qwen3.5-35b-a3b","collected":34,"contributing":27,"admittedWithoutWeight":0,"excluded":7},{"id":"qwen3.5-397b-a17b","collected":89,"contributing":37,"admittedWithoutWeight":0,"excluded":52},{"id":"qwen3.5-4b","collected":26,"contributing":23,"admittedWithoutWeight":0,"excluded":3},{"id":"qwen3.5-9b","collected":31,"contributing":25,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3.5-flash","collected":9,"contributing":2,"admittedWithoutWeight":0,"excluded":7},{"id":"qwen3.5-omni-flash","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3.5-omni-plus","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"qwen3.5-plus","collected":6,"contributing":1,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3.6-27b","collected":41,"contributing":35,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3.6-35b-a3b","collected":40,"contributing":34,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3.6-flash","collected":8,"contributing":2,"admittedWithoutWeight":0,"excluded":6},{"id":"qwen3.6-plus","collected":29,"contributing":14,"admittedWithoutWeight":0,"excluded":15},{"id":"qwen3.7-flash","collected":10,"contributing":5,"admittedWithoutWeight":0,"excluded":5},{"id":"qwen3.7-max","collected":69,"contributing":21,"admittedWithoutWeight":0,"excluded":48},{"id":"qwen3.7-plus","collected":41,"contributing":26,"admittedWithoutWeight":0,"excluded":15},{"id":"qwen3.8-2.4t-a95b","collected":17,"contributing":15,"admittedWithoutWeight":0,"excluded":2},{"id":"qwen3.8-27b","collected":66,"contributing":54,"admittedWithoutWeight":0,"excluded":12},{"id":"qwen3.8-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qwen3.8-flash-next","collected":16,"contributing":14,"admittedWithoutWeight":0,"excluded":2},{"id":"qwq-plus","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"grok-4.20-0309-non-reasoning","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"grok-4.20-0309-reasoning","collected":14,"contributing":0,"admittedWithoutWeight":0,"excluded":14},{"id":"grok-4.20-multi-agent-0309","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"grok-4.3","collected":77,"contributing":72,"admittedWithoutWeight":0,"excluded":5},{"id":"grok-4.5","collected":67,"contributing":47,"admittedWithoutWeight":0,"excluded":20},{"id":"grok-4.6","collected":119,"contributing":90,"admittedWithoutWeight":0,"excluded":29},{"id":"grok-build-0.1","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-5.3-flash","collected":37,"contributing":32,"admittedWithoutWeight":0,"excluded":5},{"id":"glm-5.3","collected":60,"contributing":34,"admittedWithoutWeight":0,"excluded":26},{"id":"glm-5.2","collected":122,"contributing":64,"admittedWithoutWeight":0,"excluded":58},{"id":"glm-5.1","collected":95,"contributing":27,"admittedWithoutWeight":0,"excluded":68},{"id":"glm-5","collected":30,"contributing":18,"admittedWithoutWeight":0,"excluded":12},{"id":"glm-4.7","collected":33,"contributing":26,"admittedWithoutWeight":0,"excluded":7},{"id":"glm-4.7-flashx","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4.6","collected":30,"contributing":26,"admittedWithoutWeight":0,"excluded":4},{"id":"glm-4.5","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"glm-4.5-x","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4.5-air","collected":15,"contributing":12,"admittedWithoutWeight":0,"excluded":3},{"id":"glm-4.5-airx","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4-32b-0414-128k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4.7-flash","collected":25,"contributing":19,"admittedWithoutWeight":0,"excluded":6},{"id":"glm-4.5-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4.6v","collected":29,"contributing":26,"admittedWithoutWeight":0,"excluded":3},{"id":"glm-4.6v-flashx","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4.5v","collected":27,"contributing":24,"admittedWithoutWeight":0,"excluded":3},{"id":"glm-4.6v-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-5-turbo","collected":9,"contributing":8,"admittedWithoutWeight":0,"excluded":1},{"id":"glm-5v-turbo","collected":11,"contributing":9,"admittedWithoutWeight":0,"excluded":2},{"id":"glm-4.1v-9b-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-z1-rumination-32b-0414","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-z1-9b-0414","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-z1-32b-0414","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4-9b-0414","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4-32b-0414","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4-9b-chat","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"glm-4-9b-chat-1m","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-4v-9b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-edge-1.5b-chat","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-edge-4b-chat","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-edge-v-2b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"glm-edge-v-5b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"chatglm-6b","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"chatglm2-6b","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"chatglm2-6b-32k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"chatglm3-6b","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"chatglm3-6b-32k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"chatglm3-6b-128k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"codegeex4-all-9b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"autoglm-phone-9b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"autoglm-phone-9b-multilingual","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogagent-9b-20241220","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"codegeex2-6b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"visualglm-6b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogvlm-chat-hf","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogagent-chat-hf","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogagent-vqa-hf","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogvlm2-llama3-chat-19b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogvlm2-llama3-chinese-chat-19b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"cogvlm2-video-llama3-chat","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"minimax-m3","collected":75,"contributing":25,"admittedWithoutWeight":0,"excluded":50},{"id":"minimax-m2.7","collected":84,"contributing":20,"admittedWithoutWeight":0,"excluded":64},{"id":"minimax-m2.5","collected":14,"contributing":9,"admittedWithoutWeight":0,"excluded":5},{"id":"minimax-m2.1","collected":14,"contributing":12,"admittedWithoutWeight":0,"excluded":2},{"id":"minimax-m2","collected":16,"contributing":12,"admittedWithoutWeight":0,"excluded":4},{"id":"minimax-text-01","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"minimax-vl-01","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"minimax-m1-40k","collected":9,"contributing":9,"admittedWithoutWeight":0,"excluded":0},{"id":"minimax-m1-80k","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"synlogic-32b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"synlogic-mix-3-32b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"synlogic-7b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"minimax-m2-her","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"command-a-plus-05-2026","collected":35,"contributing":18,"admittedWithoutWeight":0,"excluded":17},{"id":"command-a-03-2025","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"command-r7b-12-2024","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"command-a-translate-08-2025","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"command-a-reasoning-08-2025","collected":10,"contributing":0,"admittedWithoutWeight":0,"excluded":10},{"id":"command-a-vision-07-2025","collected":4,"contributing":0,"admittedWithoutWeight":0,"excluded":4},{"id":"command-r-08-2024","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"command-r-plus-08-2024","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"command-r-03-2024","collected":11,"contributing":0,"admittedWithoutWeight":0,"excluded":11},{"id":"command-r-plus-04-2024","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"command-light","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"command","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"tiny-aya-global","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"tiny-aya-earth","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"tiny-aya-fire","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"tiny-aya-water","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"c4ai-aya-expanse-32b","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"c4ai-aya-vision-32b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"c4ai-command-r7b-arabic-02-2025","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"c4ai-aya-expanse-8b","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"c4ai-aya-vision-8b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"aya-23-8b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"aya-23-35b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"aya-101","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"north-mini-code-1-0","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"north-micro-vision-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-4","collected":18,"contributing":12,"admittedWithoutWeight":0,"excluded":6},{"id":"phi-4-mini-instruct","collected":15,"contributing":14,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-4-reasoning-vision-15b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-3-mini-4k-instruct","collected":2,"contributing":0,"admittedWithoutWeight":0,"excluded":2},{"id":"phi-3-mini-128k-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-3.5-mini-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-4-multimodal-instruct","collected":6,"contributing":6,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-4-reasoning","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-mini-moe-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-tiny-moe-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-3-medium-4k-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-3-medium-128k-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-3-small-8k-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-3-small-128k-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-3-vision-128k-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-3.5-vision-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-3.5-moe-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-4-reasoning-plus","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"phi-4-mini-reasoning","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"phi-4-mini-flash-reasoning","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mai-ds-r1","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mai-thinking-1","collected":19,"contributing":0,"admittedWithoutWeight":0,"excluded":19},{"id":"mai-code-1-1-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mai-code-1-flash","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"amazon-nova-micro","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"amazon-nova-lite","collected":27,"contributing":14,"admittedWithoutWeight":0,"excluded":13},{"id":"amazon-nova-pro","collected":26,"contributing":13,"admittedWithoutWeight":0,"excluded":13},{"id":"amazon-nova-premier","collected":30,"contributing":13,"admittedWithoutWeight":0,"excluded":17},{"id":"amazon-nova-2-lite","collected":75,"contributing":51,"admittedWithoutWeight":0,"excluded":24},{"id":"amazon-nova-2-pro-preview","collected":66,"contributing":44,"admittedWithoutWeight":0,"excluded":22},{"id":"deepseek-v4-pro-0424","collected":48,"contributing":45,"admittedWithoutWeight":0,"excluded":3},{"id":"doubao-seed-1.6","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-1.6-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-1.6-vision","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-1.8","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.0-code","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.0-lite","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.0-mini","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.0-pro","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.1-pro","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-2.1-turbo","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-character","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"doubao-seed-code","collected":14,"contributing":13,"admittedWithoutWeight":0,"excluded":1},{"id":"doubao-seed-evolving","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"seed-coder-8b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"seed-coder-8b-reasoning","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"seed-oss-36b-instruct","collected":17,"contributing":12,"admittedWithoutWeight":0,"excluded":5},{"id":"exaone-3.0-7.8b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"exaone-3.5-2.4b-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"exaone-3.5-32b-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"exaone-3.5-7.8b-instruct","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"exaone-4.0-1.2b","collected":24,"contributing":22,"admittedWithoutWeight":0,"excluded":2},{"id":"exaone-4.0-32b","collected":26,"contributing":23,"admittedWithoutWeight":0,"excluded":3},{"id":"exaone-4.0.1-32b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"exaone-4.5-33b","collected":13,"contributing":11,"admittedWithoutWeight":0,"excluded":2},{"id":"exaone-deep-2.4b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"exaone-deep-32b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"exaone-deep-7.8b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"k-exaone-2.0-750b-a37b","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"k-exaone-236b-a23b","collected":27,"contributing":25,"admittedWithoutWeight":0,"excluded":2},{"id":"step-3.5-flash","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"step-3.7-flash","collected":19,"contributing":17,"admittedWithoutWeight":0,"excluded":2},{"id":"step3","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"step3-vl-10b","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"solar-10.7b-instruct-v1.0","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"solar-mini-250422","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"solar-open-100b","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"solar-open2-250b","collected":11,"contributing":9,"admittedWithoutWeight":0,"excluded":2},{"id":"solar-pro-preview-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"solar-pro2-251215","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"solar-pro3-260323","collected":19,"contributing":17,"admittedWithoutWeight":0,"excluded":2},{"id":"solar-pro4-260806","collected":15,"contributing":12,"admittedWithoutWeight":0,"excluded":3},{"id":"mimo-7b-rl","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"mimo-7b-rl-0530","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-7b-rl-zero","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-7b-sft","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-v2-flash","collected":28,"contributing":26,"admittedWithoutWeight":0,"excluded":2},{"id":"mimo-v2.5","collected":28,"contributing":17,"admittedWithoutWeight":0,"excluded":11},{"id":"mimo-v2.5-pro","collected":41,"contributing":29,"admittedWithoutWeight":0,"excluded":12},{"id":"mimo-vl-7b-rl","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-vl-7b-rl-2508","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-vl-7b-sft","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"mimo-vl-7b-sft-2508","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-0.3b-pt","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-21b-a3b-pt","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-21b-a3b-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-300b-a47b-pt","collected":12,"contributing":11,"admittedWithoutWeight":0,"excluded":1},{"id":"ernie-4.5-vl-28b-a3b-pt","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-vl-28b-a3b-thinking","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-vl-424b-a47b-pt","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qianfan-vl-3b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qianfan-vl-70b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"qianfan-vl-8b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-0.5b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-1.8b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-4b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-7b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-7b-instruct-0124","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-a13b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hy3","collected":16,"contributing":13,"admittedWithoutWeight":0,"excluded":3},{"id":"hy3-preview","collected":18,"contributing":16,"admittedWithoutWeight":0,"excluded":2},{"id":"hy4-preview","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"hunyuan-a52b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"wedlm-7b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"wedlm-8b-instruct","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"youtu-llm-2b","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-5.1","collected":1,"contributing":0,"admittedWithoutWeight":0,"excluded":1},{"id":"ernie-5.0","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-5.0-thinking-preview","collected":13,"contributing":12,"admittedWithoutWeight":0,"excluded":1},{"id":"ernie-5.0-thinking-latest","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-5.0-thinking-exp","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-turbo-32k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-turbo-128k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-turbo-20260402","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-turbo-vl","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"ernie-4.5-turbo-vl-32k","collected":0,"contributing":0,"admittedWithoutWeight":0,"excluded":0},{"id":"minicpm5-2b","collected":15,"contributing":13,"admittedWithoutWeight":0,"excluded":2},{"id":"agnes-2.5-pro-alpha","collected":15,"contributing":13,"admittedWithoutWeight":0,"excluded":2},{"id":"mistral-large-2407","collected":10,"contributing":9,"admittedWithoutWeight":0,"excluded":1},{"id":"deepseek-v4-flash-0424","collected":49,"contributing":46,"admittedWithoutWeight":0,"excluded":3}],"observations":[{"id":"ad37bcc3a2f8fbe16d11bf28","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53d28fbb092f0489790e15af","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfda8506d8f2f566c79b7f13","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe901ec4d3a93de8dca353cd","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3451d3b73f08ab58971036d1","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"252993f87b0a46d83c161b41","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e7d0cd968f12fcd6837a961","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d22306241e32f3b35c337299","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5eca0b0dc509f3d924e864a1","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"83831ab910de6136f183d0f6","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d2ba4d99bd8f7a014e1bc82","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"125887c34f0290cf5cb09b60","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a8bae15560fd5c9da384d6e","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b41b48e6be3dfa1ef6d8980d","modelId":"agnes-2.5-pro-alpha","configurationId":"agnes-2.5-pro-alpha--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14d799d1a84fa43e5418d7b3","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77a00d93b0f5ef316bc0a1d8","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2a0105959356ea86cbdc800","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64756b2e556ca7f8a17d562d","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c3fb19ff79ef2b89ad8b459","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d76da886e62765c45f4009d7","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43c45983fe0fb2950ee9e471","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0751248f0bb7ed65861e7389","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ec7663d5fc9ea3c3a9845c7","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87be9250018af73102dd2d5f","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31ecbdac99d99d717eb4b69e","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee6d3dc313301dfa2d7580f1","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4993197d550d0437d05637f2","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0cbb3c39f8958e73c8b93c4","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77f69a1006c2ef2b6abd62bd","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1aea748fca8ce6be15473ca6","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b42bcc7d72018b481f9d6c8","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"341be8170b3f5df517a7b9f0","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9adff1036db8300025ee8851","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a898268580591f6bc1b5017b","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d1e0d12a0e2697685e738b4","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb07aadd4166403d7629e25e","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"617a75985f9d2bf4173a41f9","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3e8d9bb698a5328e7da979c","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26aa72ea349d3636c0c207d2","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49a7a5a737f5b970e9b48dc4","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60e3e99d7079c86ec8901d6a","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"880b196d9ae0044312f5f0b0","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b7053d76bf32edf1ce36ca6","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81d6342d15ab0e2f8e535ccd","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e87f48fb86040e2c58054ee","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7325ca2c64074f1d8d7a2c6","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f3218cb03af524271bbe7b0","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3af2c688d4c527bc96bdfee4","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a4fea5769cd4ea595e3f20e","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"275519f4bf513ae6169d9b06","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff7874fe6f63e29676c8c47a","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"971a463f2747f1886585e328","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbcffb6add1d04899e8b3269","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"83d446faabe43549fc8be324","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"05bbf3b36c46a5d97b7af99f","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5b5db7acabdd817b3e7dd73e","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"afb57bb88ef56dd427661b2d","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c6d58f64d07be8bd8224d07","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9230424096816687b209590","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e84abbf7f996ec789cd2885","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71c943ab8c5eab00a4c30043","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"450be57bac445f754df60261","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4061e9966b4ff81008aa5344","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04fb036f055cd49b327a6ded","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e343ed4dd2e1401efdacad3","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5dfd55398cbbd3eae5a8ccb","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8eaa999820b9e6805a4b51bf","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb49445c621170b904099ffd","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9703171c0c398856408c474","modelId":"amazon-nova-2-lite","configurationId":"amazon-nova-2-lite--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa4583be3fa22d830b8f8f25","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3846226f9a4f5dd9d89d3dd1","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6175ce4adc218cc2822fcbf9","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9ff4d8772bb55e2ef2ddcb7","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de4a8f08e90e822753707555","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27dd6af97bc82a3f33e9bbb4","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"163665ac054efd9d9a38517d","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"576f4f9c9b1effaaed221378","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dde0536564f2839a2ce52d8","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e64b707ff2d699c4ecab8798","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"633313af7ea748295dbcd2a8","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06219722cf816fd5e2329eb6","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a696000446e4a94aada1fdcb","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7292759b8cb168b50cfc12a5","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31db5b88eadca6dc97116930","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee7d2db9b09a1f2983f7db7b","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38aa2e7ea58f399abf54de70","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b1f0df1aefef1081c703ec3","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"209c17d4d5266a21ce2de7df","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b14ffa0e6e2c2eaae9e72551","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"822022aa52507b9b3001d3c1","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8a630ac2b0ff385963c2da4","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fe32683ff453994e752cf0b","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5653889b31519d66e60b5b3c","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"143991a4a457eea92fe5171c","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd2de967d5e4ceefd8d21f5f","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d03bd7f7196acd07f6a41e5","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce55605faf854659ff0fe76f","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc95d33f7ca12e3fd5fe88fc","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b491e7d678f7eb03aa97fe4f","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"485ff3ed3089d2ec72eb65fb","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f803a4fc980517eb71432d0","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e48ea7bbae50fbfc4709191","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f918288816d545d015333d7a","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"83c3679cc2593a1416e8ece0","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"25293590da29402fbd862593","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1cb257283aefcb143faca8c","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e507780d68e9a88b3fe816c3","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8fa487d441e2a3bff731883","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a17ba591cb2cb5153c9a6064","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"073593c114d374a6b5814324","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d67198df6216e3d8b684dfaa","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f88cd83a215ca158a04fc06","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77e985c0ed8b2995e6b8a80d","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b46dbb37766de1e2ef10d6de","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"366ec0058521e2c38f0622be","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f56f639149bec0565169758c","modelId":"amazon-nova-2-pro-preview","configurationId":"amazon-nova-2-pro-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50e4adca8e5e54dc5a129468","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"adf5df0b30d27f83e52f2b51","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff486d9ba46adad27a1b6fe4","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbd1d83f7580735392e6f6a7","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"981168cc7575baa0277b03a4","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6feffecc4d281a47d9a8c63c","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbdd0586ea1c53079fda7843","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7dd1a3d260f548765e07a7db","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8e86b20efeee800f08898bd","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3a7675bf193929b296e1238","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd3e68f24b42e3314808e348","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed17e3be2f9a297198964c70","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c810f78cb4cfe1a60c148b93","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02860b6478118aafcbe8cda2","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69ddc6a403ed9b335c7c7e51","modelId":"amazon-nova-lite","configurationId":"amazon-nova-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c395cbf5898af86d26300d73","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfcec14d811a655ca4726508","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db9b99c98dd617c9ca05910d","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"696c084e4d6c62ab15b53492","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8a60f4c48d2cf35f26ad74c","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e8455203b39b886b2967732","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aef838f6a1d2eca33b5a1e33","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffa04be81f3227c6f19350f1","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35e37d3045a2a291273b84f1","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03faabf6a483486fa063a636","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"abebfd3cf4beb6117af462cc","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88ec995dfbbdc4b5240ddad1","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19d78b7b4a3613704624e4c9","modelId":"amazon-nova-micro","configurationId":"amazon-nova-micro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce9a2089796d737603a17e0b","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2f040f4479911816988b68b","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56f117757019799897341310","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e3b171515df1dcd1001b493","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a6eaae484ab8fcb709d1c0f","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f0a56bbcc02e28b010b7360","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8be501c4015a8228e5bf59d1","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63e379977a372098a782ec00","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c279ec3f04cf3fdc739c887","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"354ff394a1c479d16d1ff096","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ba3c2f0a8977ad288a8f0ec","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fe566bdc8b0fe8917d76032e","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bfbe8f57f24704b45f141ff","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3abff7933c0a42c95c4f53c9","modelId":"amazon-nova-premier","configurationId":"amazon-nova-premier--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"541b9cd8656670591c6a1d18","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a068df3721adea27be27ecf","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4896e593ff5512235c65933","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fca9c963afc237552313f230","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b7c848ef0c5b4072692c53a","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1718757623befb2b04cdffa0","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a72aadc62751bdabe32c810","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc2fc962c57c7a95ec0f5ab6","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b21dffdfeaeb4feaa7217c7","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99044be57784aba47c270823","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffd340540d54b4c2be0c4e29","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0050677da9a66bbd582ceef2","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"180bc2e6c945ab26a8631548","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8eefcfd98bc646739e26568","modelId":"amazon-nova-pro","configurationId":"amazon-nova-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5222e61d0123ece9278f23ce","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19d3225518b4ccc8a6be41a6","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ee4fa47e6674b3096c09c9e","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"680b64b696a83786a6320608","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54215a497f41ddcb020ffe22","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d97f93bf22fc4c9fca52916","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de3bcc367e4e2ad72d9e19cd","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"428780032df0d32274761c4c","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c449154a748a844ff65a5ae","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ad95d72f436373a20ff679a","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5d9558a6fc07487bf1ba370","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1463611e4689ae0b5f7fe952","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"744e2629ba0b96b375ed57e4","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9966b462b29331ecbde42490","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"577b7d5cb453524e4357e7a2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b65a404336eb24164c2e979","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"605ea36789b69436cd8ec072","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0061ee612fdeb8168aa309b","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a12cb0123ccdceb07c3e79b","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1d9353cb007b83474b87e3c","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9601059aaf11a654942910e5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28d5bc6a86675295d42cb6c0","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f9372a183ee68e6b48bb18c","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"332952f68252290ee6a5a920","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47f74dad473d960addbaf5cd","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd5f5a2e4f7c743ac93db432","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"557dcb6d136782df1d6e3170","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59377a8e5a165f1e29a9f170","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3efb0703151365e0a5c57ad7","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eade32ea719c5f0ba716c1d","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c326836891084fe24c0ed23","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c44bf1486b2f7dadbe84989a","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"667b208122296e70c88bf453","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c767d5ab6384b96f9010a82","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50b1ef50758cbe6e3e7b2670","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0db58b309bd9c9bcf504997e","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e19c0045c0eaec856209c2","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4cff675467f54077a118366b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"706f331d94b42da72a1e1201","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"598af2bd77d73da5cec3e552","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8523e5443d536bd47fd6505","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f4ffc277e559a8291b00d73","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"843c626e866362d8cd87a028","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"399a2b5e968764b4790f969c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31bfa9b9f74ca86a50b0156c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f39111d381d1364e81a542b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eacb51c8e87a7c410276ba17","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45fa7394cbd38c801f20474a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"618d9e76b6eb57ca3bcfb5b1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67e728b27e7cac9181b83ed6","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e8acabfa89f8d0bb6a4cea8","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca8f62d35b4afeef27e6ccdb","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d38118e2ffb318c2aa3e3814","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"833da61d17bd29175043cf58","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c85fa539e15511983dd0461c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7495dc8ba744e6c00403ec2c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fab1974add12bcdedee8d5f","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c48a3bf4d6b9ee989cb4301","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4fb4fe89df5d58f1d649e5a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22a61bb91a2a848a7aaa01f4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56cf34e23d01d54673edd390","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dd9ffce8af725c94fc62c52","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5e184202558abc3af535731","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"960305805fd5bd6c6dd4f56b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ecc02773bd7ff3ec9c0186b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a28c83371bfa7c7f4036bb38","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56e19612c165fd00da95d347","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68b36c309fc71fc38607f10d","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ffc561cd3a97d25c4d83e56","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82a94f00f660b6b69c560e78","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01584fe92740dab26d1a82cb","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb980b508bb7de6e8a60602e","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c93a148cc00a00c4296dd23e","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09418514956dfe8150fe5db8","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b1a819b085a3ec294c7e8de","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e98323dba07921b9c5c62e1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e48dbc098b0fb31a3a874828","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f04626f3b72848c21148576e","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2a4d9bd93f2fc6f534b5fe9","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6495b66e8d711ccf1b3b50cd","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35674df3f02b7941e8620349","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"597a3f60fc7069ecd1b62427","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"58328d3a42b280731f127b87","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"37d9e698a4a4cb9b195ba794","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"896645ed1ede361c8c0efe9a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"28a67006474651e3423b9c3a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e923688d79048f36fcbf5cf8","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a9b48125a7a12fa9c2ed18f","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7f05e3e2a9ec8e6cd3fcc35","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7800dd959c9c9c332f79e99","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8b018762a29006e12d9587b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67cf4f284cf9fea377b8405b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"559bdd63a6706d0f6fee9a81","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ca32c0218ee7be58ce7af69","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9483878dd9257fc729ce79af","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5b00c8a4cdf9cbf28308958","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11fec5746028caad463b6b63","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d93eaf0e3e460c62a67ccf6a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"152c5a0d427284e3b05fd5c7","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bee8344681eb6c5aba76cc3","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c63a5aa101c5042ae00499a8","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6843d8f13eb32f436251813d","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17776df89fd155c5eb6e37a5","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"003769ec709037bb79e89924","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8258b5f53b25da1e19eacdc4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25ed925d0c2280f2ed57c925","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65ecf25aa32fe1f6291195b4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2f7245010569d80dd44161a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"352aaae7d9ca1a02b8614131","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dca6ae59f27fcd98e0970afa","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed1a32448622df1b6e6a2c76","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e32cbb2b2e540c705e2682f4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29140dd5416b42ea788cab53","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07f22f183aad2883655252ba","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01e39ca976d82e99ab3b9be8","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12613d0c4a993819d4dbdce2","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7818278bf3f2e55b20200337","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c47d4da68b5bf084c0e9f76","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6f6b975bd6c103d42d44df7","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2705174dc70afd80971d2f06","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"468ce6503360afbf169e36d2","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bea6cc2230d015678cd7aa2a","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5791f8e4e8fde45e7fb66886","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b99ba0207b1b453a50cc06f6","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db86f964ce75806a4ed189c1","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2806b54519e581523aedfb18","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fcc39bdab94bc050439a0683","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d65a5ce38f7183b304600ef1","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d49a8d283248db5fd5e0e34","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"509191a186cf539ad56147b5","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3486d7ce6fefedd596a57fcc","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffb8c6eaab9ce5c0d4156a57","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4ba8ec0f816cf38c66148d7","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf094d38468fec8c0e27adb0","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4261bc632ec7f2d41fba238e","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b93459d07cc3fd00f317e844","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77e2abafe21efe47759564a5","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad5e1bd45ba3b1854e2f521b","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f10d5c0ef1a592623e7cd20","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0905c2c3dc408b46b86803cb","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc24d97f80cf49b75640cc90","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"acf88c56fae018e5c7c5ee48","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23ecbd3ca8a4df7f15ba1758","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aacbc7330857d739a0430710","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cbf4db0f85b1a9026199f02","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2da4c6c978b2c7fcd202e37f","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e9c6fcae19f0b875efc5d431","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8862c4640b472096ac1a95b1","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4ab94d87626afc466c301f6","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb4ff6598c0f6e58acbeb5e6","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5067c956bfdd13d3de44ff4f","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a14c2426307d122868a12c50","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d76d253d766085ae9b980404","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d18cf2172a3d45ea811b2610","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c85fcef255e2897eb9b9056","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64b4f035f94e078ac148dbd9","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95e92e71b76ea62d02ca6cd4","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-32k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba3f20c5292fdd48682b2099","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-1k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2c60a47ba43609d5f7802f0","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-8k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4fbbe2e4e16767233d36d08","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-16k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"777d836c2aab8b1a753b4fe5","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f517ae1f51f86c35cfb0be4","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"364e593f02f62ed75fd18066","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85c81b940cce2a4e217f39f1","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"108fba49cb2e133b5c3292c6","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1958b99c15a27c0d8d0aba84","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1db7ea0ee512320711194d0","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0e35583919bfa925e3253c4","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1db3648c4fe84e124fa696fc","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea5097c6ae66554091a20a26","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be7e6806ef9ffabbe47660e5","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8afa47b2b589899209075fd","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"555c0f000e8ee371e88e57a2","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"321deea5aaf37c3322817314","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa884eeb86cb180cbd489bac","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b0e8231a510903a76fb9715","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5314fc9ebb9ae8bcdf75b98e","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d150283271e045da32ceab8","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34e7fcfb97c55289d0bf4b48","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46aff7e0e196660d8e321636","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"299cfb2488b1b12fb8bae121","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"06bc173078345ce534aba7f3","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"313fe229263c5d3be7780b9b","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8667c79135a6fbe7cc5fa1e4","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"993af034623aaedde3a3de9b","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08adca9aa4e2043174db9373","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42a28e056d264ff2cdaead6f","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87149dbfd56c9450a6af41d4","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"883c249929e963c72cf44009","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1df24d4a693777637b218ad1","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edea07f755a646e80b59fc5c","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1079b6e09e35fc3bf7181c3d","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82d31085d8e7dd2df2cd8276","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67dabb07507f3af6b80f475b","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7837606fc0dd1e1d67c4be7","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3c5440c1476d374192760b2","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c7a4e4716cfa28abfd88e18","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08cc9eb85e32224bc1421970","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01eba8e6568c716b434ceb9a","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a199353fd286c627af757e1a","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"819fa99734059e55c305dfb1","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f8d701703320627812d694d","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97a5c4bf360e00751e6fa217","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67766ea16f853c7ff84a817a","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"46b85c1426a94560e8491464","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"668e62a5d42e2bef73937cce","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"baa04b456361440058325f0b","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63d40fb93f723399e39df0a3","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a0b73f4ddc5a887e70736a","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c239c04b17c69baedb9f629a","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3fe5100a1b70dc45580f44b","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3da84ad297936aa3afed7671","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc808875c949319a9c28aeb4","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d89c7fdc274f08893e4629d1","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06f217cc8cc75c7a1ed581a5","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f95de089dfd26220d76b06bd","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/swe_bench_pro_public","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d191d0319c4a21ff3c9f3e0","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d97fa34c6d74197e5651c44d","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"091e5cb1037fed300fe45855","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0cb265c650fe3cdc983ffe8","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d44e895b9101241914947dee","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2683b9293f59efe8aa064de8","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89994a0a4f9540721a978124","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8ead59f49e97a9f171599fc","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c82836191e21678e7e1d886","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dddb3b75d1a29c96c9cd5fab","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af98b790618965ff81b8c93c","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05438d532cb2f9dd8da92413","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af7b2396e18ba580ebda89a3","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a319b3c96aa5cc4abdee521","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8700e3e2f9d7fafb7c78712f","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6035dc69613ed9a74dd7118","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1ea4bf0714b2256e0cabb78","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26ce26f97e9518e71d17a846","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"032009afa3dbd206c24621a1","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0fec6d78078202d2ff626c29","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ef24af42f560d182356c45d7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78c91c33a4b44b6c86d050ba","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"154a39d23fcfec07f4dba3e9","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e814f42f29863fa0d0aafd9","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"227305481fdd337950a1ec37","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbf9b4814fb13eef00b601a7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99a7a4ac71a72c0520740983","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0461d2eb2969cf81f0a93ea2","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da713bbecda4ed9bb6e4575a","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1a9e8085f72db6bccf6962b","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38bd39336f87942a65930af7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96e07d2acdac72606809adc6","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"396c304045bfd21fed6494cd","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55ab6f2bb1306e9de5b5cf55","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9baeb1c807742dfa60b68f32","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbd34afbb3a236f1e52c05d8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67f24e326dc157af68bba59f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d430d708739c1838a86ee01","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19d5c01029e87cfc22eb0792","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e9513aec83ed5c426771c7a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"837eed14d5abe653526f9c1e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f68d5f7125d6078981d1cdc8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4440269bce8cda5310d406c","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2f0cc5a86febfa51defe5db","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1e3ca5abae432a2e5870be34","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa9718cf977935383075b2e2","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e87020b9d0c264608d5c3e5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02cceeaa14a76c764ac377f1","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ee92943d34643e7c8109127","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09b44ba8a082ec541fdf76c6","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6bc38ad1655069ba484c206","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5c453e45d5a65111bf8c8fc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7609122fbb5f21e0336fd79d","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"099afb744367e0027cb4beb0","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ed225cfbd8da4a68cb773eb","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6529363c938719d7a1e4c752","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8158b49aa1444c7311339716","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"excluded","reason":"Incomplete task coverage: 111 of 113 tasks. A common task set is required for ranking."},{"id":"00b724564a3c562424e7d7ee","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c9ff5a707bf93dda7c0ef5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"766dde2b58473794011e3786","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c56287d7e5765c02c88c155","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2acbc319f9ca38c18ec3a259","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1414f305685da0868a45a66a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ccf007b68cbfb59bf9c8252","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"442707c1f2c89460f6d3ca4a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d9fc3bf92bd9d13a3f094ea","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b22e582a3c8e14d92be4915","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5132af703da957e07672d06","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24a003a38836b7cca709a4c0","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2570efa51639dcd9b893a408","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc4f79530a6ea4de4924d3bf","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a177fa122a0704fa26e22ecf","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae356140a8fb0176655f86d3","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c74b70fe0573557faa90b030","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c641df41d523e8929af62e4","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"172013119105d4051f909884","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f8ef1151d05deff6991bece","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4d4ab463a8327175663102e","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11e328c7711c66ea215224ef","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62da1cce8a6cf73f3672b9e9","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c36f895ea5cbdcebdf9c59d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0bc6fe30fabbdc0ca3994ed","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2c1cac9115a42116304eb4f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3596daa06314edef2be5527a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c151f6e613c9f67b13f406ab","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"291f2f1bdb22c81ab94d05b1","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e9076fe72580ca484849f73","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcd761cff60d797b91471d68","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e48970372d521599be694114","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ee14965b98c9860ecdfda01","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f05f223070de2c4dc322b132","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8dd90d8b9eba1233eda9dcc","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"006b1964b4c677ae98cd2b1a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dcd39578d24b8c83c91a5fd","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e79f74f121b0c6c0e762121","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f113838bc0b1f8c607b1a4b","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2626ffcb9a36bdfd69bb332","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"190d3154d65bcd070a046533","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36dff2620079957f2cf44006","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a3a02e52af1195826001ee7","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ea79ab29bbd3b2b3a79eb04","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c6fa27919bb5bb2fad17c59d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4e0fe498e9b3dfbf28688c0","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"efca67f8cab27166f2aca5bc","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6111e4573ab8476970cca681","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14e148b786d25d0b58bdc6e0","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1085b20d5dbf474ef852eea7","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f5d2c4f3fe25d144e09034d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c5638fe71f88682a29658e9","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2aac50aef97fb04e4297e03","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47c3aa23cc920ea643f444d8","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"efef35ac11fb92942609d0d0","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e96ad605e9106c9bdf8db4f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6142b61150b247770757b261","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ca4fe51d6a460da93435b44d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8aebe6222eb321d01c1e6248","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"95767f397055c93498b7aab3","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"87c811d366c5fbaaaa3975bc","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6d975dae9df671005980ecfe","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"adb649862ee1cae5791cabe7","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edcfcac8042bda56dd69b89d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4650a9f4c7f76ae664f13c2","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1dda745c989251a13a81b6fc","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40cdc1072dabab9b4c857204","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36099057e38dc95fa8ab5f47","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbede154e31777d84a3eb6e1","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1acb4b14ade97952b30ef0ce","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"807a399d7233df30a7358e46","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b768b05eb73f6ddd5a4b833","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9632912356d7829b44d8bc4d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0193783b1bb63fe4754172d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9b5f13b89dbfd47519f2e2f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dd542a8bb903e6ff2c5502f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1d00a56700fde6178cfc616","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc03dd79445442141592d089","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d3ed199a4eea5302ce0af04","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3200a107ccc03d4b7807ba8","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5818ec32a44269e63adf0105","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed71d135daea16e33ab93a9f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bdc81d0dc6d9e8e2e5473d75","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1ddf5e6fac2438349cc72b8","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7f1b2b1e77d957a1e5dc41d","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e93aba2ffcc3b81a912dc2c","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee2fdd53366196c1c9cdaf3a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48b4a19317b73c4a3f407097","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e57e43848926eef736a897ba","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6a6f991a9a99441b39a26ca","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0003347b8421c764d77ca4a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0298f83d2256dcf2b5ed6e3f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d138eb10af8dd2cacd7a504a","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e11780747804a9ec05171e61","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a159d4fef16041d56762dd8","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de1e01647292e9102ed45aa0","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"674b1c581fa7dd12ee0b66cc","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db806a12c42b98a164ee977d","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1774a54d662320565d170e76","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34d2f64ecde456514b2e2710","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a36ccc9c0f665a4b53b1d6b","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1016ec1494cf8458139671e2","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82cb4bb8edab7333e450a2c5","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f403f5bd47ca2833fc80bf0","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b31de44a316fc16fda8177e","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df5144f0bc3dfefc0a136256","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f783eb29b70679064120eaa9","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c60e757ef68afcde43a56bc8","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9b0ce7d16a5006a78eca66c","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"752154fc7bb6ab5b9437f3c3","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7076314c6b18338bfa363af1","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c9293e23e64f29131b3d278","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40bbe6df11b8de4e7657ecca","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"266d8dc9f86ccb95c6645fa9","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3c0845808f574dbc704d157","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e0d99a12bb7de08ad26556c","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c712e425b0902b25a4bca75e","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3efd3c04564d707cb7af0c5c","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5d5aed22ee29eec8262d15fa","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e508c8c6b578671ad893039","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"843d8eff7e70d1387558ec55","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0a93edeaedf53b41d00dbd3","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6722be7d2b55c374d9bb637c","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9f243e03759b358a57a4007","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6535f19e64380503ae7e87fe","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e1797d1fb9ba82a6999f801","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bac4143f9a745d98bfeb22e4","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f78303c3188cf807ba58ec0","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f070c56f3e96293b3502873","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-32k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54de588ab99dc61e79aad8e5","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-16k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e513347234a010f067c79909","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-1k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e78c77d5cf9767ea4f53df60","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-8k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e332f1b2228e9266a71d05ad","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3ee41fb89c6ccb1e66adf8f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b93039d4563fe3b157d15d5","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d8faf0c2e0685f2c87902f3","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95567387bc84bd43e2e17443","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"eeca2c029f49887d2f8de42c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8fec0dac751edaf179a65615","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f405b80c050b037ebb56264","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a850dc6ae782aabcb69a92e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"754ae6038c192fcc20e15317","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dab21af4216ac279722b33bf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa8db74b95a531e6228d4cdb","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d6261c518f3a5cb2d3aa799","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68cd3fa6809265041ab4e058","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bac7982cd94b783ce9937b37","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"6ee50ff3940f843b316a11ca","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9faede113e168f7e102e28b7","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bd9dc8c11e74dcf4d21c0355","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"451dd11af5aa03b51c7df735","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e5f7bf21fd13c70b5963400","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7ef923a70da041c042f467c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08964d53879fda33454d92be","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"fbaf3e468a069edc24595e53","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"5802b72f96fd2bc36b68b3b6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b9a5ed9afd89f3d3dc7c7d9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"cb52c6337e6d1ca83f782771","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e75ab74cf5a997095d1f3380","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7f4aba36323901ba9da5ab4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53a70f8e8f39a9bf4b309039","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b302bedcd3669528b4703126","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2753a36a2d9898ee83a2c7e0","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eab8dfd0579ff09141f58f1","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c9790672cda25468a59d855a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2b79a8be3c4816ae5e4126d1","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3c8824c30ba25df9377473e9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8ff03bd6cf18ff4fdd035fca","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cef67cc03b37e5d955687879","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"089295a829a4b2eea0c45567","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"524488ae2a2507b68ea71d3d","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"af900336d45849b431b9cad3","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b286a9e0d17ba5da81669d3e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f4c2f07253b00381b8a7e93","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"687f063bf51789c89c7d6efd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"3f305729d1c2d29db2f9101c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e7ecd187c6d64aaaf7a121c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"382f610161294070630b7fc4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"cb333ca12130594126273d1d","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e9118d28b3767fb3d536c9bc","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87726611ca55ead407ddd84c","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fc5dd5ad41a965cc918cdf2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1a628a019bde02cfbdacf5e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46adf8595dc3ea458bbcbb0e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6347d0311c4338a42a89d14a","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"104c2fa41680303d6bba8b0c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6f2b88cedc6459b29218831","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8e9b0de20e17f4fd8b19fbd","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a721729fc0a05c76dba80f20","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7f24f53024297ef7abf92a3","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bb50542a24a257e4eb3f124","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c33097b0dfb2fdab394c3c95","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02ea645c2f24a2c80752751f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db04c5bca2ef3de0f3a096e1","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3360c18e5bed782425bb787c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fd4bde44ff9666411635d25","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8b899f7952e43c80d07ab79","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85c0183e354cdd4caf89d750","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99219b85ea67436dd032d3d6","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4bdad75574e83880be115a9","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e8ce6b0ae75bb9042940f8d","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cbbde4b95b5a21deb83b2a0b","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2530a99738d53ca6decd46f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0678b0119462d76644a10ce","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3787d1b957fcfa3c684c083","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b8fa8daa2c88b443a7449aa","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72851189e89b18b175a34279","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd5da788354923633e1ff1d8","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6065d3f4174954a37c01d1c7","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d987d8372c351824904eb80d","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4325cbb6bcba32969d52bf18","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f5707f08e154826e63e8800","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8cec453083c2b2c64dd64b8c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15587f3af3fa9e59ff755686","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b119aa5c97483db76e43f40","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0842fefee8fdb0f5ea919705","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0557b2c900b2d809263a81ff","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7fd469141573e139e6dc01b","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a335f96e4904dd7731faeb36","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26b7ce6d0eddb010907edcff","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fa3149554f3d1c058930336","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1987b1a28ab21f28696cf3f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2ed28284e20ee8b8775ef5a","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b359ab1fc0dbf5ab7fa628df","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"938293264816e12f768d2599","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f4ce5dcb90a73c1df4002f2","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d82c20bf270d1a9536b1eae7","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21139124a37a09effadf4583","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60c78fa2ce7f6be78df1e264","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d43d5179fd12d01362a07e0c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21b4d6e29173c4e8a4a46a74","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"737ea32644d6db0a08c42ad1","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c21f43cdc9b325847d265d03","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c121d252aead88218ae94083","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9421851310be4d5cc39103da","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"26874b9f4b82ced0f4d4b331","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d7cff7448ac9d293e5b872bd","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1df0b890fcab062c13afeeda","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d5a99932e01192bf9d1c479f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae1bcc5e1967bce93138e279","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6ffc71819c6232475ebfe2b","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92a6cf69529cf4d7779e63ca","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c000a3056d5754838032631","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7b652686b8bd48c14a72ba2","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63d2d77f1bf4eb85e55eebc1","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1bc9299f4da293519040ae3","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4bb4682135688e4351c6d658","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23b87b7836cba38b9e707f76","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa57c67e5f6863724b91bb55","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f862c5e3a18f6a6c8fe36819","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7aa7cb43d88f63979741acd9","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f92691ca7303d9bd88dddc12","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73e34cbb98b30940b928c16c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4418309697991f74b90a896","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b6129afe9abbb202c5c701d","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"926ad37100a0ae2005b7a705","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"813ecd8b037459b829944c25","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4c869fc652332f41bd59474","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52163093753564a0e2539873","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11a57984aea1a8da93db31c3","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fd633042f2f5198fccbe085","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a42f15ae42cd5b945a0d0f4f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"856339a53bf647f60852283a","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aaae9fdfb56cae71deebae41","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d2b209a9235ccebdbdd2320","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e21fc7e41b06c5f966ba5005","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"201b76826240a98b3cc2f619","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ccdbb5004b77a13dc61b015","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c284b9431d0d16bbad751202","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"765497434c3a092fe1716fc2","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10229395b4f5570e9e94c618","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b91e3c66e0cbd10f89c4adf","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79f1835a76a8ef96e8c7db02","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"641499b97a2b15845679955b","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ec037f6ae1a0299e9e2a7784","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fe83ac17762f2d5b91590ca","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"26670e73b2cc07d434922fd0","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ab70dacb88f83e57d5e2076","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45dbb1834092da47ce482a2c","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12d6380c2e451719a74ba2ee","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b428a724421ec67f5d001f52","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e07117252be6e1880685c4d4","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4b54c7c7c50aac1e09c9338","modelId":"command-a-plus-05-2026","configurationId":"command-a-plus-05-2026--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f2099408e3868dd3f5bbd0d","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e7b2966cb801f40d53a63d0d","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"78c2d72883d8472bf84bb942","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c51be1971aa7732d0e3c9dec","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8738d7c5dfd75c32c1227708","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"f43c9503098639be7baabd71","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"14c3bdfd1b0511c0d8bd8d7b","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"9fd73563f403665e135e24bc","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2deb81947d71e3f165d2316b","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bfe86af3326b7bb69930545c","modelId":"command-r-03-2024","configurationId":"command-r-03-2024--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"28154d8ea2e87ddacaa50495","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1f9132429ab5fb1330d2974","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d457e9fe5dc1d1849bde49ee","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89c583f754304a1af65e90d8","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89234d302d97c8daf59156c8","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2894a03cfe0dd1c35eb63b61","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51289684897e664af54a05d2","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3bf8f6694da5448f8d82c11","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10731a3c1d964999d4ff6598","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac159579de0c6415663fa834","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da46f877760d8faa5938e0c0","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b93f0ed6713171396a82dc72","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18a2418d73fee9d97b9e6213","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91a19a0300fec337c23eaa24","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58ce3731b6917805aad4c062","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08fd0fb9fdd7b4017f5af622","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2258149dfb5467587a60f57e","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30fce54c7ca06f7f9c3150ac","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"502b0514328b85336c43b79d","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"278e99ccd1bf0c3c5d492f6c","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a61d3d8a1884f195532baf1","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50f9af8abf72ce37fba0fb3a","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"752650e6b94ff2d88f9139d6","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfd5bf4e982521e955c382fc","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"dcaa7d394803f4ee83bee90f","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fbc7e5ecd7f934aed6ef04d","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29dfea68f2a7733cb8a8cecb","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"243c60a86656d1595c85745b","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dd78fb19901b64635db44f7","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2db469a257b0c3f2f9b40bfd","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6222d4f378654bfa05436ac","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17ee47efdbcf843333a4b243","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae831c640f2a28b64b82e0c4","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9505e9c34edbb45f0c1117f","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6fc19818675129310568bb8b","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01313163168fd0c915717c34","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8e893e3e38807fa7c5bc79c","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2f9d19dbc5ed104d40cdfb95","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b37220933b4b948d9b751ff","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63f152f6d7e4690aaad8b67a","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"717d45d07de6c052364ae732","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0411fa720378242cd32f3640","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"202acf3ea41812346b29502c","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28f69c15c898a22e11d5c5c4","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ea361c2d08a7937fde27b2c","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dead492c7767af300580f03","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36c671e4534c9ff66d2efdea","modelId":"deepseek-r1-distill-llama-8b","configurationId":"deepseek-r1-distill-llama-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a116bf871d78b619440a0d27","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3732ec9546845932aab5bfbe","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e90674679d47770bee4c60f","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"055397757bbab069a14a098c","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa0a9617f5d6b929618a9d65","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"967ea0ca7b70675dd27176b0","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6a1f34951caea6c3455f61b","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78dda2ed784ee488b907a8a8","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df13747a2c4fb0617b290384","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6729439534a49931b93c6d3","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a99dc39b2489e5491d366a7","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5db07063f3dc97fd82ec4610","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0f8badfdf79f42dbd45cc88","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b88a2bb503c88bf49553b4e1","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"664755cb2071b85ced978db3","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c5936db8bc598b54ecd95b9","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36958495a1c3cc263aa8ca57","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48284251b9eed81c130233ab","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad1db369c6baf73ac00539d7","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88242b8c0ec5a510a77d7f1d","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a99251c3bb7ceba3f13ebc1d","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"833ffe1e8e5b5830b4a596e2","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e67615c87f9dbb2127e0805","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9efc3ef712c44c990e27aaa1","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51db25dec7dd9b6ee1af0a92","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27b5897f1b8a957838bd8cd2","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55fd90923f763bdbaf99506b","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bb7a5261517f9b7393edbbf","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"509e652963248d4d5fb3d747","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"257d1e613d6552d3fb81fcd4","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca37adba46b2003742a66663","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c849784c994c92d82594642","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"406b55d44096c3fc11bd6e0e","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3e8ddd7c4d1151df0f2e9b5","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95ce60be501a5563083110d5","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"078e78833b376471c91df11e","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa22308da67df2bbc79a5257","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"375a2df992ecb3932c79a0a9","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91a9cfa474cd837eb548b3df","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0258d20c0150addb336ab7da","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e55950f34a54a20d60015ea","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"abafce31201ae669660cbac9","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd243264a418b155eec7573d","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7211928466c4d961deff26b","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad70fb15b77d81ac74c0ce38","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9bdadba43260d89af264c859","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"560f2b6ebb5e7968026d533c","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7560286cbd56eaed8556521b","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f6e7bb623a6f650fd1e7a7f","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1cdb72f437d4c38c7e68f79","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c6d9bb636099f72e73c8f57f","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54cd965a443d2ae081646656","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fa83144d986891b98ca55e1","modelId":"deepseek-v3.2","configurationId":"deepseek-v3.2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5de71161ca30dde6ea78d6e2","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edc9ec337f8ec9c00318a38f","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da1da6326a1c6365f377d1b3","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19939f3f32bedc31c6f2e423","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40fac96214150f7c9055b2f8","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"934f82bf796a5f145286aefa","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d6fbc4c2f6e63c01d55902c","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7a6befd16d9965c0f855044","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"841d60685fb658fe47a7ef71","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6d49d36dd36d19e284b4d40","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9e9c78a7ffb2a500222ed9aa","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"866f5d18b5c5f028af163a6c","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd04ee261df4be08b3396245","modelId":"deepseek-v3.2-speciale","configurationId":"deepseek-v3.2-speciale--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a45c68223e1ae374ae76da31","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a7f324185d4152bcefff6a8","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"198c518ceb539e173702fd0e","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f80aa4cb8ac1c1539ed4751","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5034155f9f373466e08a2796","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7aef406561c55abab75d5692","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"407f6ccc80858a01c74fe91a","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f1a652d223fdc1a82c7a442","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e9a79f5ae68e547841899c9","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35b25adff9293e9983993576","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"40312e88cf305dbd9f804e18","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ac03d02aab2b66b5ec98d6a","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06b57055d7bf20ee8731a0c4","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c415823cdba1670ec1db8602","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b00c6e5708fb4aa9f02984e9","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a7bed5705711ac27a52863","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c846403c911a1743e84cc3c3","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcce4d406862908e10d2d67e","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a96e7a8059bfa86f6a2589c","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b3518db91f03758794ffbbc","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30359f55b56cbb7fa8922b58","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04d5f243dcc96f6864df12d3","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7498f18a3d7a0d6e3a8c05dd","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d8304ff46ff8c93cd730c9e","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af09aabfadc9e1d549b0ee1b","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c765bd4f69aafe0eeb5740cf","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2d91e73f95d13125116701e","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45b5b005e82df984c4754e26","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"211a4875f6e5efce7a1f4c6b","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4fd006a2f22c61ad3ad7809","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddad624429ab904ea43be527","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d11f93766b03fd342fcc0ed","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c50f6d99203b49ecc762174","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1267a54ee820ffa75fa16b94","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"647f5ed4f8ac819f8a92f455","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00586cea2fa92d2e78ddc42a","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f021e7500c5cfd741f9d8fe","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0aabb05540f7cd3d2c0492e8","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35d6e01923cb4fad3f436062","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"022b14ca345d31ca271e5300","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a981a043ab444538f1dce56b","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"181336fde2158d3a0c42459a","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a96281f88d8d9d3e8d7ff8d","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b31df469403ec55b09e81e8","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64f11a73331e262497eae162","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9cb1689f0757af2acb41929","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1274257605774c664bc3b62","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"817e020bab9c448974914094","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"439d6981fbfd192fa31d48f6","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"020337d791c025678d7f669e","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c35fc22fbf62c8255fd2ce70","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"28f74cffb85616a21ef0466f","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6c0936c5bd19f197b911186a","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c10422e572b9a348a7c9166","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80863363a872f8c35502f3f6","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e12aeb36a0c85da4ce01c982","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"059689698f8cda55ccba60fa","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"727778276f17f9a2957761b6","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60cff368f41fa32aaf7f4572","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5ca0b9abfade94ff13f824a","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5dd25c29a727154d7b02d62","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2876c384840221381c3f43e9","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2cc630037385cb4acf65861b","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"389924a1e46a90f46dcec917","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fd65426eea5292e3162825d","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"522740b9265e00e9395dad06","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a287097357e9878ccda9bde0","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"556c0c748a7ec53b1b4d0120","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7000ea0f1210578b91c29b3","modelId":"deepseek-v4-flash-0424","configurationId":"deepseek-v4-flash-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4708dc64616b39f8d34ca8f1","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14e10a95b270ef9d1ae373e7","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b8d6f24397d8867cf1faec4","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dd052bf6a4ebf107f6de0da","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09421a76c727dce721916f4d","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43690b5f91d764a37de970d1","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcda011b6a3f738075dafcfd","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b35b842ffe605a75e112290","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"760ef06b17543599268b84e3","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ba74afd46cc724b0e2b9629","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1556f05dd2908433d9fc662b","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a30393a098bcb7270303b12f","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49acabfd6982ca02015ff725","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89082513bd20d1cb04639c1d","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf40d9275e4b9284715bca88","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfe21e52f99ab0089cdaebe9","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c64dd03820fdf345d94145b0","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f79426f1f5a6b4e49959783","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25337d15a8b7bed1bf41c830","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d725d4dd6ab63e2174499861","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac3167852c54be45702e8943","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is not identified by this source; April and August revisions must not be combined."},{"id":"888bef3b9b0600140e38bce5","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35054ff738a363369f96e691","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2dcde6bce83f18724026ee1c","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"832cb2beabefa15c40d173d0","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f853b52424d8b5786669fd6","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"049ba5aed9de5c9216fbc178","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14e10fac21af13eafc4b2bc3","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9c2f626421c5ba55ef64978","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7d837c0d9ee11b205c5c946","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36654ea29065ea332b7ef40e","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1d6fa2bfe35f63d8163d16d","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d006aa70eb1d30bfd9f518b8","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c29eb2b92d9d49bd6170cbf","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"656be5ab83573c50c309760f","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c648452dd378bb0942cbc01b","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d7cbe2d37cb64936c4535d1","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b744d3a7ed205bab6424371","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"327957a4bb715a26984ff1d6","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7d33629352f4a94fd7b2299","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c92b67b826689436a74b727d","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5ab64b1ce76dbc203820b05","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73cd0af759c68add3867fd72","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a3ad5acded4b7c851f16171","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f08f499efe39fd2ca951eb4f","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6af1a2a35becb877bc4e094c","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f006e7160beeab0a79c6f970","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2d986dd108115769c871ef2","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"daf424f4f812afb14ebb9d27","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cf19915c5fd19c9700e73691","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"70c66138b4b47ba2b8c19d8c","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"095fea7e3506c915a48e7c30","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7984ee407acd3bd66f6db6f9","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99ba0a234f4bfecd88b3a019","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"947e58b0b93edb29c2be18b7","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d88ec7d9a63d161519180539","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ceaf48b790d6b1c784fdd288","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f620bd2cc9ecffb9eea9a636","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecc83bee2883b16c02eb805a","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7c6b737ef04f71916d523a1","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a231d0d6923c87e943c7c7cc","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b349b71fdb3781d4f060c93","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f90177da988f2f6b5e5bb5e","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86644eda7144d6e39917eabf","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"044ab93a3e45cd3aff772342","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcc51f4502c96a31cc744a2a","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c027bac776af43b4cb938c11","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56b570282eeb2d7f9bc5720b","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f20b6e6193c225e4bde7c4d7","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4818263b0b0cdc6012971d70","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18a919dc18d96a14e330490f","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50ced579c2ddd69ac4ff06ca","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b73f3f0e2fb4a983219b412","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f3c6cbea54937ac773fa184","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f67d22c0ec4ea389ca56cbff","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06996081218bc20d64759001","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0028f41bbd3897a5e62a1019","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b77d44d579e2a5fb4c111b42","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f87d2326544d8fc4fc49d91d","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"28c7d9bfa5d2fbf77e67a274","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4656ead8373195f1a2848cdd","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c16d1eb56b6a0b6ad2c7df6","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54bcb36c56b3510fb13024ba","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"520f49635049319b43c19aaa","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8338dab33792ea1da2e48ada","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d85460656a5d267173ae81ba","modelId":"devstral-2512","configurationId":"devstral-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4149e6a6efb13371a5919a0a","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16155cc9771f19d724e14d31","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb26a8a40cd04f0794905ce4","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1dd0d4ad446639c8b032f826","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3599b35b722d8252b79f6f35","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d29b6385e38b2fa601e91de5","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91892dd7bf1a5f08090f9d9e","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b3377f33c68c96e20808b3d","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0a6b438d49c67c6b0125a1c9","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e6d3333f88940e6403844c7","modelId":"diffusiongemma-26b-a4b","configurationId":"diffusiongemma-26b-a4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"454c740f40aa59103fd640fb","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dda4e6313c33f052ce51f21","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93e5d74fa9cd4b8faa10f31c","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0b2a7f440e8d5397f0978a3","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05fc8421995c99a0e7d522af","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5af52daf1449986eaa89dff","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b83eea8de1c05302b1b64c2e","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7d99c67e34240e8766aad72","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19ea5a48da48057701cfe1cc","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96e8b68fb86c6c0f5461090a","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dbac5be77e69634487925b3","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"111fd2d05544b06f84c1f97c","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f16565827cdaac0168c025b","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eab63b4ac56561a7e1509869","modelId":"doubao-seed-code","configurationId":"doubao-seed-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea6dc61a26cd710caaeaa276","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89cb005073731bd86024d136","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ff20db183a764049256077","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03ab887691c2d04305534b99","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4419233d06025238adf7fc2","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"048a4485e7a9a4c8d5650791","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad7581b9cbb13c55b285c09c","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad7ebbddb49c0e728ba114d7","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d15eb698c8417578a083d5a2","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"531621bce0f156b7a851eb0b","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"396c5b6a5799009c00a077a9","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20f35a16a687d6b454dbaa39","modelId":"ernie-4.5-300b-a47b-pt","configurationId":"ernie-4.5-300b-a47b-pt--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f99755b76c6471b984bef051","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c71e752f02177e2307ec0208","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fc7ba284be33c52df15619c","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94de804551d84e436bcfab2c","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7dfc21f139df43e3647f983","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"381abd772bfd4fcc40a9ff1d","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fa215c1732d7ec7afca35f1","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24b49036b5b6c2c71015d226","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47e6a1dbad4f44e3baab9363","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cec86b4c9567fb892efd3dde","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"637a534eabbcc15462e13a67","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a17190accc3a0092e345b5d3","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2919bcee1f19cc027c0b8e4","modelId":"ernie-5.0-thinking-preview","configurationId":"ernie-5.0-thinking-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bab5b3f721c054e194163da2","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b597d1e3c86a13c59c590891","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0660023c24169d0375b9331","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c83bd4489ef7f16d4df9e0cf","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"74f33d01f1f6fbcdae474f72","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a41dda65db95525981059fa9","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3b843795c22987d82505da7","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ebdbcfcce04b951368b4f81","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8caf0e4036cb60fb443a2182","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1b99c8edf1d5b0b83a10907","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10e9713791139c6bfc66aea4","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffc52f3cf3a2ef4dd82fc717","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dc04b302fcd46bc8980c038","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"942dab2d051ced6ab8272528","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"578f3fc0f7765bd8fde6c59d","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a589219818ac81f6b4db247b","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de9a29070b73434bde934a9d","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"91f5aaaa147fa965a95ee6e2","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cd1008d27b1fbfac60e39554","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37a86f44ce022d6dafdf777f","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81337225c1cfbaecc298a109","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e07bdb18a2b42aa76c775099","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19f33b7a6965d3055111ffb1","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f639c6955dcc41a97a992d9a","modelId":"exaone-4.0-1.2b","configurationId":"exaone-4.0-1.2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c900cfefe08cce4e82a15a9b","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e146162ac9b155d4b57a4230","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c48949f7d4d375f4aaf944fa","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dccf3f99ac4f647f345a44e","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbb70ff8ccf50d3761bd741a","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"465814ec06b1b537bd6b8db7","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"182b7997becaf9b5dfe635a2","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3806f14df2e84d68e93bb3b","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"688816e2f1a961f4d3aff674","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96fc68b9a4cdba13bc5714a4","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2bb057ef3c15aa7c1a0099c","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44e88de85e270c332ba612c8","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45918216b4f57506bc18f43f","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab9a17932f0001c18c76fbf4","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df985a406bd973b58bb12714","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"caaf789de95efc45eec9e06f","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1cc2edb1a9f3b941f175cda1","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28161676227107f4bf1e949f","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d18d1d42d9c3d891e66ccc05","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"bd5ae655caef8856694260ac","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1eaec2770c32a1d977fe2e9f","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0e22773a86c483105fb9aaf","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c56e3b4c1bd36102a0d428b","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27cf0b2a4eed2df72f1b5425","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d58e0132dbc6ea2836492ddf","modelId":"exaone-4.0-32b","configurationId":"exaone-4.0-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7d6e5dfb2517db3a3abffd9","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"300ba2762404242763d4c0e3","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30e3abcc63438702d05b2993","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a34bb9a5d6b6b0a922ce76e","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41ced3e964a27a11df4b1c3e","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85ca8391a463610733f224f0","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58a06a071e5a98afe4e66531","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87ade12107a80c21624bd73f","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e7c7a13c51cb53b14149a39e","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9200d5c5a1c2397d0c658a6","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3258d1e2e465783b346ca7f","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22b05a6d0064688a6d4b8d73","modelId":"exaone-4.5-33b","configurationId":"exaone-4.5-33b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"778a476fac3a54bc26ad1bdc","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25e8b81f8b05ec46c5e80257","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c843963587d72d6e7fa6ab2b","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1e35c9dfd5a9177d6520490","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fbe3f48f7d31ed271a50ddf","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03903b802c05359369266f36","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae60d7a4d3b3a85a296b38ab","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a919ff134ab8dd622151ef8","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0508741ce4e4c770a963f3a4","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29c12307a2fa27b9adfab4e4","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad52dd4994d43cfb7388537b","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"615f11f6104fbdbc6397c19a","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2274f10c01fd49af34cc8c7","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a32eda887ff803501ac260c2","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2a790a25cbcf597773c9220","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ffd498b7959470e367bd26","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e548cc9df3852affb6827c7","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9a8955bfe6f14e6cc47c6be","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5513fb39e65010cbd84258eb","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa36fae3bef0b68268249bfe","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4871389cdfa8311f33acc44c","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8810b2fe580ca34e86a3b029","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6ea19c704d0cd6d45804ad9","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"94436d1283ceade19a098e93","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"89031d6f4b0b9da5cd80cf55","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be837d02ebf79658b1d356cf","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b82146057c975a009a40f506","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6896924c93716199a8e8b23","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b1b7e45360ba1982d470496","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6d86a700f4535aa3b842c46","modelId":"gemini-2.5-flash","configurationId":"gemini-2.5-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b6d985260431c716d5f32f1","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a433d84489e1746d7f57ce6b","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c4270b425ce13c10d94c734","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d69a72ef36f478ea09b68875","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4da0bef5d2711a9743bf008","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"434ad978699d9f67751986dc","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32549bdfff973940b8fe54d1","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25128a1d8bb8e5c053dcad35","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"838fbf397ffda157ad949a61","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60f98d8bd60241b8c86ec5d7","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e11e8fedfcf94c7848f35e4","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d5d302d8a59f5716d532cb4","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"208bce24d8fb34ba60bd10e9","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f124c6e37fc898fcec9d2aa","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5463a06d82c58c7e8fba350","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc2be91ff8211d91bea25150","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e51c2efec3e1e4facb453c9","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8b3bc91b10e83be18e8677b","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a0ea081f38de34cf0138ec6","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b619e01f7daa0e5ea4cdeda1","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4989b8aaa192e67ee9b036ce","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd0e18878398a2cba1e2c630","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"54fcfd9dba64059091858233","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"67df11bafe9809cfd9e3f3eb","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86b22a6d3c908a4896b22e32","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"333ef0ed6319c3f365aae494","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"402b1b95380a385fcfc42d37","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c90f54c21e1329dfe593d000","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb222f50e00f52ee760583e4","modelId":"gemini-2.5-flash-lite","configurationId":"gemini-2.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2baacd01517ef45b2eceb1d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"487059beacefde1e01685e8d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5604a1b3b4ab8c68dc8d01bc","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe94c818a9ad0ca7d39e39ef","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aec0db3dacd7fcf771012a9","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a2fff8b12d3d37901295fdf","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88d422808c7de7f23d709556","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"defe800b4fa5856397240d2e","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0780118e8e66b234eca4b2a4","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb4e80a7918d6b9057e3deed","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f077b068853bedaf080c341f","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5a906c034fd39fe365ed813","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69605a228871fa6d6a1fe38d","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"effe61acb1f2ecd3194c56be","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f2d5e3be696b0d89edeb2fc","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fed8f4ab77fcd5d31da67c95","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cf0ed4c7679f5831c0151b93","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b346e2f4d8c39e5b6a8796ce","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5336414aba2be78f3187de97","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80b93729bec1b12b13fec2bd","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe7921ca6643b00dc3e8c896","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f6648f08f82d8663f02b246","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9861b3363626336b8e1278dd","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53fc9ec1dee0accada2433b0","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-8k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cc85ba2b198bd02c85a961a","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-16k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85789420efbd10e4bf8e8a0f","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-1k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1746e4a5f84cad00df32d6b","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-thinking-32k","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"076c87b82049cfa2ea7b9df0","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"162b72dff2b62a478a4e3d38","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3a845d5ca338864a0c68e84","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e4484b725f885d1ff5e913f","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"681dcd67742f3fabcb4e8443","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b771ca3369e45caa49d4b3fe","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"862b3fc84116cb2abfb29a11","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"766bfc6c0bb47794ea896d7c","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0939c33b02de61e8d2569c0","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d45eab2a552c001f2dbdb704","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5177df7f65f8989816e07078","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a0c8bdb65808c38cc8c6ba8","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f524fa4818eae0de4de4b842","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d1a6871f955048317879ba7","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe637f0f65778514caf29868","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3877c7c555480e56e2553353","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afb2c3230511cde285428634","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65ec7e6d31d6f6ce02771c4b","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91700195796ca55967f40f20","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7161c5ae63b41bca96c70974","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a699cac3b6da2ec95d940e1a","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1db4c190ae70acb2a1c1a232","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57c50354c54c32290ddfc4c1","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e31d78ed7068e350eae0e017","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"31aec0c830003796ddb584fb","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9fae7f3a431a07e9ef03a649","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ca294472ce7424a59037593","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"090d329b550ff7c39b218328","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb0e8ee7331851f023b16462","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"216792d88d988a2e05a41153","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66bd4898aef466d04784881c","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f07bd2d137eff751c94e16e4","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da304a0f8d4e4dc282b7a95b","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f72a698e068a7bc179feb19","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3906ea3a7c1254fb6ccba8d","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f433631bd967cd374a5a92a9","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ed78211ce574b898ce5c37e","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb38f5a1da43f9f671c2940b","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95738bc56bfab2218391b063","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e51ce9e31d112599849140e1","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"542af94496db9fff0c50c33b","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f43c952940a4b6d26d536be","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8416976c2cf8e61964b2a869","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"866f484125051166bc2e4453","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3435307b024c7565dbd94fc7","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f39228d0894775a799d9e673","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02998383bd3440afe47af683","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a500a1b31b9c03cf2da51aa8","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96ee84a5b928f3599cf5d764","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4aae5d6df970c338630860a9","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"334d043fe09ccc4d1fdbf484","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"897f612ed5343edc51d5b099","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4bc71b7684588e825fa67080","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"097b9973b90993f5f5e7d1df","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf184358925df7a4fbedf4bc","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2684a58ff4342575f23cbc46","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29f5bb04ad1bd05a7465f796","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37c6a530f1ded7b9888ea2c3","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a09a2ae31ee117af6ce3dddb","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c7f774514f7fa2297208e0f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b06e9c41fbb683c7a2f4f192","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37687afd20028c6089e77920","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f4e475d1f8d57db24bcb7a6","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db8f74e2e14e95ffdcaeb92d","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa3f112c9b6e79acc46b504f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93374c1590601b233140cd4a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8063177a2a63d1be8648e2f8","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"369dcfed5847bd7a41289d20","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39bf8cf4de7d4ae5d9295e26","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3fd1ba1d2b182c00683d93b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f119405d93465a62350dc255","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3631e2d668ca3ff2ebfe823","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aa04e6ff77c61f9b93c9290","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c7f8cd7187c61c11375f19b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"208c2682d2e878ad0bfc59b4","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45e4f876ba3f9fcf04c8c5fa","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a904d86ad7c12c3aac7713b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"24d00d3350012cb696297151","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72fd11da3d45e05f88f9fba5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d824de33344d5f7c900a32c","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d20dfb2c84bb4190f7edf29","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f78b4be38ed10e8ddcd80664","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"154ebcd0575e2428b67b2398","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd2e6ea2003857920a1bdfcf","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db901e8199046d5c8d479ba0","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f6dd87d3bec8be094065e59","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/swe_bench_pro_public","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09a429372313877fb69d9077","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"a01dc047adae16bf8c7acb63","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48c0d21f430546e8b664e36e","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"832b5d2faac682af2778bb8f","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0700ff7cd391b4c306b5da1","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fa218e0cf898a409b6950ed","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcf5c26a7ddbb18487aaa05c","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"921be86f7b8792e802437eff","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e65297694f3500bd1feb181","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"917db71bf57d80367ae8bfd5","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b0114a88e6b6714abe361aa","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b35874c17908b217e3f71aa","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd1feb290814181d6c5dd6c7","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e90839926b182c19b92db90f","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"464626e6d0154934d2a6e655","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d2eedb5e7f7997fccd036ec","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ef4ba55001e85543ca153ea","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb5a3a6576ceb4adb3c8df02","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d007c9e0b18cd0ddd4703b50","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b58ff93118c3e42b1754d425","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1c845fdb2e5b52dfe9e7a72","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a0dc10839ac43723ac2505","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb0b2ca6de9c6338eead631b","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1db5c743173591e43f7f5c1a","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc28dff3ff295e97d2349723","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"590ddab9886c546ab0d14b7c","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8428a80e7390cee8670bbddd","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dad0aa507881840bac4cab00","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a771020cca119625e60aaadd","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35c03f5c2529a7110f27178b","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfd513399a8483ae072d0f2b","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8591301a5ba5c21a75e096ac","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"43b3aefe7350df929f9338ae","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2bcf32e69932a11f901a5098","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"98ac17a806eee8aa49717aff","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a8897c73ef4384656620585","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2412d1136cc38ada8c6b745a","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2d64f49b13cffb585e68d94","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5995551cd29bfab0e3cc8de4","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed3e1c0e64e9cfa96b91e340","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d3d9672d6f1a58a61fceace","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da70a188d3e459342f2a34f6","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df563aa32b42e8f9d09508eb","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c8c9a8ad3983efe4fdd3bcb","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c81bad7ecf4502ae991784d","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"588473cbcd9f97a6d2d1c049","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6217a48cc35c3658cab6318f","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb38b0f3dad2c23ea05267b5","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e2bb982e97ed49d227de10d","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d995aaf1dca8340a4a693d8a","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"581ccc3575dba857c4980929","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa3e7986ac74b1d41c049659","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14a902d4f36d2bebe6ff22a0","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e8ef8685e32a69af902f783","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93f57b1a7efa63a3d40f7270","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae13f406495e677556b5a0c3","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d41ac4cda47841b9af63236","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf28d2d6dffc1a351c70a760","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1cfe34cd9aecb7162043dcc","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc74bcb7728d73322b4c984c","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fcc617a3338c6253fdf4353c","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2996b27e98c9a488eb6dd898","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"199cbf5b9764d44dc0a19484","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26f351bc48bbc25a81380a4b","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae5702c7b4374ba438f5ea3d","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3e410a3346994f7eea97dc6","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e253ea51b6a540f66de5395f","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b0081bbd7294e66bbccf771","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"673c903462f2e3ace1f8a3a5","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38942fa126421e15bf1592ee","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f591fd70b9b02e903ae88a25","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d2bef889970f2b2e07886ac","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02af98883e86e08c7d0d14b2","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b50c064c019434c76349a34e","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72c53815d6f2e5985dc88b2e","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0973640464da38626274814","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb531999926abd475dd85d12","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30e71b2d4dac7faf9d150a7e","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"956c95bb8e0b490a259250c3","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e22f9c6c9fb4eb1d727f54c","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bef04938effbeeff2ad67939","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4c925125109603e5ab10dd8","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01c9c562ca1e20be38366b5e","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0ec0fd270fa75ee2504d1492","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e4d77610ce1730581d1461a","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ffc630ea762d5a97e563372","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab54c861e14442ee403959a2","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"567b11a1bef86be59583e08b","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a40850daad4b8e157f489b7d","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05c31f600e16e2079feb1579","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3965013d4d14d4352a1e30c3","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d701fa1ba2e4bdda269e42e3","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c81497e333fcbd26ddd6cc87","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ffc6e719db431730b9a76d2","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15fcc7b3d81479e0cc30ec90","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9f672a5f7f4a4ed529fc3c0","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d3e98fc6c09a465346ff045","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b18453959beabe4bebe0683","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bc1e313c94fe673b2f5922f","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf96594b0ed1f96377909640","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfbce63c7307804098e6a934","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02a82960bc44c535be451a94","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"763a8c264e79f3dfd28feea7","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"623b9bf3960dd897e5d3a62b","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"335f683b38de6b878c93a2de","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8daadf8e459cc18a9edb5539","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e20b3c33a214f6c253b39d83","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"033e1bceeaf591f76562b322","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cb5439ae05f88b975030a3d","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fb858efa3a20cfc576dee30","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dc2d6f01a20b073316891ed","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0e918b40a70a3fc785372aa","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1eadf639a7b64077516b415a","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a7cad906a57f42cc02339f5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38e737a0e552ebb4ef35e0a0","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3eb581d14d32fb68f0df6ff","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8854a52a87268c9344295da4","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7efd00c773b07079aae442c1","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d286dd08c71ca1a94b6b4312","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2165aa4444d69b835f683bdf","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cca0a6b63d00776b6e87dae5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"227c852a7bff02f6f5ca567b","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e813c8a37564aff5565dbde","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0dfe712d13607e0f7d46c60","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99981533fdcbe148dc5a8339","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6468affea290ffe50d9864d4","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9c3b38b79987468d416a723","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7975b0656398a8aaca18ed7","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3ef65f4bf0e05d2f9d76fcc","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78d7af9f4fc293caa27736b8","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da8576588c7b0a1eab39f8c5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c81592af7ed61ce7169fc91b","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64fef02ab879ce4a145da39c","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"548e1414ba9f0cf973c69518","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e7c651364e9ee25998857ec","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c66a9ac890388e11ea72db7a","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"198d114dc938db6f199de747","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b75fe3ec33c013c7d01ac1f8","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a8c13fbff0cf24590cc04f5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ee91dfd4e3a98ca959ff95c","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d0702eeff3949dd042a2fa3","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c34c178b65592e795b4ce504","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d14c6c4c0ac850e9893270a","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa03d1f1eab99dcae29627e6","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb5a47af5bbb05252e36909c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8913d162877cdf204b25cf8","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3d11b8510947a6f385c2981","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0375b76709103c37e2772339","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e4cf4aefdb6627276b41de9","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8116ad936926f7e5d42cfc6","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fce47e70c8b6a91358f037ac","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd1501b4ee4241b7a2f2fc55","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e224dfcbf47d68bf41d3b8b","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a003ed6d7d4810443711338","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ece8a1e32a834fb3846d3e2b","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ee89d80876b2c8b5dbc820c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"74ee4b8771de4179c255f519","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"443b3e01dacbb5afc498695b","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"015e3e9bffa0ff59feb7dba4","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"245d13fe1bdcddee2cf1de6a","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e0e5dfe41adf43f56eca928","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff15412b30403c3252d273d1","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36d7ccd405b78c98c664c26d","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab851146f8ddd99d32600bc8","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c64bb74f8fe5f3043682b5a","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8c59f541f7805b02740779b","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b15f5d90d3ee83a48e00ec0e","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"311f120c93ce87f66d442b9c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b362fc4da74b513f0c9e56aa","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"349a9170a6967dde2f69d616","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"29918922aae0f8078778c893","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ee812a20006b312bf3a9ead1","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a187fa977e12f34c4e80fd19","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb26375ac1e276d6bde537c4","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08294d5a9e316499d4fa619e","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"349131d8d0617e56a85bc759","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a76f4a4ebb003dfa2f1e2a8","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"631bc4c0ebce57b5312a5f98","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f6dd3569c76f245c1790da2","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52f48c58bd80ba863f55dc0e","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12cd11cee76cf6a4c36e0087","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee28fa94d3de082b63c35438","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc03c5fa8f7705011b0cc961","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c3c62c25ba7e7bb7bb448f6","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"388ac9f7e08ee8daaaa73970","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be8f73138f8e1ba0c8ebc015","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"405dcd6b0cb92b2c4c19515e","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02f746944e782131d58a2c53","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bae0ffc1da12b473f74a2b1f","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1ac9024e3d4ec61f9a27b73","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f5c45f943e79042aec9e467","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e92bfd8b7eb0fc97830fe231","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6589219b0e0884945d77b28","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9ac6749ea0ddde7b22c0665","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"475a94e16f23c1a63ea69240","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"adccbe9b822ee7f815ae4a80","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"641540b21e3f392cf8f0bd9a","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71da35fd94ce73f427f2e7ce","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22e8ad1e201236cae3a05725","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"080268458062c51d69e21edf","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0ba5642ee15db5fba8b4514","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e09f5f3a1d31437d4e2c6d10","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ac2366a97ebc55c10126e78","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"65e36893b56d652cbfd11b4a","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dfa25465b0259154b3eed24","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb329105825c1bb19bf3af65","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a374e979dbabf157744673dc","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b0bbcfc9a419ea70d04d3c8","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e99a62a6a4b3677568cbb008","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe7aac0ecbb0c2849f090886","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"870a7107c43ca88307ffdbaf","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea441b9a6112bdfae0f748f8","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93c701d15fcbd95282d8974f","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea7330bf72144219f9f1610c","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a85c5930a31d561cbd2a37be","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d6447d51ae1eeef0c7328cd","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8f8c4241e62ccc94f5c438c","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"967c42becbfc1b7f69a023c4","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b405af3f368ddd8defb911f5","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19ee2523e0c844fa8d5056a4","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d572ac181de7f4a7bd81c4e9","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"986669b662cfc130d20c3054","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7781a6c80a8cf308f349051","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd8260748e66a80c27ada5ea","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52d80905949128ccdd8df2d8","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76fadff0e219977139924094","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fbe186ff0d120f39021406b","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3309f5884078782f5109c1aa","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"296e9bf178830a18dc28aea5","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b36408c26ff599f500a313f0","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d43728608ad6d1780bac10c","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae1485e7ba3805532af5d722","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20bea5cafe0c9e45a478f6d6","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"da6a60d5479d339a034ebb01","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d60afe4189ee37f28c901da","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5482e2f6a8f5c425ecbe1b94","modelId":"gemma-3-270m-it","configurationId":"gemma-3-270m-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6171d7d4fbe5f0e0c06bf689","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"879b05bb7efdb989b22b0dc3","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06a85450b2a17ff417c7e6eb","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a72e48f0c589d27795a37bd","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ba477dce1a0ef87c127a612","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ff6f2c43a694eba82d86602","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5421892f4adacf93e8314be4","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ff7f32b33421c1c9c6ce965","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b72a49afa1eabcb932b719b4","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9a7a6546e6e6d3d50d90e69","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c238d9191ee2d48b6a84b9f0","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77df7e4831b72de2ed9a1961","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c0d40f3fd2faa8072484fd1","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d78d7410ecf03f58df197db","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09f9d18827eea3ab094fd5d4","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2e45792d6883b2e89cc3c62c","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe3bf9bdec38cedda2c4603a","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea5e72c4e76b0f441b7b788e","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0382a1aa06c99f35d0e5edc0","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c6288b8deb73d4839d789d6","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c690cd70e1220383d0f7914","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbca9a0d6ee1668274b86945","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d22ebd4720d57b1d0764161d","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"613fa8b94c50285eabaf9c8f","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a442736b72445b13048e7d53","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf36cb19af8c5e42ca17f4dd","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0cb0a7036c6d87b2926d3b6e","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d8ce4772f34fadf12075913","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b13cb76860c726d995622e9","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62201b3cf05086b0b77a78bb","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"555c7d3fe8cc0863494ec509","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"616fdd55adeeae6be1242f52","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99f7e488d25cf68d9af18b26","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"84dea6e1e3ef3afc74262d95","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"024ea9c47f612bdb82a2af67","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b46e070e0d48161a9317ca32","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94f7565276574925a5e8b94f","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c2754460e15897101c6669f","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a5f475968c70faa3e41558a","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"254339b1bd7ba893610b28a5","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cc3c6f529c5fcaac01b08b9","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d24e94beebb7749ea1d8ffea","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e9213eb8cb6f7bda1d0f1e5","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e6e05f44c22c523f43e0263","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc57f0fecccf2986223f97b0","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"265009dd01320779e45d8889","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c6b8a1e0fb87413ec47be0e","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2a432a9133e962dcc3af709","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b27d10aabf75f3a064bc461e","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"085cdd0603d97d7410437c05","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6beb07747331dd05fccc4d18","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0214606125afc28f6556fde","modelId":"gemma-3n-e2b-it","configurationId":"gemma-3n-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea42f23527add8b9c39d253d","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99d58e99ccd89cd35c2b912b","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"696ce85764f9c9d4b1ba6e1c","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0d8d76e50c09ce3e119f8ba","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc586044e84b48830b7341ca","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01760f7dbd3659373c5cb7d0","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a88eeceeac43fa8c6eca502","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8cd759735b2f8417924de7a2","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90efdea1edf0d70b9c91f2e0","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f604330d5bdfb9b2f5bfd3f5","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9082176c134078aa550097ff","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2ae2a55f56fb56a01959e687","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a340915e75cfe29b8a881e4","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0fdfcd89c7b44fa4f91571d","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b88afa6c66f560b3e323a93e","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42b31d167ae12b063c4787ce","modelId":"gemma-3n-e4b-it","configurationId":"gemma-3n-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fa190ad552336df40fc5759","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f25db26af07cec60d504c7c","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"716efdabc122b732d667420c","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bea6c787579f9a1237d89ed4","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"903a6d2eb139cb2a79eb5200","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf1dc487a514004349865eb5","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a333a9160f2666010facc8ed","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b0cac4689133115cef3a717","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9d2340a77f08483cc4db4b8","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01faa81311cd7b4f50088ac4","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a15f95933b64d5141645bcf6","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d44fa4443a7ce8124d0a70d3","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38462004b6ccf5545dc45a40","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b90c9332daa18e534fd0fcf","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ce50829c14122f3091899493","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2751c624590967f5d5249682","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5850b32526048230419690d","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e5cb56ee5eb6803aa8bd6a2","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9aa2621884ddc873af35623","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"350822620ac30f66a2da1d9b","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ca27f0cf0791ac115c1d87e","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afa273af8ca9474f2626494e","modelId":"gemma-4-12b-it","configurationId":"gemma-4-12b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"949edb06f6af88efae6f287b","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ecf2ada691fdd1c0a03b480","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6fc2dd3e0d651bd9249e2633","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6dcd64e671508e237b35918","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7a9b3fa326769247dc5cb1e","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fcfd34173707143f2a99925","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"297b1d6d72e973e016718eff","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0311d8249343cd490439681b","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b3cd8bd20e702eedb423658","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b414517eb3739571023617d","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0b8625f23efeef97463192d","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"123c6d4efe200397de794a3b","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f245bbe38d52f3b84a64e4dc","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7177df54c2337ce7eaf62e08","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67499adc1b46f586a1c3d2b0","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"49acca20990729f11bd62386","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f2a7a0301ac7cdb230df1663","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"319e9e5b1b3e864344a503b3","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2bb7da5d78c57f44d827d9f9","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8a5c15274c4f18730b4d9f5","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23c4101446e544ed2ac5b82f","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cd407ecade291b598835150","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81715bf25a80b1a5d222b5cf","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60c606d7f6815f665071f6e1","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea2a8c7140a73f18e4fb3694","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a11579402aa7ddc9dd6348f","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"706f0676dad235cacaacf815","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d730c431d429efc51487ae1","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89a616e7c917c56392cafec6","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"601a3ec51179b6fffcfaead1","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e1832dadb83cec7d9868f04","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b21e911e97485a34e9502144","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92b9aeaf6b5e97c54493380c","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d6837e9f7a3768a8f372375","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fa903a68ff27edd309baae9","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0a564da6c85edee9be55904","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de6a2332adf2390b998fb058","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7701f8f5dda40cd06fa4c776","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e3a35ca0c938e259f5e70b4","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"559274bb4d2db9e3dee3156b","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26dcfe7fc4f0f3ca73ea75cd","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25e5a78d91ee39f3070e8ee1","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fca70e45bb76253f1f919976","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cbd352ef10ac02c691f3078","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba8e82e53d70d6f8aafa303e","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"098d80e8ba47d8a6ef0c241f","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c7458f1927e4b1a2a3dabfd7","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31dd36e84421125afbaf73c8","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e131f49fc0290c2c251ad59d","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fb1a0a25e052c05799b4a8d","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46fcde8fb24e810ecbd0e3fd","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38550b8a2a207eb0da07c6e6","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d0393ab86c8e9008391b8f9","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c693dcad0bad4f75e983ec7","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a59f286887b9777ef477767","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7082033eb30f427626a4ffe5","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0daed7f980e0bd9dd3d6801","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"632c819ff919f14202c38e37","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5110c2885f54e024cd329be3","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6983a9fbb42127d71547b6b4","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64f0265c1003812ec781556f","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"673c72fe749a675bb48c99c2","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"921d07d6198fee45dc68baf6","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c01f4e5c42675a3c6f3d9aa","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"117449d508219e8cd6e43180","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0d5158b58c9798a658ce75a","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3dabdefbac77e863019f219","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2135126d4e4981631a2395d2","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3fed7a0571b3df4e44deacb","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"935ddb78227e9b20558bbd5e","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dbacd79912a83e02071a8f7","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc429fcc1335cb09f66d90b4","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e73a2705c80206386d342583","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c21205c79690fad58d74523b","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b86207217f529cfa79a01fb","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fa492fe78a6b6374bdaad9c","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"381279b32093010e53f60864","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed4c579b74058292c68ba773","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e62ae3c573bc0ed516e86b34","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94f2c4df5cb23012e2ed42af","modelId":"gemma-4-e2b-it","configurationId":"gemma-4-e2b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d5dc30c068300c623a91a48","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b93409ba27f2f5c6f9a53d14","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d1148ef014c1313b8bb33c9","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"892bc5fe99c93c72090843f4","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32105aa20ddbef33298c2a12","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09f4fa9699ed45e540bccdf5","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc6981039f93bb34311c5aaa","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94598d71e00dbc497012ed1f","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8014fef86e630db2b5b16922","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c949f5675b407fd8b972461","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b37f6fe8c07bb8bf8c55d62","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb8d6f02b4833a2bfacb1689","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8edf8e0f16e79a110f25a4db","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ecea92ea2a8f843cc72ea55","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"bf37eb7ed991ae1c14f31e61","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"411b36bb3f028339dc23a40a","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb15c5f471328aba08aaf5b4","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97f873fbbc402712668863f5","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bf99cf2364cac7350bf17b5","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6faa5c06f974d9bd6bd6075","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e25eac2feb6eedc0f86c175","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17d5928b1cc07aea7cc8ca5c","modelId":"gemma-4-e4b-it","configurationId":"gemma-4-e4b-it--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8298ccc202056776af853910","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a005dca05213b4a73bd1f631","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d40825300ffb78278062990","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa89cbb630e45386ecb9a21b","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a25e325728168d4811f7328","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53c7ad0bcc622084c5c97bac","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5252efc29a3f74f35b2cc18b","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fed2921be1ef626eaf2a2bbe","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbbfc474edba92c7dab9b479","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f36782bceb8f45f46260015d","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9532998fc69d20d9ec16b054","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08f28aaf925a9d0fe859921a","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"370832ef81cc12e7336b2145","modelId":"glm-4.5","configurationId":"glm-4.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30778ad113a0f6285db2b6ff","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"450ec3814ad0983a05e7a649","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf0dba8bcf1455f91c347f09","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d56ef2f2e608d5f1b411ba5","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d3e677c3bf1025f2a641c60","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b433f8594cf7a6275f6bdda","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8cfae35f6575df2ef5f407a","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"527bf2fab21343432d365235","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97020ae33cadfba84dafac57","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01d4601ce35baf7582b2b1d6","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e7949f905f5354d088ef79b6","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb25975b22bc9375e5cd191c","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc0e4f99afd02c7db9b646f0","modelId":"glm-4.5-air","configurationId":"glm-4.5-air--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4871200d6165cb682b2f4db0","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4545c8e6a9f48f87e9183ab","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0729665e03aab12509527098","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"922c35fbdd3776fc47267594","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eca393b7c441fead8a16594f","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f40e1888dda90b48a7c89c2d","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d03512bcc278ddfc0116961","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8adc6d5ef578a1953c26485","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dcf51bad5f69f32997356ae","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03c90c119703b5139fdd86d2","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"713f47b76c588cdeed905e1a","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c2c5f83154687619618e3e1","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c761f12b0a18361cd10bacb2","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b524713fda2561eae7d1aa5f","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5091aafad1bbf696b1ec861","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24ecfed1451beb78d27f9aad","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35ffcd0393390b9865e927f4","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09112bc5833f03e221eb9dcd","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3448b6b298eb30f990513f92","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d6ed32645d4db9e47a014182","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b391e172392ad37ac3d246b5","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcd773de3a0b8d695f5c99e9","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"089e4a139e5493e3585dcc44","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e34271c056b08e75014f0dbd","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4503f7cd70608a6263c8a831","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba4b24c2832b05c124a17fb1","modelId":"glm-4.5v","configurationId":"glm-4.5v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94b2207ac99b20596113e239","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c0bdeccb0c354ff92adf063","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f35e6b7857e8f7192a4a601","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0344a85a899d64b5d461c992","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"315001284817defdcd52844a","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fed9d2112a78902f9f4f0e51","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f20e2ae26627536827c101f6","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1bae8321f9546badb45d0fb9","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f82dc3cb8c29059c143578fe","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ccadcb53ecb9ac27bab7aeb6","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d3bc66cda454029e3c6020a","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b40312601b47b4babec1ab4","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebea8e8659f63d3cc4eee8fd","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fb0125cf298b473640c0aec","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40fe745d4d40c37a7d37481e","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c88494c785e24d0e1cdaf51f","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3c0ba45f30db91ea4c183c1","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1db53b8e924e88e0152b0bca","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34147f34008b905a9aaccb96","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ed586d5fb6e4774692dbe3d6","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9c2e61e1aa9164545b79fcd2","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c53213ee6f0915802c451959","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d316796d0ffdebfc5767c923","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9199e4208a43755ee68b1b8e","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bda5b832f8326e62befe8f7","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d02b87f4d69acd7535e38333","modelId":"glm-4.6","configurationId":"glm-4.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b53925946f0f877aafc59ae","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f27314674aef5a4b49f2640","modelId":"glm-4.6","configurationId":"glm-4.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4928b0276fd6c9a8c444b71e","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"837343c2ac3011d1ba300da8","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5e6ec6c228c7287c39d279f","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d141580c3462963d595336e2","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3905dcd5f1aeeae6a2266f50","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afd55634a947e6c3807e9226","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eba8c8cdf1f756b264cfd259","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7122a72135860cf4a9ad81f7","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7fd67d8815e3bbfa5923edc","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba3ca764bdc9824f995c4087","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c68005b6921e3ff990365ab4","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecd415b5cced2b02caaf3681","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c716d0178a13ce9a95ae3cd0","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0421e7c6e87d6634872e2e40","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d7305f2366a230af2f05859","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c7927de9636469ac8d473a7","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"384accf5ced6dc13a246274e","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdb7e30eb45da4db40e78049","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c89a56b6d6bbbcefc7ae2df1","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2827544ddf30cfce3f005022","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a8e6640c8191a779ffb48c","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6fddb525b5d0b94467ba8661","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e1cded7b38ba045706848908","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6ce561dc26c02cc5b8f2b40","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cfeb8b11e9274ce0f4325c1","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52cdb947037479b540381f2c","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56681bacf5ef1774b2acc379","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35b1c4bf5d6fa8c5baaf36b7","modelId":"glm-4.6v","configurationId":"glm-4.6v--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0771a4f46146e10e4235d642","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d958d31de170d1f70fe36e3","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e0855d0f0f6762f6c2ffdef","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"600cd8ff296dbf4c45f8dfb1","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be2db485b78d0a1b46ed5356","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c1a7f1baae339fd5be9c307","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4346349a6b3d09e86089959d","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bc781f14b12760c914bf4ff","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d361191da2645058d234a667","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6b2c07688573b5ef356beb2","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2ab30db0772c1973993e6ed","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b20d65229b0b347c90b78a5c","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"580c7737090958a16068b38c","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf52da1f53cc20f4500101b1","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6382cf43b3a8232f5674c7b0","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e4ba8a5e58f7505da22c681","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6011d3f6af7d6023a6300e86","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ab0834a7bf56a40feab81d4","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99a720d42d9ab77eb33f8999","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4e7b558ad298402697e6731f","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b5f9786af6208eb41d64f34a","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2a7e666a331885b7d3dc6b5","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1df34276ac9f506932188cd2","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66a84bbe9d4d9beec66aa404","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c709f287f79e8409cab1324","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed118dd9b03ad11a94dbc60a","modelId":"glm-4.7","configurationId":"glm-4.7--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fcf8a79a09b5a2fbc1bf7633","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0a612c35973a4492ab95c32","modelId":"glm-4.7","configurationId":"glm-4.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cd24111c9965cfb6c1082ac","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd1295cb2630e66e6f215155","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed9425416741e32642acdd40","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0db7ae079fcd8b12ea4ae666","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d0bb65c43e4e65421db7974","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c6b02da06598a9564b5f0a1","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64779412a942295b2f1fcc41","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f063c4ae2b226ece4cb36abb","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dd6590fc2f380b2c4012ea3","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c84ae887b9f12258846745d","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a401455d8af56dc225e840c7","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7ce9b77baf9eb443d943cfaf","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b9f06013867513c4304ef9e3","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f604a4640d84fc42eceed08","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e4ef0923f16cd949083876d","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70b12115dcee433abbc02722","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12babe8e33433fd23f2ac171","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29f7ca5fdc620111b0d18ca8","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"371e32e413b5c1e2b63024dc","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3428cabd424a2de0154d82fe","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe7a9aae7813ba9b022e0a72","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08067a5c23ad9c568ec00812","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae84ac005a4fdeda6ace0f05","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"498eceb3c7be3ce505460dd0","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7755d2a416f32e67386047d","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a1cabde7a1e7348cc33f64","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16de6f0d8d08fe75b8727d3a","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fa3e46f37c7db7f5e084225","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13e503950411783d5ec9b173","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2025179161cc4f662dcc530","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ee2916f2a458729d0bf1b6b","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9d54baf80501bc9f77e431c4","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5a3b5525815de32a23e559dd","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c3a2030b1af48fb9ae3dde5","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9229265b86c1968b93d86775","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cbdf43c125960c2074118eb","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad5cb316707e497431201b78","modelId":"glm-5","configurationId":"glm-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e99d17495fc238ef6244f56","modelId":"glm-5","configurationId":"glm-5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f452159e71bb7cf6c9df55c","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38fd5b20ee074591cd6ee178","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82f973f0bcc93805188086f9","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4768564e465e1b47587ec2d7","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6da62a2c7f9a3a460475f9f5","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bdaf0c08a9f5d6437f640a7","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0a4a8c34851842bb451eabc3","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"776868e5b235788549bdbee8","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"556b2cb34128790508b0a194","modelId":"glm-5-turbo","configurationId":"glm-5-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1cfc8028694159742765a26","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c39102d86367d9fb4babc11b","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"595338c539b2c4564f1d642c","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc73ee323b1e28e5bc9197ae","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30a13e7c9545cc95c3213936","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc8df65d5ad38aaa1f26ee2c","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5c0ac6e2cf24335a4aafeb8","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a53881997b19ab4302152797","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3af2e846ff223b71f85e5654","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54f0aef98b6d8f147c847061","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bdf6dc6e16a18d863fbad514","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae183160f013826b3737ac2c","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c83698c69eebf7abc6a73de","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"485e3cc25dc48e1a9389fc9a","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fb343bd4b97cb79826e7420","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5b509e455ea18ca2e688dc8","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7fdcae53e99c38cc6d93e736","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e4cb9ffa9390c3c6084fbc6a","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29edc738b17c43dc468be90f","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"751a38b92383dd44f4f4b6f8","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49be3f22ea03e85c39c33f83","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b4a47e946d0bad8e61425fe","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"824624d738ab3059a6e8fbd8","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1da9a555bd7b230511bbc67","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6d79b63b7974c406cbce5a0","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"407c1f4b591ee717a0225582","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4942502e2f28e870df1cfb21","modelId":"glm-5.1","configurationId":"glm-5.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5077a6fd8bbb23f0cf30638","modelId":"glm-5.1","configurationId":"glm-5.1--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67b15250b5c413661efd7b0e","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c55f7602a85dcd8123ca612a","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18cdac599b2798cbd58f55ac","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e94927ce7fbb41be1446de36","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b685b7628055bf6f6e85663c","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a5b16a69844953fd2b67b9a","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"509692cc7e198e1eba713675","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b0108fef26ae8d59ed7c16d","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62f8f1a0d281696ac1bdb1b4","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"517e739317baa8eb42f2d78a","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18c42bfe96c85a2bd5b0c271","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"734f734b8fe4083cb205726a","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a6e78ca66808b560219a6ef","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02dde0b3aee40e4db7e181ef","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16a667a162f6c87ff81115a1","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5734fedef2340bfa5ea45ecc","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04cb55028548a3cf387804ed","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30b346436bc3eba563c3b0cd","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65cdc57d1a980747e1369c54","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0deb219d986680fe5482eff9","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d905bff8aaed379cbae34a55","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3c94594dbb5ec187decd3c95","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18c771702d3ba14c5fc02b8a","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2aee869413c2bc6b49a8cf69","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04cdbbf68448a780f51d2317","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"559a9c09dcdd9d2aac2890d4","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d298d6a3d4fc3a4d17703a24","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5eb3f20394c7766f2c9cb0f7","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"731debb2ebe4ab8788acee6f","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1714719aac77d33cf0b3aa16","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5257c396059cf0e1ea69c0fa","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41fb67eca9e0c6af98ac79d1","modelId":"glm-5.2","configurationId":"glm-5.2--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"036eacdadd55f02cf88f8c65","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be4dbe3360dd3f02bd332d2c","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03589e0cd6d71614dbdee7a5","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e6fdbe329769f9b2d1bc773","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b2b1bb5c7a2e87c08d5a4c1","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"395626c3695359937c7d12a8","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7f416a17884df7aef90f9f4","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d421e3e8a95478bc0e53938b","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8d48be7c4b3b312fd3982fd","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"580cd529e7bf91092259785c","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c030d58ba58b16f1f98af31d","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dff0f2b52603e6e86eb2d04","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"815c075d82fa152d7eecba36","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc1e10b808769dbc5b58076f","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e0077d4dc5e45d0d02cd521","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa57afbaecfad6b6f2b99ee3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c1ac3e144270be20ee96d03","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e2a553a0ef9312c689f04ed","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07489b0b2fa05d32b9093115","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2edf5c6a680fd2d04a804ddf","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"451a12a824fab4ecfd7a24e5","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e29f3fa7a4442d420295d70","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d01a0db6aef0175ea0ebcc2","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c84d1f50e5616dea725fb651","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3ebc0609117d26f1b3c42a6","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcadd9e7664a3739734c4683","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14bbcc046d8a9fe05aa2991a","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18dfc980033586824c069087","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed40864bcdafb5eb329dcd23","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9bdb6cca3acc7ef5de99c107","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1954fd811496a176698b207","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e4e0f16955a0fdb1d162c5f","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f2e3da28b530a9beae28ba4","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d247681ca8d8ade3d4bf48a","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea4b0ccbfe7ece48ee812e8b","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6783606396b8bce8ac51b24","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12b6566ca4ca6c13138f9e96","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44ad128942762572d234bdd2","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16870d51f189414eb5dd849d","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37982711b6c81550d0bf0ced","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bac296b6bcdc867575332aa","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f7ad24f8763d179c05b02ec","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4d967b270cc1b306d32a8d0a","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fbfbcae27f2a663fec6ea03","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"919e117fe8b99db2a9b0924f","modelId":"glm-5v-turbo","configurationId":"glm-5v-turbo--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e86dccdbe57cd031461b162a","modelId":"gpt-3.5-turbo","configurationId":"gpt-3.5-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b7b5a85ad55f9f5265d61d4","modelId":"gpt-3.5-turbo","configurationId":"gpt-3.5-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4572ee6f0b5d5ed597a0caf","modelId":"gpt-3.5-turbo","configurationId":"gpt-3.5-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9805c79b15db7da72bfdd42e","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33dcba80de235a7178254ae4","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"038ce8230ca4b6eb3d669d9a","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d475d04cc97cb96522544e6","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a974fcb30a93f5f4469e5f6","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f1a98c6041a0347cedc067b","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9fe1f5fef2e00423fce3cdba","modelId":"gpt-4","configurationId":"gpt-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f633b74d416f6bd43ad13675","modelId":"gpt-4-turbo","configurationId":"gpt-4-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9560dd4fd1468931e9052113","modelId":"gpt-4-turbo","configurationId":"gpt-4-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ffe256a0e1313ed70520f43","modelId":"gpt-4-turbo","configurationId":"gpt-4-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02bbce731291738c87436522","modelId":"gpt-4-turbo","configurationId":"gpt-4-turbo--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71e63379395e6cbc0d8af312","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6258690b3586212c0ba891ed","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62391a002947467a08c83e49","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6341242383674a88e3732cb2","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08a0c963b233621f21dd0ccb","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d67dd78b382a9e804734322","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"615f90985d1bd979b83a9644","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fbd303abbd8215370445d77e","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cda7d9aee07435b67e05e255","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"babd604f90f1908b5bafa26a","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"516b003dce56d5a7659fc6e1","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"45f0a1fb80d261d7173f15b7","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2228ebd23f321bb595a53cb8","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c2b1459ddc5b975cc6374e5","modelId":"gpt-4.1","configurationId":"gpt-4.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eebaae45907cf005abada7c4","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78e5e2b4996ff8eb159b948d","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fef727774450464c08bdd0f7","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"daa1afd94711e85445c307d4","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2aa8871a8db562e9d18d39f5","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98e459e9baa066381c77aed4","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b899d6847a198d9782271fcf","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3555e10497e1abe114c7141","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22a4815b9fac3ade7ef81d55","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a981d16086d951f236f90c7","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e223341eecccef740f030378","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5aa5d02a1b67889fcf36b3d","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b85f2dfb7db4041669025541","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0c1df7e5bd17d33c2f2bd4e","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a234bcb3480d187f78e691a1","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9e7e69728999f70de8da6ac","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4bdb55f172fca20477d7ecfe","modelId":"gpt-4.1-mini","configurationId":"gpt-4.1-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28ea576bcc8fbc7f7d7c10fa","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"489b206164aa46bc047e9442","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"622f6b3b250d7dd489c93fdd","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b87adbd661773ab7017dd58f","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0776aad3ae4e24e33e23a782","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3e067b47919de9fb8db721d","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a4df2fd7696ccf624dc7ec5","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b423f62f5dc4c141f8ed488b","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd5c7d1cec7975be45682128","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77df975eff4ea000f47f5a15","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"588685ec1855237622d161dc","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00077c09ee5961a857ea9812","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9ac947bf063f982fe5973290","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"123959e1480ca28caac46f0a","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f223b4e74f1c051e27d17567","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"caebc613dd7096aa01c68408","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"645eb8d2b06c1ca684efea03","modelId":"gpt-4.1-nano","configurationId":"gpt-4.1-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60cd4a91f69f107025375b3f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bc7edbd7f528efe446e8db18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"870a8a46a2b531f6c5af62e8","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"ca8731b9c382bd00c0d8665b","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"fddc09f5e0e8bc06d04874e4","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2ae788a49fc1d3e582e9f839","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2e74edde37a3d7442f9667e","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24a10eeb3a46c7763c5a63b2","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"4e82b51b3daf5aa1c8d98aee","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"ba806794d6c0ebc1b2585e8f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c88594bf8e16a074cc837dfb","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e0c41d17488dc4ec4ba0f0b7","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"5b174d58d4c658ab3d23b8bd","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"676bf2b6f6b8d425be537a91","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c5b33db9dc0245a7fa091824","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c611da33ffcd9a9e78304e4b","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"fd73d709f3bb83bda7f56ac0","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"adfbe98a4535a8b4dcbba8db","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e8a8172c365961fe52158eb8","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"111a771f0c518f482817be18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8d6af27176cb848c0da30e16","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"952674fc62e371988760c75e","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e26cd77447c8fea5c2954d73","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"08df3f3cdd6b93731cef3bfe","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"51e4170d40d5c177fe0231db","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"60f11419a7766054a4108a18","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"67323d93d4710a1a34a75f0f","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"93d23dcf1ef65f2e23f876f9","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"26a5dad1362342e4f74d3ddc","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8196e10e1bf2c6ab7a48896c","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"893141e7225b21e42fa2ce7d","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"ce9dd7a47db415076cf5f8f6","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b8d0d0d98797b082257d92e1","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39324a10e110c667372e0e04","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a9b3da7256fa223acaa958e2","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"750e957428961c84d14679b0","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"b29b60a9d0d8925b03ed31d5","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"007fbaa1f184a893e7a405b1","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"79b4fb7fde5db57eeb15ccdc","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"893788f0d9759cc5abf9ec76","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d041de7b25693c5693bff38","modelId":"gpt-4o","configurationId":"gpt-4o--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"454128a395b09cae70c46934","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93eb46a4501346f6907da9f0","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"feeff42eebfedd28d3c20c28","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40656865ba698a00d4904512","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d07cd6e9ce1790b198fada31","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9211c553e48b0e7de26c2187","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a918130cdb50b373f292baf0","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89e1e3c13465dce088558ff9","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebe5f26d2cff3c26c1e525dc","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9efca0c777e99b96ac172fcc","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd920a26d682a51dea69c47c","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fd35df2bab242febe516b4d","modelId":"gpt-4o-mini","configurationId":"gpt-4o-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7afd0dd2e0c2831bd43df404","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2978ced94c610a533fc15dcf","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bed6be5aefcab5726cdf356c","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b75ed3c2005520bcff79192","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a69193c2658d703e3ab0d38f","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ec6f3cf2d9a8a6667b5416f","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1edfc9234b1bd40b3f2f40f","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"886b2d802aa24414c17a9bc7","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4a62b69cdc0e1a0d5cb8379","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b8e7935b9e6eca2dc1c04a7","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dccebb85dc27116f61d0ec95","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f32c3b7c6a7b931edd13fca","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97fe07dd084d37ebe2bd1af5","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6018e12c941db22d9c89342b","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"314e8f1bbc4184a98514f076","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f307c0c603f46e975d64aa7","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e53c717a8e22876c004def0c","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"833910d2932748414e7ebb5a","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90fa89e6f74cc8dc0598194b","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e73bd02fe43e5cca4bc8c6a2","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebf5588481b79006df61a812","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94ad8689092c3f208c75fad9","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7962edddc555df2dc20ca1c","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9c4f38fbea5a2fbb5f0ef73","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd50b1a9d15e800849ee68ea","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de2fbae5009e0d6316cb4494","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aefdfb568ca7abbec2079513","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44ce98b84236dedd7d3bf0c5","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b8bc6d894db65ddf0177cf7","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"feaabfee5cf01934c80e5513","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76566dd933fc00aeb2f0db10","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eded1079d08788d3af7dc031","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c15c44a6ad1e030b1e0c26da","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd00f3071c01b1231d01a8a7","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51134d1b66daccb7f547b8b6","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c65c8b6baa6f11b465f55b52","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fea6793321b322748650d7c","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b9d978aafb99e1ca5f6db8a","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b3c6c148099d10324af1af1","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63161aa56edc9442139818a7","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d2152c4a4c281085f9c1840","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e499ff7d9dd41c59d2cf26c2","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af2e972e296da28768694fd4","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7398b8233e31b341403e09d3","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5be07669413d5fbc82f7c02d","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91b99624fb02eb7e686199f7","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9080d3104ad2cdaddbdd1934","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a782b20675f1745dca4b7f6","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c17ca7be5e2a6d1755562ef9","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b00496d4476acb1c38c5a4b","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3f1e0619a146ac6e6cbb8e2f","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2b26c17405cd2af3cd3e0ce8","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fb32628f32aa74c40826c44f","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f47a7ce169e5b924bb59fbf5","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"544e9fde3bdc5b20a3b48fcc","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ddade22ee1406e208de826a","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4f30e4023a3cd5c890dc0f4","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a464ae01ac0f5f7f75c50348","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78115af496f27ad55d68d169","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c866f1bf891458ba5b21d1e5","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4bb0fa1567c2b3a28b1a1a94","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ed696e37ca20657d9df1361","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63f5a7c021505daa16f98e6d","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c02210fdaf89f9f0e12d99d4","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94e1aba89ea3744034f015b4","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dc51ca56fcc852863e19286","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d307de5a94bc7a0c78b7ba2e","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"292b0f2eaa1075a11794a0fc","modelId":"gpt-5","configurationId":"gpt-5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5cc6d996a983a7ec027de79","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd810b3c8809c7e5dacdc516","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d4dee0e98a30d128b276dd5","modelId":"gpt-5","configurationId":"gpt-5--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88ed12ff4a36b415143266f3","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fcb070e5d72027bf895a4eb","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb56015dbdf9bcad0f645fe0","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1271a620f3430d2823b4299b","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9e17b3cbbc705457a910059","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc315b6babd5754fe1888c5f","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f708b652c79fe0a2cb96ee2","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8e6f8d6007be0ba8722e722","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e73829fce5399bd164125ec","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a23b0e2e3cd6a9e7f601c733","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9abc939d215e713e9155509b","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e66145b99e8be332098068be","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da13f3721ce5566b3b8d61d3","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcdcb630b7de8facd7ec6b9a","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"948a35d44f528f1d38a3b66b","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edada08421a44d2f3e03ddd4","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4de6a5ee986febfaed4eb744","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4bc1a117796f1bf9d343897d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bb8a1c2b23359f5ba188c31","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4ded2383bf5737886312cd4","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d43fe2c78b72cd2774597421","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bef9112daab2b8a62ce9988","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91ccad8d704a295937a940bf","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c852c10a1aeb9997ba4c18d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cc6553b8b5f44f42d0cff6d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac22cfeedff8faaf8391a9e7","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92e0de6f0a6b1d9d6c54d04c","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aea508d42b293a20541f37aa","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4517e6ddfbacac5148c240d1","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d8193aa657bab4d267af29d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a392444daf4274640d0df32","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd3f3cb5ed71699740cda268","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bdbc6cc0360082531b0a111d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"480b91e9af1b9ea0b14ece2b","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"987e8a0057a72933ce78e8fa","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f7bce3e28e655c5285f0b018","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"07d410b5a7664b7b7f3f10c0","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"eba00be8c23a89a00c5a10b0","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d35182ee44e3d769141e77ef","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77d0804600c30799618023b2","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8f301314bc639970ffe4970","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1f5d834e4687add84c92091","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fffe4c0f470f545e4bceee4","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81abc9bd0c31fab2bed3db62","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d70a2d525d90c00d5382538","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb7e22bf0f8a76fb67df7daf","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb279744f928898f4a1303f7","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ed6a32c5fe7f788d3e7fb6f","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"957a65b66d2f331727303705","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4bdc6f08a0a0edd6d04d8e6","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"849548a81dc92ff4714ec68d","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c50d5e16d51cce9801649bf5","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bebc0e4edb23ab523a4bf08","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a02220558f7ab9b3d8a2e05","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"61bdf3b2d27f1ace40287537","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c991b2fa62637a6be1454b5f","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b0374451c65b0b8a7ff50c3","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13d6010f81e7fa3cdb5958b7","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"253e6d1def64f85c64b0b28b","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64dd24dd1517cda4416c0940","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da129cc262ee6417dba1d29f","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18af4c452fdf8ca84656fc10","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c50f1c9e4759fe2cbbec4866","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26850502e7bfad60ea1747a3","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6567189c20b9832b2e06413d","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23cc64a4102c2fbf7f0d7a02","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f621e321f59f8dbed5a6f93","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9bd254cfcef9d2712d22317","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"484445c812989992c1caf66c","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a16ad3a4f80ef4f749aebf00","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cbd5e115e1f8d30021e73c2","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6139f2a56cafb489a0d5e9a2","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43dc8e829983dcf65dd49ed1","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0a48c169192e6dc13bc463a","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cebf68947470466956e5daa2","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d043407ce66d5fb5604aba1","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"013b446a39385e3780136c25","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"417196c8a2ed12522dc2bb77","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13a2a213533ba6d9c09df9fa","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d13bcf16f36225a84e762f2a","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bfb0a43a3f184fcbb2a73dd","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faffeb498dc7fd044f7d1b4b","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24ff7126b123fbe6a2c9c298","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0879c8d5d665baf326d041f1","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b9c929a6fa6f2e980e735683","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0fd9c1984793ae6a3d606b3f","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5631e681e91f5d7cf5e9ed45","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6d315631424cf6394c7c95e","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d4c5eb419fdd9e604627199","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7557fca860bacadf64b9382","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2df4bbbd16fd7912105ad99","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78388e49ee401e48d45b1d6f","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"927f5c0539489cc0a6dc1e69","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ab95f3b9a2ec250c8aeb819","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"999b6bf8f366cec37f99e596","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f05d176f9e5db89e675db70c","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5db4793b8e4f1f4fac5f2e3","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"151137af98f4465de79cb3c1","modelId":"gpt-5-nano","configurationId":"gpt-5-nano--effort-minimal","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"239fa90dfb33619a5081e9f9","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6abab40890aa0c0372d0f089","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4f454e9391cd595d2c59a94","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"242467cf8ae03ca5317cf999","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cebcc0d24f668fcc1ea52594","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9268c5b8746b04887ef9d764","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47fb804697213949c1022802","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"245233a893e0114ab6b3d52f","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bd1a0bd70e4ab77e4a980c7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fcc61e29b95a07ac78e5842","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a159bfc6abd91a7c701560d","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cf4aa2e67a6c7ef11ed452d","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f2435a7d3956433073252a2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cf752361e0a75cc3c1dc615","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36f6e69708f8a4a10940441e","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1596ea955bb7e7d0db23d9a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5dc3af27f6bddfad8d051e8","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15ccd3e2bad00dbe4d513d94","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94dfe52c82affb9fd3334eb7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ecc1a5e9d3e0bc1554f7e5a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7c1b35ac1102f446ec8ef52","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ad964ce0ca054e729c02f3c7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"753b9a8a6643e8cc1e4b81f8","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcb6c1cfb154e6dfd47677c2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31bc5bcd1fc862e3317e60bc","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"301d76c19099e4fcffbb57c5","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f211d243e12f56bc1a5a756","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e264fcbbf9c34586e7b6dfb4","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f32ac719f9f42f00e7041db0","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67f77366629a3d4d08cce1e7","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fbbe06ee7a41a332409a02a","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f99ee8a4e9e3a03a96cb7c2","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be4f45a2511f61842abfae20","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29c08eeadae8b2d685b7f079","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bc5e74d87c25067c627e4bb","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43f5bf080d66ec470f227436","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b1d4ce339f0be508dd782ce","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4acb1581e4d62d9741460e2","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97b188f9a482b61245c487bf","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15d27807becbd2e61b76c8dd","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8618dcdf278a13bab124801f","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39e4db6a2d4b286593f81a2f","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e1307562e5cedc762ea7855","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30c86445a68217a0a208f023","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bcbd556ed005557ce8a7b3c","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dafcc8bbf476817926c2900a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edd0345b8eecf02194512beb","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eafdd4e9bad6ca5f08e931d3","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d7571d199452fb69e77eeef","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bf3ce28a17c78a01b889176","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edec1a78b1ba26e435444410","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ce07261b3d388fb2c493603","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93f2eb1c55112966a4b0b422","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6c3b23ea9419654c4f638f2","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a9d256e31c77a8f35cf66a7","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fdab89ccf0e68eb33edd46b","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2034e9a0a8098ad23c06ef4","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d02cf01c1f12385d68f808a4","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"902ccf2fb17b5ce2a099b850","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cbcfd9035f147316126e0cf6","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12032c332a9dd9cc63c917aa","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3a15fb476b3147892ff7991","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02827ac803609d1fcaaf7843","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"818ef12ce3bfce5ac2c89f3b","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9ecf2868fb35108a7e7ef152","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ef3e4ad9b8ae863c94c78e92","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e7c4454251c39b4487c0012","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"200f6e2532cdbd921a373829","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82d00c246f0f4a0a3dd49e01","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1395f4f5ccb6546d770922c","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be060584c97d18cacb40cd94","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7064152db45f868fe5c922ea","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a6cf9e4615c5c5fe5261c6b","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a2cead721972b6b2ce7905a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16d35c254882070f80937822","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b725135e8e60193d69dd2960","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bdca95afb303a9bc58cb0fba","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17b466b9eb5c749ece0b0106","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5967fa8ce31cc61440245a31","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26501f216454a4be44cafa23","modelId":"gpt-5.2-pro","configurationId":"gpt-5.2-pro--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c69d8d070ed466b0864fd277","modelId":"gpt-5.2-pro","configurationId":"gpt-5.2-pro--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc4e29911e90397830821424","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cfdc0adcdfbf4bc5d9d423f","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc31cb13000d15bacea6922e","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"263dabe16bfa078c8e1de364","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c121d52dec8713a26190404","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"771f9183573b3dad01cac7b0","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a226188131e02839f00830d4","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2c8a67afe8f17e6b041971b","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"719a5465610bb34014bb8403","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a2a3b23fba84b174082230e","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2b1e5ebc415de1c9208c5f8","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b70ff21cadeade5250a4cdd4","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f309b1f6f08733ebeaa0ef9","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95d78edd094271c8788986f1","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f2febde52d8d84fd8ad145e","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c4e1bd0b148f6dd51d255ec","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d984aba50e03049fd01ac4a","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d37b112d29dad129f8c2272c","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46bbf2825e58cadd1a201fc1","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"800c2b0a0a70be8dcb0b707c","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39ae139dd203eb5f9760d5fe","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2344e5d6dcea1f546cabda9b","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c96c49dbfd0aa0da502f5d7","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b486a1fb6c5b341875d5225f","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f5b6d8b0cbb04daf83a73aa","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7877f48e230cc4baeef262b1","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df4e5119a87760b18053846e","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e811f1b201ee72834eab6f8","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de2513acb4a89ca7531cc863","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3aea57a33fca8a2445fb7b9b","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6f6ccba2bca3ef7bf7d0890","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d716b0e63c7c102a4901c761","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0f3e47626675965f1c173e90","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c500501b1945eea9d57c2159","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5baf6141fd2ae3e320d68dc7","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a69fa647e71e7ea817df5065","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f673516a17545c4423d632a5","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb7fd95206fa5df765473dad","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d29f2bc805408ffd2df1fcd8","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6cf2569a32871892e4f8b8d","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a637545b18b22b592f62617","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e041f09eacf7d4fd39fd06fc","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c16de1fecb482726fe8e501","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75d0d7792bc9a3baa87c3bb0","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be1c7cf00872b8462a1131fe","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0856c22135884a80af840b3","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"061ce8db3e09b74846381514","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3c4874853691ebdb76d0676","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a6430a8d8f773ee0e4b369f","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38295b12f6b510281d185208","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62c54d2819ec816195f7efee","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/swe_bench_pro_public","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2534457eba7560619f63512e","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5520b5130f9fa2fd774713f1","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d7b7db9d9e2d62a4e6255fe","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9e59571f50871ec599909b9","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"965e8c06b231b38d68f45540","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5793613cad74b4bf6cb32671","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"445494e2c75b91f1b1c72cd2","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c09b14f332df9ba540c4257d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f0043eebb5fc496f99c5d41","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"335557613d037f1c50797a2a","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44f6a9d0876c62f9969bd2e2","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d2598682aeda2b70f8949ff","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87338a3e4925e9b09e12613b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"368b27fc0d4a6105664dd792","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a32e0b0ff5a7abc081b89492","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"836a4fc52dce6b924dd9342b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bdf8e025a1f4ae5a410deeb3","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a87bab0335db022f0edf404","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52d38f9a5a5985b6d76dae3f","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ccfc0bda87f4b31e905be73","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2f48afd3e9ad8bb0db50802","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37d5d7b1d721fac5dafe7e7b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1076b1318c5bc4c37d18d8ea","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b7634e9a4f2aa6ce1c7c3d6","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"131dd74a1b35809a78362aab","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"941548924b2c6866be36f69b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c250f07c5969c6b28d8bed0","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd8bda1b05dc61a3ffb32559","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d560899b3e3a3783a09b409","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4caf2a595e0d1e29cd4e1527","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8da817cf91aaef2117cf732d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e51606290704088b2cbfc50","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cfa95e087695c99aed69bc84","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3cd56c92a3dde88ea9a3b202","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e5f76e8ff788c8b28858d6ff","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5547369703711b1d6c3e150","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6590cc5a5636c4c28cd7640f","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5352b2fd6acb9f531b953bae","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edcee1bbd3a7ad3470f20bc0","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e02284a264740ec8e4a969e4","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"018c19fb8733fd63bd768352","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a187a848fc0ce99eadbd03ad","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7a2edd91ab0e54985453abe","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"790a31336a15de7f1c2f3fc7","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57bb57d79d367ebca4969ba8","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d0e3516448fcf9952984320","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bd37c42f412294161b38513","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c23a7086cb8ecb85426614bd","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57762c5e8137a2a5daeba07d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4da6e2b1da2186d54e3ce949","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebaca6d5960cef29ea2c77b1","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c77624126c7259d8d6689aa","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6588a09b2111a94d20040a31","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72cfc790291a15bea1f469a0","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a30b6a299803a8c53fc386f6","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfb7893aafefa95f0bf57eba","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01522a0eb397abe9a4b3e7ad","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"257a53ade2ec0f11fcf6427b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42418946a505191ef5a70b2d","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2db0c825f02a829812d96d8","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4878e09873eba784cd6fa9cc","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28f8e45073342629cbcd1f04","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41e3fdfa813ae60884da5e6b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d96b030853fe3babef9db93b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cb30bf867f5c1f5053b7a68","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e32c91e5d573f8a290fc9551","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a42fe3f89a9b765429303d8","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b35fad67d00760fd20d97e51","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b68876c858e31ea44d4a6e1","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6afbef4b4803b50cde7c41bf","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5396f9036343c5dd9cd9cda","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"957da9c906905cbe92dbeb4b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b5803afc0439a3888bb92cf","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9257050d4bc850e6c5e2ecf","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"392fdb79124099bb95eb2e2b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edfe6c94aa68b7f9c2f45609","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5ba40fb088648f40631c495","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64edc39fc6734975a7219f93","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dd63508597a2e4abdeaf990","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fe52f111e50218f32b63354","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2278d8f84915981206e7d284","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3ff8dee9b631894975c131fd","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c4db83fda20000c64985fe3b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d29bcef5ace537227fcc55c4","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23ff2687c585c8fe5f3e5714","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc8cd3289013634e97f64c0b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f36909f44f6bd6e3d03934c3","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52c9b8ac34bbd17642c99bdd","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"403a6d3e1ac200e730c8728d","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d71279bf2dc97982cc5495b2","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7ec7fb8c26351288b7ea90a","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da9ed3465f84dcb583c05cce","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1b9a2e80cbf15c34406293a","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bef2b5724ff17eeab4b5045","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7d514c904e2ec6161fae584","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2246eae6e2997e08c4d65de9","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42f871c2b906d38c584a352f","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"469ea5fe99e4ed4a10b50a81","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04abf124fc7c57207ee66816","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7b73b0067ddb6090993cb88","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27e4e952645d00a7f8a7d955","modelId":"gpt-5.4-pro","configurationId":"gpt-5.4-pro--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eccabedcc721af9865bf90fa","modelId":"gpt-5.4-pro","configurationId":"gpt-5.4-pro--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e174c25c1c54ebe5c182868","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1555c983a243a17510b40dc4","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0152373f98f2f553016fc2a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69efa434ae02e80b795fbbb5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7047715ae9bc7a865daf3ed2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c8b2c146c296dac71ee160c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90e2155ee6574cbfb408bba6","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab8a89f60798f3987c2b7439","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fead76f801e079bc637ab4d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cc54c913f0c3c5fd1bfbe8e","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db1c449553c526c3c0266728","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0102948a1581c1564f0ee927","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08caf68c49dc84001e718cf3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b511394630e5ebcd27d413b8","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee1edf2b4c024e6b6d38419a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b1809ab0bd1db8eaddee70f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c972a4925d752a97ea28660","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0135d32f920a750ca394238","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b28b889a3898a56c690b349","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5a79a77704aa637fd9795ab","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d75515c5eac922ebe333874d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5abfa43f7467e27e111f92f3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0205ab4d4424d47ea961a60e","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ddb11bcc92124d67baaef78","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4022f7aae075849e8205d262","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d152fbc61d352c9b84ff711","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4686881dc0789cc81968120c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b208e8e21bc42a8199de8c6","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b40075d5b2e59191a241eadc","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09a711065a797c504b74f99c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a36d0ff8afb79dbbdbfb0f4d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"548462147dea4c436e05bcec","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b28eee79d55650b860a152f1","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"434bd0d5c4a5bb430cd9f3eb","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a195cc6518912d9182efcef","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3853cf819c86f900ecd527df","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d4c21f8dab02b0247fffde8","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78170a0f6e0ee17187ad77d5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be62a02da138b9b14310aa5d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fe44efd80ab7373d4a0b6d0","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a58774ec1fb4cbf14aaac7e","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2eb0409f9da6a0ee0929913b","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffde0f1dd99c1c6271ce3439","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e3eb1a94f0b4480f8138f70","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18fa03bfd44b7cfa49c6e776","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86d356377d78fd0604c1c3c2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e715eafe935599163304f3f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70f15d54df23ca3059f38070","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"264295f63d7a32bebf53fc80","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35fbabaad9b8688274150578","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfefacfe1b5abecc9a5307fc","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f840c6e9b5ddcec51c48ee2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3711a13a54eefb292d276f3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f7b2ffe7858c791c7cb06cf","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66b92c7f427f88d6d7904ffa","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"77b7eba99ad5a5fc3fec1ac5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"02e59ffc919ccd6442705b12","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"631dd98cd9c042f570e09cdd","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c69cdc7db016bd0188152763","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cdfb469fcfd42ec46534c3e6","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"938728d28eadcc0276c3067f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97f48ea80a1054889428f5e9","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"390acde9b4dd20f84fcd6e76","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f194b42101817c7b5720086d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f9c3bab82f67b9b5df4c67c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96bdaef9215773ad68035c89","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"debaf5299891f9f141fe4cc2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78f55495a92e1dd015dfa7e2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dd16646ebd62ab48b2e0e28","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c1df08526cb67f7263b2be4","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e02f2d421477234c78032860","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aebf349d59b3cc886404354","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"febb481ed447a56ff687695d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a520295b72b53f9c88bde2b","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"142188041f1e2ebff8fe4d2c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3588eb89e953dc5abe08662f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4625d73442d6f82dfb89fe0","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a898fd86243ca3a79676c56b","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05a390053ae415339bb8f54c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"375daa7952f0321b6fb177fb","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d2fcfb4c90f4384817d28c2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5086da290a2b683a13289e77","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"755ecb13869cad91fe1c0123","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1346726febc4a85d3a200f5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67e2b8836084dff484d7b8a0","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"111185a60b03a16824fda31d","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a487dc8f09788c69c77af1b","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1226618afa18c4bbed26581a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bbd40220411ff27bc823fcd","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"abd5e28d69db084a66ab35ba","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc45f7c6e1d0aab8b73e7aec","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"205dbfe9537d5cfd1c612317","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58c732552823494e3e219dc6","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e082fe244b558a6479f48c03","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"073ccc861e30db90aaf28ba0","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"552921ea13a22c9abdd154aa","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83db8e5e910b00269a48317e","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2171f2252c414c3ccf229887","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e58e8485712a3d724ce4a879","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"084e9dff682a86761c6ade08","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2721170b729aceff41261c98","modelId":"gpt-5.5-pro","configurationId":"gpt-5.5-pro--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e24cf58ae552e5e1cac37b5","modelId":"gpt-5.5-pro","configurationId":"gpt-5.5-pro--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e4b0ebdcce2198efad4878e","modelId":"gpt-5.5-pro","configurationId":"gpt-5.5-pro--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cce8835bdd40983dc9813222","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ae52eb4cf2880f7bd01c7cb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3167b8d747931de751cae0b5","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a726b6dcf749c9acb5c7bbf","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02d05c7abe22fa3285c9ac71","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72bda9ee03ada887ab9f5873","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"130fcdb5555e8dfecd1cabbe","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e83b4b8dc25bfbb27019e9cb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5216268e146e799b95dc99c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"856ab16a48655ff4a36054f5","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7efe6c725ad52ac72d679bb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86b4187194a5b9f269e16b79","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"998c622e7ca5d74bf4f0b53f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6729e09b403ab4e0dcf0338e","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75bc8e752d3bcda5970ca8d7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e5f958068d23d661d725ec6","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4a9161028703eb2351ca812","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f206c44a226d2e55701f09e","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a94ce2ae1cce557c73c568f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0089ecdcaccc9d09718807ed","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8224f9cb2cbb8895671c5d44","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bfb1abf53ef39946b34f5e34","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db6c8eebd3a0ec57c7656dd0","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34b547f008ed398a4df7fd80","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea69d1020a5393a70c8173fb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ba86fac5921f386eb9c9a42","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca6f41331539c64b2a525ffa","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bb1f94024cf4ce3880a9396","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba744ce31ce9f95019e58b0e","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d58bd2f729dc96c19ee00f4c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5288a983e0221cdb92143a89","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a815bbcac49bec64b4d06b0c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d58c9fcb89c2bd7055e1606a","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"694fa4b4d2530aecbf590015","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d72c6dd5da8de1be61882fe","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1e54282b4f1f8f519b7278f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76e60c891e3116396dcc7618","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59949b95f1534a3748990225","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ee7116910b9330ff78fc872","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46ea87c1942d502b2b579cef","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c15d04aa1dd9a38f265a487b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dc7c87546ca68ccc7831299","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"303cc2990f189d9882c8659d","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b59c440fd89debc23cade9c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecdf8537de73a65fbe62cb3a","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad38303a78643d9e6c5e4560","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e39c449a599e4b624e70a50","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47864eccd9ca9b39975cabb8","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d4ee4765d6cb757e51572ec","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8209490ef6f3208cc77978c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4975272e5acbc2aa940a99c7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc7d08143c8ee816bb7af3bb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dda6ee7aafcb2845bf15f032","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc0813a1a59d8d5b98332926","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d0b5c2f9b2912655f6b841c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf832ff3fdefad9e9307166e","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72086a54f01ad01620ebe237","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8db81fa541ba661730e3ca7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddfa3e041821424b91b3d610","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dfef61c8d999d26f5ea98c9","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4a092c3788d5c3b17dee941","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfc8b492223a91f50b185df9","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7d33a31cfbe100e831b57b44","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5d9a53e8e9e01657919bbbeb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"715aacb5bd2e20f8cce59472","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"150c85bb1557c00c7a6d1ffe","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0c21ef5ec77360271acb025c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3af8b4a0b3967e921bd5faf3","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97d73e26297cc5a04b0a10bd","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"197ae704485f6de2c1c7af50","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"620c20db96c65c82d77d6437","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d46bbeaeae22d52a50c1fecc","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1eb3c4388a173c7eeedd53c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce6f3b545cf65ab839014640","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d95bfc8437fd7cf311431cb1","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b1b538a23511ce91127777b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b05f1a4dd27368185ebfd113","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f032e1b501645e98f29247a2","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"182c267f7b8e72d819bdef01","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c61935922062d074c492d80f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"905e6d83a9a976db0cea7fff","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"001bd78a610f1da56b52d85e","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34aa71f8070e9a1e6ef3977f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d843e67fd6f0d17091736af0","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17f8252b564348eeb47626ed","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cc464ae02f3e9f2da643da7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a69ede28148beb260bb5f32","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22aeeafcd445d2a241516ed7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d5b3002c73d51ef146aa99d","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e45a986273b02dc7f81df27","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a3bb3e493e12f67a8c96ad3","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da420896895bc43bf8c2a41b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9c8d7ace58f0ccdc08bf59c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69606b281be372d0c8f5060d","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14294eb2fb3509916b51e379","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d5408de712e8c20684fe7d9","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ffbc8e19c59582d10c22554","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2854ee06891af72b895e0a6","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58b2a2ac3a81857ae37fac17","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d97b14ae64e526fca71b0f14","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d581184225be8abecad4b42a","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b56c7ef4cb20e19925c7bcbd","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41d96fb8508ef9bd7eca956c","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce146c74890ffa309e9e6ac3","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b08fc13fce99f9456b958dd","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6552d55b1ffb5a8f8cd5cc5","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbb6678796a098c465ad7693","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e13b0797df057f018b4ac2e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3f6ddba7d18a254e6a01bfa","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26a18cb1592fa063905e6ed3","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ba5a8dbc615b784ccded444","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1fe717e190f981f5aa05822","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b3de29f0db37a207872753c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43e8b61e20fdb59c20e6462f","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fc71784b9a3eb4248ff7395","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f264d81d73e1d61369a091b","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fbfdfab14c4b164ffec16ce6","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b477cc013715702362456cb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aacce64036ec0f0d8e84e89f","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d31e56c6568b45ad1761e422","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a79a1eff2db294d172ed855","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afc9edcf049516f411971faa","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3023783527b567d2a67e3b4c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d0179989b5bf4843fd20b3d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"374b31984c9bfc5328ef0769","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac91c9769eb3daff01abac6e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04c71a7ca3f8e9d23016f19b","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe671423347370d5fbfd1685","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b9dbe4777c1a4c323eb5d01","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0934bf143e987370e42469fb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33c85549be25373443706bce","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0310a1aaf6347a09fede947a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ed9dbf3e31a81649cfd02ec","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"875adc69f4aa8909b13bf19e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a5e7ac9815b8499f396808b","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fa8772d66054f3eee51e969","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5b508d43827d30796284beb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fc514d918600938d56ae075","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c2ef83d138ab32b93ef88d7","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9528e218990bfecc472a95e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e663c8f3737238fb9d6e347b","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a56abe5bfd97bb76792c1893","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96ff192b147ad396e888ae9a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f5704a90ff59264335a0fbc","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00f3ed01079864e0a71ddb7e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b02c53f17931e0611130b75","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c89f4aedb58325a99416195","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"734e78470097075663683c6f","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"985f2998ffeb8bda69255f09","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddc38dc05a8c2148da4d0b49","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48f0cd2d5fb346e209366d47","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e48011239d82bdd7eecb7877","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a14c93bba5879e21154eb3c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46dab6b30ddf4f6a6277b5bb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cdd519b2333828133a5ed982","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18ede9f6bd90825a01e9163d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8c6b3afce23ad69ce7ee3c1","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5351d2eecf30c83b35817587","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5248437a4fabf5fb53c069a5","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9360c47d82412d751eec04a0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dfc7cea1f17f5b6c9939d76","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4938b0cfad18d1bcbfd8413c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d039a2600471fdd98591aeb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c49c48c890b3be06f4a43ffe","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65616cc744847daa5af4b6f8","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e05ceac233710b02ca5fba32","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c16e8f935fc3fbc0cc1bfd4","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7dc7485ae3112a509863bacb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e4ef7a0d80b54b2b4f40df8","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e1214963abbedfbd236f1d7","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eaf5836dc0d624ab48f5d238","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7af2d5b89b2876daaa95166a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3575021ed42f7eefce75c85","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8a235fa1b4c25978fa241e47","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"280829df0609ed1382ed4a5d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7e0039eb395cbe91e7c8810d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"52cbe7096d25c4e59ae6c392","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6e384940f06acf726078ee36","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cabcf5c45622732e23c417fd","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6681f350443008f8fceefd48","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"632ef0e8d2883b55e55e1c3a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17566693e8a8fbb09dbf7cbe","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d8c39b5b1f8cffe20bc488a4","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbbe310343957c43bc35b785","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef3791ef2791a9849a7cc230","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edf5d917eca3ccce858fedd4","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2acf89349f68435cd22ccde","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7451fad1dff4c15ecdcbebe","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b319780d68012d2aa8b2b8d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac708520fd129a87e0711859","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07b7ecc7d47057f40710f618","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5839a1f4954b5ac6747e3a4","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fcf67e993f0a396e4bd615e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c17d26923573df115fbe521","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d229dde6dba74ddd2adfedae","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af6ff9f9a7007f68a56908df","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"974f6bd0bff5e3a6f76e05ea","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b14b8bbad5f6e66599f14fa","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08b420cc86ad300f73cb6ece","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f0420d7590f84996d2ea9d9","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ebc9090dbe06e85cc04ef19","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f97d02e06ce3b15733d575a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c678da667a6203b26e10bae0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ccb8868cd62c35d4ada53758","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"424bfb7f9a3e98f06a09af81","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dca4fe966c9bade5a782bbe3","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bdff50e874a09b8eb58d148","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e82c94bca1327e12e4c3458a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0a5454443397c5905ef4d54","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dd6efbb347ef62f98104dbb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98f6e9db1815d631c07dc6a0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecb1e1f34aa85b54b5bf67a4","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c982eec64beba458859ce0cd","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6dd9cabb0925f9fe971ca60a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e737a7759ccb7886c36e2835","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"908118dc12cb8a5c5991be3e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44d14513877192a9ab52ca19","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"807ea1d13e6eff4620060049","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b83cb97a7ce702b83c5f1a1","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c14d5d98e2ac0c35e12373b0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9714ddbf13fb44d8cbb4989","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3289fff293acd220d866101d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7154b7752b50075526308bc","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ee05b294998d24ac869adf8","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd0b93e69454c6e0b78551ea","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"045b52fd58198f20f15b3ce9","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f837b509fff80b3fd9db2ed8","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fad35c7386624c2a0c2ac667","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62794428b0bd5556f2e3b55d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f69d5838266c7bec7767e88e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0bb3e44bfba219e986f640d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cf9b8871f98f2f3dc6e9717","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a40b0840d2c40ef5cde0e911","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e918305b007fc81bea460c3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7a9d82047bd5fde60daa5eb","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f7d02623829941ccc857e01","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9411741547a9ce320fc3b7c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"558071cbc1fad71c429098b9","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"137c3a9aa2b092d9dbdc6f1c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3000072f94bc4328db441f14","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"037c70d5b9f11f368b0b0598","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fad8351a8fe27cddc29e147","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73d74bc56842a1d8b5be5c1c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d85f1b4a2a8201a16399f3cf","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a40b76164fe807dfafb5a7c4","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3bcddbf64272cee4d28baf5d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2d291031635829ba6765af0","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"273cbfb2e0ade778457c9c4a","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c1370b3f65b8ad3d1b78deb","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3aaf828ef24beba259257923","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26bd50204ef69387ae04ab34","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1c1c81c51606d8460545c60","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae746b151e814f96138c1d79","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32c2e9ca6aae5be333bec8d5","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"244c6efc802a0039e056a8cd","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1370d186b2f7ecf637dbea90","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24922a66c0b217def3fc86dc","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"176963c027b7fb0794676ca2","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a35d51953f6500b174cac323","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e225af0afd77797f02e985af","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62790fb3721d24b15758fb54","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"008864bec446e487e855b794","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"314e6e1525729ed3edf53d23","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a50ebe54c39cf58f5033a93","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b98e3c88455d2dbfb7f82b5b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2372abd3a60a271d0abd9477","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33c3d386b31ffb1ebcf6d165","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ec772f0a1718febe4c6d844","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c95672aeee283b5fef342d8d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ba4b2be874ab19488769110","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba683fd42c10375f40797b41","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29a07ed0747163fa9f389e83","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aee60a93dc8fe876e4049c53","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38cef7b62412ad7e99c933fd","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d0247f50e656831ea9aabde","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ed56a539484a5f73e9ff3f8","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9f8a6ced8874b25dffbcb42","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91476fa189b93b0776f1bdf4","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42fb3a4f851acfa22744a55d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce1052f4ad2d977687334955","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63378eab3084fec4da7ca85e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91cd264955f778eb91b1e72e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b51f8fa2004ba1eb88914187","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9c26ca9b33d9a30127d7187","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3bee327932a8a0599e6b585","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c51b0c5bea9242071dea9961","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9680f81c64b5caa7a869f5c0","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5524ea51493c56e06fba4eb","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b2e849d7082de02f0431086","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5581c0c0fe2eec4cc56afc3d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea99a5d3d1870424b5f5826f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e5114e5e94150ac97017ef7","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e70e59a6c4a148a62a6807b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"db529af327cadbebe82b4ea7","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"64b892a9ca7a6bbcc0c53e7e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"42f39e504fc7276c2c18798c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"acb6eaf0788afbef68320415","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ec4c04a5ed6eda9a62523050","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c158bb5391dfbc5e2a3fed8e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4df55542bb4bc82e99db4ef7","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18975919769d79c2f7aabe27","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"756d177bada59c09b067ba79","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0cf0c4cefc218ea3fcfed10b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22b78f1948d47dc36cd93ab4","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a51313008ff68cd29a5f767","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1fe3c0b12b2dfb5a6fb8eff3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b0554906366f0cc341dab75","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63c5560222549737f2e0e88c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8de910ba2d29fa18f668fbe2","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fa4671d195156dd4be0fadf","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62279a52d639f31937928cea","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"073ceaaed64a3cb558696e32","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3cf6f26849ddc64f37fdd32","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d920f106407fcc40c28ca6a","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c541bd9c7c101116ab98982","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"504d18053fe74d158c33aa73","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22920056114cab28593ad293","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2128cf2168abe6660486280","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc2e0c6125fc70488c1fc96a","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7a2f490d85a68b29c409a12","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bea096f36c115182b9981251","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98b78d65faff3684e0d83b45","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06d278dbab87f1de97c29cec","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e46a92f2078a80f376c15d27","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f62d1c0f70617c2ce6f41103","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de4c360a76fcf8f1e9238e88","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fe60085a81d28d43dd1087f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d90f3d960aa67c0446b46ce","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ec836beaabc8142f018c103","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0582a202960b97fa05e18a5f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73ef0228f016101a421c4e50","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7be981f3349a9a949db3cd3c","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac862758f3c982bc745691e3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bbae9a1b4d67b1fa44fd55d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"027112d02ce9fab19994b1da","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3ab01caf6d0687478a0ce49","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b818dce06c0fb558e7d7167a","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"853bc246193f33df5eea54f8","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a8c913b486b6fffe98e5acb","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4620c3a04edefbb34c222e8","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d998a419297ba93aa26c6ef6","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2a027bcbbe350e83bb9379f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8af3e2d0812a9e3c0e993ce1","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b1b840c7e90fab89305a587","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ca3b5887af025e030617db6","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0e6da3e67b23e17eb3133aa","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db85413fe9209e2b0de5cf0d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"755a966fab65185fe86a6a3f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ece1ff77463962fde604f4","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad79ebd59f8f5d834f4842cc","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7b1fe48660acc637ac33074","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aaff5027a5f7e208e6c185c3","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c740aea5a9c9e66b074bf005","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59c29e213b13058e1d392cad","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31a8d7d0aa0db25528ac2b90","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef56f4ff0a4a4be8bfdf8ba1","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc7508dbb3bdcdb821d33dc3","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2590ff6ad112a045406a0318","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3a1a5f0185c6dc703f03e14","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41f6a229e3c6ba9c944807c9","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9556c116d9ba6cd9674311a2","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19b6f84e00cca14dab4e4fca","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"949137762feb62cabd539e6e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"230415b4ae666279d98496a1","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92bb39ae21e69a4c49047131","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc9f1bd4a67db549d887eaef","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"61f09bee008d98058c42f4bd","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78e47a74727f6a0a7b418e1d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df752fdca1226a27fd5c1a2e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b29f5b940ffa1a99be3c0d5","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c424f776c3f2564a289da5fa","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"271459a981fa3bee871a0b22","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ccbfdb9df90f7cc5072208c","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"573a6e35711e9767dd69f9b1","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c33190449930ca4e4225fc5","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80eb32120b91725a61382370","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fae24ca39aeba9192224ce1b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"402d36c960ead254290f0768","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e610fdd88c714cb30d3da16a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0ab245e5ac013b082e6631c","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"509266bfc25d269b8b5a31f6","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"248d5b9d9353a7711dd6b98a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"179197f8c2324342b4bee44f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80e9c426918b7f08c57c829f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c22d718b307d5bf6ed04a7cc","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f7d3bf6b13392365eae0d7f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82b3ff8257025e7f86fad034","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16384903800f91c29ce6cec4","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47a30e262a004b8e8fa788cd","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3df17843bd35fea92a10f84d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8ad3d59cda0b382e1b99b4c","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f55dd30444f88d31ff3696c4","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92aa0a7d9adc26688902769b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f3b750498047bc39d9bfb71","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"dfb7acba10dca5fc82abe032","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d30acb40bb5196501ac2761d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3642c13a42011ffb84ffeb73","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"100886d649a4b50d59ef79b2","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"04a342a30a8f1280e4a629b7","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8df8efb4fda9da9b4fb82f8f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6716ef13baf122440d53c71e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1a2e86cc234d929ff53ab07","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"915654deed8702ab05055898","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"335a849a2fb438ec4bde5168","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"303c651e520abbafb2c40136","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a5fa66a096a038191288912b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19deff1c8e90e34d79f61ba5","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2593f0183e54fb2f104a565","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0777683eb17c6897536a177","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"408d3f3efd0b6cf374a543c1","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffe7d8651a092d9145619e25","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"136c5da4e66b0acedfec718c","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"359ea8551779850d884aa1cc","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a66add5ac66c7147bb42a309","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce32ece08b025d45757eca86","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e53011a45e167017437eb4c7","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf3b4f7295e1a5a836532224","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"784760cd062750b782d324c7","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fee066836b00e916e060c936","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"126131a8129e9a9ab4523922","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc2e317c662765899635e709","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e08cbd0435533452bc89eae","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fea2051b45d1aeaab254e09e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c5432a88a6429cd53ba80de","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aff9b666a1cca3b3ee07c2ea","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34add3a000b32e26d7ba251e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f7f64f65d746e4beebd2d85","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5faeccd54fcda2954357a39","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-none","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"excluded","reason":"Source-reported label. OpenAI documents Low through Max for Astra; this does not establish a supported non-reasoning API setting."},{"id":"8a7b9cc900bc1e48522b2d77","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"192a0a52134befbac5912c90","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb733075f994115168315353","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa893735776a86c9eaeeab33","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eba425fa2243963df9b630e9","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49b1b70f581245c54e071b3a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"434544966d1431c1926d52f5","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91bc2d06c970323599005b34","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf597f8d4309561326a1ef1f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb6111da7a05efb610da52fd","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cefb2b8c7589ea007cb6a16b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"523b22474bb4399c00f66fd1","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"abc6e0a169207f03d4d5a0e0","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bbc2727f91077b7a22629e2","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c503933cc53434f0f92b70fc","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc1909dc186f18f73c79311e","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f405bf6233adc95f10658e3f","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8ef371ad6fa26792fdbb7f7","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"638d7bb3d20aa239038426e8","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eee8c8b605f6997383cbf15e","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c40749ff405aba50340cf7a5","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6a5a2e3ccea877bb2e6db69","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0db19adeacb4445ff814565","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee9bd53ac94dfb155f2ea271","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46bb1061dbb6bfc2f6366ec8","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2651230274052f15b2b3443","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d9de7a169cb83d5e01f7d9f","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dc3723aa579693808cf38f3","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cd6972861ad2dde662f2af8","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3341e10e726c8da7b0533867","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f51a3ab140cd5bdf49e8f14","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"976efab9e73a5b78a9019c7f","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"adbdcb278184f49397014445","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"684fb34dba74fd14674a23ec","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c084a484b6c8acb146dff42c","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9beceb876fccbef7fa802cf7","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a6ef4212d041bf06cf764a","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ba3e86b77e24cff96aeaefb","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6e6c7c03102d2ec5db38d6c","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b31454600a41bac85df8781b","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"44174058a335a21db34cab7b","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0d55b9a126f4a041bcfbb598","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcb24bbb729fd83366ab2bd9","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01007d88982bbfbb8f529d6f","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22231d4d7245b35d3625e3af","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"612939f9cf2e8c6074b59550","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c4911fd6570f2e07fce07e2","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e655923c9219b67e8a6c1fd","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71def977bbcfeb57928495a1","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5158abda3c8444a4add0a606","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06bbe372969d1260d126de3b","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29df99841d606c663c6cba2e","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"324cbf4c56dbcbc2366d864f","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"261cd80255a8f86b29cdc64a","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7ad936a08ee7062350a5949","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d25466d9f8bafec004c6e0d","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a209082ec9bbfa072a58c650","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af73940d617970fd2fef15bb","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8a6e40363d5090f2ad2c7ad","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb045928e30dab4357c9599b","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"210db506787c6ac19c05794d","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bba46d32848e2eef7785b44e","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95200cf35a926a4f51ee2775","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2579297fa894b9c2d833764","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e6e6e66316d32dd747eba8d","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a55d1fa7a6a7c2c5d6953114","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d279df6be2703d37479fab78","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"564986d48d63eaff6ee3a969","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9785f3bb2637f59ea5b99c98","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca818e3ea19482d3b2454dee","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8b53cc40fd8751a180074b7","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f4fc1b4c1ead78822aa1179","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff8288575593b36e49c877d6","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fcf9d977ea9bcd472708bf9","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e0d3cbcdd797311812457e0","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a200d1455a5a357504736341","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c79b6f15d83991a7ab03c12b","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1127c1a85f619737a188828f","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"783912f707a26b3b11a91fbc","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3bc57c6b44aed57e184220ea","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"277feeeee0e2bd32670548ad","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3068709e4fa6d80249ddda10","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dc0ffd2a175311df4e9b5a2","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bae854c8ba6955a5ed0dd327","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53d5a25e09a84b9518b95531","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"050e2e0ea6629b5c9f1cd8d1","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26c8fa378df6e0c862ab999c","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f152f80e228c99fb11dff1d","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac1b2b3889ae72ee551cc306","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e148f07e65bd83da8552afc","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a28e521275a8117ae5ab73c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"332cd4432559a24c1067763a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab02bbad93d66a73317ac504","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dd4ab978ed9081e7d2256b1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"036d3a1334196c80a57915e1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1326a222541d5fa16aa3d69f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8c5adb6e6a04bb44455088a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33d428149eacb23f8023a22f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90dc9f391ef590950102f348","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f551e9f045bc0b6ac729b202","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"281d1eb368851122cc17db8f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2f7b3ce100e19c3b23c1e5b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a58cdd26382eb8561a3891c9","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa53133f053c6453c3b57345","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f896ff4dbb8782a2ad6cd1ef","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76697b005c207eca60a37292","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9a055af1a46fc2841cb4811","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7193993644401ada0c561b94","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac16b72863ef9ad38f76746f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31d0696779501c33756e0d41","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7551c8c0295e481116b6da40","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87938cd53777003184b7326c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a7ea11c3b23006d2057ffc6","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e22732096c5a7cb5e49a22c6","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"864db222a3748d2576b04d3b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68527a9aa6a80fe2b6b57d58","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48b6077c8917596c2ef7209d","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39e2717926fbad74a11cd28a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87998076f09f0d9f3a6d9164","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"120cd61fa038594ff09377ed","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6a4bb91832505b0b6e788fd","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"324617d001eff6640ca1330e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8c6fa9ba872894ea7ce1c90","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0348ca9a6bde4aa27112f9d8","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d16467e883bd502ba32d9e0a","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce4626bb5d5d94abcaddd1b0","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6729a1bc7854706665ff871","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b15b56bf252797d3b5d91e95","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"326e7b3889e629aeda2d9b20","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"abd3c444a2f68677d8e6225b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"723887484db7ec3fbb615c5c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a3190a3f384ca2ebc31bb6d7","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b73b3714dde60636c917020","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82d2a580c6f40ae99a27fa94","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff80f12b5df368a65cf2f2b9","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02504f35bcbb21ae0c5af2ac","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0561533dc2911a9c3050e1f3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7221252780a4b1647f643270","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3240e8dff8e99f1feec0b685","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7a445e9105703a4a9140142","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1676bd960d1324c582d1bb4e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"234fdc59aa263bb853ba0c5b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb11904c98e84a986b9588e1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afd8125af880999aea9ef239","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17cbb7437ff01131c310bc9f","modelId":"grok-4.3","configurationId":"grok-4.3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69351a9c04f817687a4d844e","modelId":"grok-4.3","configurationId":"grok-4.3--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a316a3c001d815220879252c","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3dea1bc0f28e76fd71c35fd","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f472a30aeb8eaf66deeba1b","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a57b0612082bbbf111f35e20","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35daaac2931883507e622ad1","modelId":"grok-4.3","configurationId":"grok-4.3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e04b4c1584c40ead300a6494","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54926ad11c502455b00573fe","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fb681f994810c739344b77f","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa8a12feceedbdedf24b72f3","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f6cab432b7af151e56d72c7","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"927091b6f30b8898774d9b75","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"74d938a06c551969af7cf629","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c4189a8314621ca519523e6","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cce6b0003a75b934b5ce797d","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26e57c4171d8af90ff7c9d8b","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfc2d18c6b5c05d46a2fc38b","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b62bae9938cc7ca82751c8a","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d148747c6b768836b3329d1","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49ddf105c76cb6c65c9788e6","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d472e7944026d02ff693dcbe","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b158e8057762eda00e49b8a","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91458be076d7e97fd168922a","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"377fe99391f8f823331313ae","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0212dd4561acee977e00400d","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3db181a4b2c903d1c6f5ca32","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b3763ee781610c75ebd4561","modelId":"grok-4.5","configurationId":"grok-4.5--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3dd688412c9fb5675915351","modelId":"grok-4.5","configurationId":"grok-4.5--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29895fdf00c54de0c01daedb","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43896251f67c4560c987eefb","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"3c5dd3212c5738aaab0975c9","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e717a8621ac7d5e7b83f0c5","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4ded8c8cf842220025c972d","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ee72461e2fd4c2d3a3b9148","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fc29bf0ad8e603f80d34abe","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"403fbffb3d4c130fe0a9f700","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e734f89143af4a8c68b167ab","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a5c886cc36cd42ce59e53418","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae37b0844362fac304b68324","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45f91d7a9b1de993e85a20ce","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"054c3ab32b6b51e1cacb8e66","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f104d2d68e7f44b6e2dccf41","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0999469725cecb5b4c543921","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45ba7bd68a9e01e37c632257","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c73b3845403c26be37e56d16","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"660f538129047bbe99b9ec11","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37e9c27bbdff0ce8078ce069","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1293bc7579eca6bbdab6135","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a7e2415031e29ef507c8a42","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddf1393612c433158b1f573c","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f40e905d9f3955576665619b","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57df6c8e4db31d53d9c4f418","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"efd5e16b51c0ef83d3a54291","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b0518cbb5edec145ab97b52","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3cea65021791dd8aedd62f2","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e5c4070f5e96c65a869fe26","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba76728c38b2f86ca1efc6ad","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c7395dffb6b3896502c73d5","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52618fd8fe81fb1041c98953","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d7228aef62f24943be9fa82","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"477c12bc73aea349f49ef6a6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e12185f9bee54b45c735edf2","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1b87ca46f07d08e805d4eb4","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4b86fdbf8e6fb1c74530ac5","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23325239d62a3b8f2f30a348","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf44cf9030f95307456d203b","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8286b65e9f1a497934f4c1a7","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b887a18f999764706e64138e","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2542d8a122e2175ba2a75e90","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"019b5793b4933474b0e3bd08","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2a59f42331436a81f65fe0e","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d21aded68f27a80ed79d5087","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01bb8807c7ea19d4b16cc08c","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba5cc0dfeff8c957916898ac","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e22a72d808c23e07638f47bf","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ef88b16c55a462f1fbcff3d","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ed711611c036fede0642751","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11ed8dc8a72cb1dd225c2d68","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1070933d65fc7da9c420831c","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fd9cc7f1f85cfa6226325da","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47f25590e81572edc7ae836e","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d11a73033247919db8e39a28","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f359942d0696f4ca296786b6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f9713ed90ebd9bd4534f929","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"146b01e3d6b3dd74cf939381","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67fb1e447bf3a84a1dc5dfca","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fc718ffaea1ef6d8907d374","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73835b49fe42ab80ec539285","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57abb41c70329a99f77535b3","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f494121ba1b32eb13d788d7e","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c80d116c611cdfdbf0794a0e","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cc5971c94263e7ed3b6e5aa","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"055e2840581f27e7013445b1","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d4862ebd4d7563b0b815232","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83e82d34b74f64e32fe5e562","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dee4caacc80397f92e821c17","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc046d614155011b4f32fd77","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b52e57716284a426b20e616","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbe2f8f3df27510117453b6d","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"725cf8be083eeea3761a0746","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed230f269f79598168400161","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"875ff8bc105e8938ba3ab493","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d88716d3f6022775ca0349b","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c62d7142b2955f3cccde331b","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7a35fd1ba65fa084a53bfff","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e3737c70846342ba1f20656","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"02867ce545a79d28fdca774c","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05c2f7fcf387f4cfcc374ac1","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42aa341468210b376e09693e","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c802eac5e2f5b0cc14a4b3d2","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9c96fd0e4307f0a3d58c1b2","modelId":"hy3","configurationId":"hy3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef559fa4c43c26694bf787aa","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c68b83e1d7b894a93142c739","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b9583430639861c86d85e2f","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81a106f485bd6b878caf732e","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8105b1407e966b7ace150043","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5b5e8eb7d2c919e6919413b","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ede59fb652037041ce1a1dd1","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa0d7ae753fb74157d138e17","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a9e1184bb651c83cf370ab6","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96069ed2be775a9053422ed9","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c695ae8e66e691e9c8f92ad","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"79511ae819bfc612c35a390d","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e6e605672e21f6d859de5904","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b0fcbd11b64f27c16e87a8d","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0695f8b0b910244d05c7a925","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9773ef1b60a79df50df32edc","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3c4359e7b3ebe3d66db5807","modelId":"hy3-preview","configurationId":"hy3-preview--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04ca7fd5e9a8ca87409e10ef","modelId":"hy3-preview","configurationId":"hy3-preview--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f87910c78684cc62168b7cb2","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f51ff08dab94ee68cc8a89f","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8804c0a4c3c7156385284ed","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf662cb6aa3124cc7b4764b8","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e33f42d3c44882cd56cbcd32","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce73d0e7d12c5a142ddb9708","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f4734c61a8de64e23bbc6f36","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfeb7e15ec86982ebaa1def8","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de7217aed61d8cea3b16e724","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3e0b62512d545bc3197e0e9","modelId":"k-exaone-2.0-750b-a37b","configurationId":"k-exaone-2.0-750b-a37b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"940370aaedaeafccbaa815dd","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"248628f25209685f2e813405","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f07384d9d52a7fe91a6f574","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d7800bef3152ab150d04958","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"368e01788a286f45ff312089","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6d4cdc6f942e0cd40356df3","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"811654dc8dea47a5dd74e14b","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9b96f3441cf2f7569161137","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcb923d99217ff28ee7af856","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c65d6e1561964eea7a2e608","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0437fefd7ee49ace79820857","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02cc8dd32ee8e6e63cc2728b","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d32f54031e59460e2a5ab5da","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5835712a4022a343643485e3","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be6b8730183dc85bad1c7223","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"856a3db006f6d9daa745ceac","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27271f132873252b7a8add85","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c644501691c892c4d6e6628","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e4b9809a8173b24a6492b4c","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"577a7a49fdb90fe94610bce7","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b5681c2b592c28e60853de1c","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2812d3d5ae36f9f251dd27e7","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8cc243a5909dbf9cbbc8d10a","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a47670629cd21ee68944b7f","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30dab2414c4fc919a207dfd0","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a942a894babe14e3d6e64da","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c4b5d8b71c63b017f4596ad","modelId":"k-exaone-236b-a23b","configurationId":"k-exaone-236b-a23b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04280450484769a36816bece","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3064ad7c61c665ff2687f71","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a44dc9f59be8bdd5015a312","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ade312ab0cd2fdc7519d21ca","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8700ad2ebedb691ad92507ec","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b5dee6f02a84bcfc1521def","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9194db1885dee526b2ac310a","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b58e12618e0788c63c62fc22","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39447a939e047b385f5d24fa","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6382bf13bada1216c5053be6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dc00c97fd0d8d4c30d4d3ae","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dad907f2acd631a78725d840","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4629bc4793dd88337221ab1","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8fef2fbfef8abe8215008b5","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e9c2097dfe8dc3f5066f5c8","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"072e7d1bc0df4bb01a626b04","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc4c747bf5bef726f47aab98","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b11893babf6d0cd6554405b3","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4cfd2aed78613e240f41314","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca4100db60d1e0bc35d98c00","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3f8fd7e249ce407ffe388a4c","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e12c88668886777dfadf2dc1","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38692f4ee2f974347e9157bc","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6dd5d4875b8e76f1b1d8dc49","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"828fe25b5f302f66f6fc6566","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d20434e4ad0abf951e6622b","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2457c88eb0a7fc7b83a3971","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e2e74eb92490b361bfd99bf","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7194781f9e8031ffdea93f56","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6584a32b8687b95ca2090b9c","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c67358f7711396086508ed59","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88387229e8cce0c4b453061b","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab60dcdf1b0dfcfeb47110b6","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f813371d1d4f13c92b30639","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83fe42da8f302edfdb023f08","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f4cc4e8c65e4c951ef26ba1","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"515915c2fb3373acf9c6b635","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e669e225a585809c8dd4fc9","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c5d34ebc7fc4b2f2c90ddfb","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a1a5b9db2d6520bd2afa2e7","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"057764867b81c8cbddb8e80c","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88eae31082764b6f63a7a0fd","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0a4a7295832157df8e2a492","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1f6e336dd0093408d3178e8c","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fda338029ff27052839f5dbc","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27d83ba961ef5fc71e6a27ca","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe217e24de0bc7151b14e323","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c29648182b4f7975f2c9f0aa","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"472f377c83d4e3dbb7ca25a7","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40ef2cb1ea3f3e136a7e3b3d","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d676b05a6bfdafc218ee928","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a767ce340fca6b1554b4c3f","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65086c25f5faf83ca3f34bf1","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00cd93b578a9e9a08358156b","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2ffd875fe769b7e1cd9e9a4","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c02cbafde90ba09e5f80c872","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2083991a4b33b7b3436d8b59","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7669a82ebf437fb83f3e011f","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86e5cbe5af3f685cbf639a80","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e94bffff1490839faca1bbf","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"005275d385d7aa97c24a77f8","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4186413bd41c45c9968ab3db","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4348a901c8e332d0564e708c","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce8125990f0e0f3ade0a2250","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"310c9ef33cf85bdcf514e515","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eeca09857f52f6fb22f8ffba","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8832707a4ee1b6f2ac875d97","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1681a5dc3c366fbdbc9d151b","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"84bd6e70c12d4a66c0e831d6","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4da2f0c4bd40c9a5325848b3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2382bd3b1567d49bc4ff23e","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d364b327127f7dd3cf8f19d3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80061346884d74fbb322cff2","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ed0111313e64d4c0400cc37","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2add98bb74de8a6d6249d272","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3cfd24aceb01fe71d063a78e","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4cb267f6327833c9fc9f39e9","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cdbbafc18468106417fd813f","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de943e45f8b7428cb8550a21","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"964db1dd2b9760b2f77a25ef","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"432c908a73875ef4d65e834e","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34300f035fc030273d01a271","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edc488017c622cc81eaa9f23","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f6edfd82bcc0576eb4a7ed5","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79c5c9a708ff0a48425e70cd","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df4665280a1fd6c8d394111a","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98a1e7f8c4f539a73b1ff25c","modelId":"kimi-k3","configurationId":"kimi-k3--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4f3231c817b7f55bb013735","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e82af3e6f3c2533aff0ab0d7","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50e28ce7104ff5613d31fa3a","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1187d83dfc7e0cf1c3cb0f1f","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a28e1bf360f6451fb459a28c","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fce6dfd0e81f07cb9544ac4d","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f77d8d40ab545d0bf411f78","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd3256ca33a1679f4f21fe4e","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c35ede4aac100ec236173460","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73b3ca32c6c854d2f898cfc4","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c774e01e9fd4a377f1ad3499","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e7fa6459cf119043d1b3938","modelId":"kimi-linear-48b-a3b-instruct","configurationId":"kimi-linear-48b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7131dec20596d2df6c1be3f2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f0df62b80b8c9fb83b0a81e","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"277826d88691ec9eb915047f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f649238deb9d8f1ed9c39912","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ccc3445c3156458123a9871","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e7d98632bdb7b424068a7d8","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"148f96724c8bc1918313cee2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5dd89b6fd04dc8216937a0a5","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdb350e52c16cc800f8fdb1a","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eb124052c0750dd77638fa8","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f3a8b308a46b3d8691e4eb2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f58575e3393fbefc53600c5f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81f793d6f2f88bd3529fa166","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"390f00a5572b8173cd2b52e2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c975ec825cce37abe4db74e","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"589703a977c33adb0239d69f","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d79254e334d06a2ca47d4ed","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f52fe8389f1bb8f3ded3aa92","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c90b87546d259a25837a5c2","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d988ff2eb76e6caf21e5e2a4","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f111753b1bee273c77e6e9e0","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dac65a9f62774845dbe0cc7","modelId":"labs-devstral-small-2512","configurationId":"labs-devstral-small-2512--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77dc3e409687fdc4123e7382","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faefecf4982a3c56261456c3","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31f2f561fab689277fa32daf","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cdf57f3e51751d8b1b206f3e","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45aff2671367df91ec82a00d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1c45db0f194569fedcfab7e","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8570e13fa3402d4a1cf0ce49","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48fc8cf05f6cf5be1916a16f","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b3e6d11f2c08cecf4bbdf7b","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0faf4ea29ec7471f2ddc2575","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0496ddc71cb780c146897871","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc29361336c4897fbe3e986d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39a00cb8aa14d4a8f1630392","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83ab2bc25f0bf5b24ca914e2","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29bc8ec0528066576e43067c","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9aa0ba713cbccb8900465da5","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eec6f4e726f2ac2843e4d31","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f6678979dffdce85c6baa1a4","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d6139083fe99c0d47d89705","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d78fc2575a1485830285d7e8","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dac821c6aa9136a83d875bda","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"604481ef9f14e63577ee5fd8","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"354eb159671e8738012a81fa","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edfcc29c0deb58a191bb162d","modelId":"llama-4-maverick","configurationId":"llama-4-maverick--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"555d23d461c05d28e5affaad","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4885145006b9e6c516d4941f","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7581f3a2422117f43b197e4b","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9353269ebd55ac03ed176358","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afc01f597c0079772acb9e3f","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d524b4da994ccf7a3136f46d","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ca6b818ad3095ba1fec0cf3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66c9c26050db4c0d8d41b4a8","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37634d64a31c01e3c55ac3eb","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab3e6dc6aee996774804be32","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b5c1e36e87698c0a87d0094","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7c19c636a0f224e332b9c1e","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebf48949184410fed6f20bb0","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2341b5314bd44225e9253b3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"342b5de48406cc12a0d640cc","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"825b3abf9640fc95590a58b5","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"29b51ff314d8015f16d8fd73","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e565fe11b60b81a60483f2","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ceeb86bffcbd0f7f1c1cb44","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7075f4c91bd36c49bbb5930","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe0a313c1be6171f1e933267","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7b21db2c6c9de33ab88deb3","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12f09ed4b289733513c29184","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f863116be3067c64dc4ded17","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96fb815ee59686aa6570879b","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27e70b3fb728057a74df17b6","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"537afc4af13852943398074a","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbfb37115a2ce93f137abe06","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ed549eecac4ede999a12daa","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37b4571eaeb976c6fe763a9d","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"482398fa7f264cd6c99cd143","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad7ae7e1f65c748e13353d8d","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00d28563b1af109ad8f1498d","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2ea0a245a0ae60d6211be17","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b059b84e2446c00ab8d4580f","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"07fa28163f5b1f3edc355eed","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40f63a5a594c4ddbf8bb6e60","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86a26110045ab8144e18668e","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2831b29b79d4466446b9ca7","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9230a89b29d00bd920b1d0e","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9557a6f4edfe4134aff16297","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"754e92a07c653f668b9fd678","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b75f74d8527b381f95e1cc00","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f110124805bb3a2e19625a9","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08ab00b7e42c1ffe38fae226","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7332d47df21579cbd347434c","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d912f20d1c509a3f0d54f0b2","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21bd6e25c91e8aaf59a9c346","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fac1628ad38a1ae32b1a569b","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42ee1aa5bdd7a63aa6435d27","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da019b5f437710abfa392ded","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e4257fe0cfd1b51a80412dd","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6035266fb17e74a06d13c9a","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f107c4759c0944a0c47cc731","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d21b8957d999afa9c21c52a4","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7a6909b11ed59de7be2f06c","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"582e8eaacbf3fc4faf540335","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f4ae3bfcadfaec9cecbf582","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0548c4d5205cb671c0f67853","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18f2737a5c5e1f7f70b602b1","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0737a6dbd590e665e154bd5","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18761c742f092bb12f9d5589","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c6d86385f0499ac90db9b10","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b30d2768f6110084619ea391","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4a73d3fd6138fe1e3815707","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0429ec3293c63221653ac24b","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf092d52c6f3a83f57432b09","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d675a347ba1cc300cdd50958","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0773db899cdffa4e1ded8ba6","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ad9dff856d49a94cb99de1f","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3920da93b773299bcb0edfce","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5baca63841da31c57e5ae037","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f366555ca241ca7c7571729f","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"136673bead80a3b356afdee4","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cb51c7248fc435c2871aebc","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1e63baef98defadff1101a6","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87b8554680365a774f346ece","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25c20a5aaee132cb4c3e9285","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f5425b9754a5e445a5236ede","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"644bce3e0d96665ff5259654","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b6fad8193ad71cc3e2e3c6b","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cc13fc1b52d73266be2282d","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dd928416fa90717a399e327","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6a30fe9e813cbabe7dcdc98","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bae7463f2643e0ed3fc2532b","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be9cfbf93f75099ff67dd311","modelId":"mimo-v2-flash","configurationId":"mimo-v2-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ffb2fbc8acdbb5fa868e907","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e83c247df799a06891d5c23","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d2e86088b5f8c7b172e4017","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"064950ae79afc2e1a558cfd4","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a6c3c90bb654755ab0227ad","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"037febc53053e2dcb9b47a7f","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dec96f1d4a54fa1a862e15bf","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d0236e6e49d8d8d28e01c73","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"832157a7f55c7b6cd246f105","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d587cd054a074e2950f881b","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dce9246667e76d78df4c7435","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"adb5cf425682f21a39d89ebd","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ad50ec8ea74deb9634c82d7","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d41a88e61beaa1a787af3bfb","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75e18d8f2290eb1f93e4b341","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e3e743e86bb15ebf4c91aa8","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b19ccc651ba74f8d9c9cfc8","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a2f61a9349f73f419db3844","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa8865db70c47bb7dfb128f9","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10408a3544658e1ddd5de105","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7d2bcfee55db5a2505b3634","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc1a2332e16a8d2dccb00939","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39ba4dba44c1102d67baf7a4","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff0c2d45c031c24afe7115b3","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0f93b30c77f797af5ca0bf9","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eba41a2659d0c3b4a213133b","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f4a0dd5975c36a9ccc0191a","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69737750e0f7b088fa8e9a5d","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e62c663d0e43ba6605976071","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f278af330e867f97be2f486","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eff5dc11f25d736892ffc61","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91caea072d8597c8ac5fb15b","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bbacd899f7789e32c381c4a","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb3f9696c12ea026ad23ee03","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ba4f52ff6dc1ac0a6b4e163","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93e1b5c3fa106e34f3235832","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a71198824bbba9c01c783584","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f20dd3ebb423e6ee03f6caee","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f8d44cda02c43ae2b8612813","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"21677ace23284fc1d6430259","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"520d70a578e2b68e229d64b4","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"180a2693d571d25cae080430","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e722cf4319818646ca6e10b5","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9161b5318bd7b88621cad180","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fc646e273a89ef9f25b73a4","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c637329ea6a800195133a96","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a75bc34d65079b1a2bf325fd","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2c532f29f3ce520c178e8f8","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"990ac08433bde368141db4a3","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5be0fb393415bc28fc914de1","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2a906d4e7d0bcb771c59190","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eab3ca6e668837d32dbf0f84","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6f50cbeea24cc50749a6588","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89fa7cef514475fe6cb85d96","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f59a822e8fe0497588720463","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b22165b4cb228728b966f75","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58c0e4b12f0557e3f0c56eb2","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97a83445db5e3087c342c4f8","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9da5239ef85d9ee0a317f40f","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b37840fcc4887b193a7da1b9","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dff041001a0b378a9dc8c1ff","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c83b7be0704c58f9f95b8b9","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30eccba22a3fc77326f6a727","modelId":"minicpm5-2b","configurationId":"minicpm5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a9234ac9a3f32d0ebc2abf0","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"788f2e240a00d67b9967bfe3","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c98715ed4f5b7aa5cacd5fb","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c47fefff4069984b5210ed42","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a456ca77982a503622aef14","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eec2171903ac55545a6ef3bb","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c03e16d248d044b91a74c874","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"500f48b1cccab1db90df44b5","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"763cf25103d998af4d1f28fc","modelId":"minimax-m1-40k","configurationId":"minimax-m1-40k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"baa673fd7f683726d8a5dda4","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d6db873825a7618efbd9abb","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e82a3c3e3750d84732cf515e","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"569994eadbf73e950041b1f9","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1551ef2a33f01b47020ef547","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35517fb9c2159a955b38a320","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76e122aa7a3557f5540aa180","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf49f69842e743085d3b29d4","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"707035a3df53472cb7e55178","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32652eb449f7c6cb3047e850","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7bd753242e76b19ea002e45b","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b570ef41663865b99bb5f67","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70b65a26ecb30426a99bbd11","modelId":"minimax-m1-80k","configurationId":"minimax-m1-80k--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15e173c41fc9f2886eb66b86","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b2a76acf855c3e0dc2d8d5b","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b058f286079d54d349739c0","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8ceb595a568197b84bb8dcf","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5a6567b3645829fc2a3454f","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e93f40e73566ac13cdce81f1","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46c99f54bc78b97ddd3fca48","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb9c2d9b8a2a2cbceac239dc","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dffa85148103a6fbf5866f2","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"511c96d55ac43f5883ed839a","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a8c566f58d9598384af26fad","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"294e3daadab33e631e294791","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20afbe1ed17985e55a8f213e","modelId":"minimax-m2","configurationId":"minimax-m2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"012ec764d84111d300f13dac","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"415c1a5b1c6ee36b839c2b75","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"706205dd32d2865bdad3c837","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f89ac3dfe86a385c12009ee9","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06bba500a66ed5571b158392","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bac805b323fcd165819d80b9","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63fcf0b40ce80d3935457cc3","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42d6364f9e1e5af2e60567ba","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"607ba4f5a3bc386b9243147d","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5300b173b3b63c3bb16dbd2","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"63491bdbc3d101722d1e08b6","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca2ec2abdaaeae0bda0f8bf1","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49baf6fa212628aa4d1c49eb","modelId":"minimax-m2.1","configurationId":"minimax-m2.1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdd30d2c9b426a753f20b9be","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1617509d3cbb2fd7d00a142","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ce6c4532cb91f00ecbfccda","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32c51132daff11e2ed08e2f7","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5ce79cceaa2a277376cead9","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e865e71141b2c84968e7539","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa77f8427f177890a4cbbdd7","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c0846c958c8a9391b1607a28","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d891e4daf4fb77148b30e881","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79f3006b495cd426a1b73144","modelId":"minimax-m2.5","configurationId":"minimax-m2.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"321b203cb1bcd8963cb0d3f1","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f29c7dafb579787394c73bb","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a2ca8def46f136850189c8d","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb3d618157a3f1a25a01a961","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26a788cce0f3865839b1a6a3","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"794fb014d2eb798e8b2998f4","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"567794a1ed9be3483b007022","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b89c3f9dc6e1bcc60f60a946","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0c7870f4e72d890a6e64bb4","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5472132d9679cc02891ff10","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee98703c061223da691631e2","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5993fc570c20cd787f9e13a","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b989c5a8f886f6da83a747a2","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e4e76f6bd4e0359ded238ed2","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c4cc58c4b043d4096f9904e6","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffed6553b2632c7198bffaf9","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"11881577f9e60c3849db70ae","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30e77a7107692ba54da4230b","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"787cc9d04ef43d1609bcd3bd","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8ae42068ed742b6900a2f63","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eee673418f1fbd3067f5fc74","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b190b8dbfc16399d02b9178","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca1e3276277c91cd2ba305b8","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2e74f20e737aa48dad4c020","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"248b861b8fed37090c1f8c0b","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f198b5e25c25ed5607f80d6","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"951a4a9311deecbd1ebfeba8","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"658dddbeb79c99f8170b45c6","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa7c570ef6685ffd1d23a3b8","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"256f9459d7bae8c1220d17aa","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8017c016e002a36286acd506","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e81c6a6abc1d601d7c3cc6e5","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1215dcb06b2956ad29b293d1","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b71623bbe996f6dabd9c34c8","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"309e3a0e336f395747e154e9","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fe2dbb70cb706ac86051368","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c8a6c5af1be278d8485103a7","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca3f36ad153ea45bc8abefbe","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfa5db0c68d02042c0e75111","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ec3544112e3145637229862","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28e428e681b3d40c5d5bd4b7","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2daf109e7eda8d8d1b90de72","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ceeed623352a3b0afbc75255","modelId":"minimax-m3","configurationId":"minimax-m3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fbe85f123d76d9d2586135f","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42349f526e6d0332bf405daf","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0c8321b9301b9f1798b9cfc","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0070a33608cc4dff46bd33ae","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"846b8d7e1064ca9b051085c7","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cda2910501e76db2d2736f56","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"24e35412de2028573d8e1019","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a3eca23d8d091c16f3cfd1c","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b2250ddf133129bcae06578","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"587f9758a421063bc87f1bd3","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e84b419d65d216d6cbfa5af","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fb5342b1e2722933a4b16a0","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f87c3cd084923ae9b2c7f4ce","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e5192b6eba15650e9b5f30b","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d6441354088c9ffdd6ef7a3","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8fea1cc0e155ab32e6483df1","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41e2bdc01aaf88a7862f9af3","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97bfb615237aae3a3c921741","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7b6b01c635f177b41f7ae72","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a19663d7c4239500d8bf6258","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c19f710109a638e2159d0164","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36a15daaabc73dc6d5977ead","modelId":"ministral-3-14b","configurationId":"ministral-3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0cdd6b1bc45df086f827bb9","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a944bda300cc996ed6055a5","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"377e02abab9d9b855350cd51","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"843d9648b3e5e036b0acb2be","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ed0c4631ac65f1f25e3f7ca","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb5b018f13832c2363fbacae","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06fa32a04d01bcf836b82456","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b537260129d057deead47b8d","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58e5a9f2cd204be72403efef","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1a4aca9ced7ddd73ed98e8c","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bf69fe4d67896af5c1f65c8","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bcb8f2f21bc3ebaf7da173c","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"283f4b4a8c76f509c6d422e7","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b5a9373617c66fda5b546f0","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"928da08d1319107c56189f07","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7a796ce9f7d23b28986ff5e8","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"719ae7fb0aa3a8f58828d8ad","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83db4f32b2b311f3f83c14d5","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9c4e289cdf58ffe5ffa14b4","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f010862ca6747cc6d8401ce","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77514ba2a733e772619ec66b","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7009edb8b996cc961ae08907","modelId":"ministral-3-3b","configurationId":"ministral-3-3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a43ec3849995da12ffe283e","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dd4f3c338791cdbb4285fe1","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6007b52d64bc356c474923d7","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"605bc0d7c72327162c223151","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a8ad5cdcd0e1929baa7929f2","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dea8abc42d6581d240a14318","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3275de864af51270520134c1","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7183c2052a20887069af7aa7","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41188e61e8f63338df1815bf","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6bf00c2a753272d88d86510","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05a6e30b5856ecc160d17ae0","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7c5d463ec1b8d046eeeffef","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e640a3de368a7ff58a8b9410","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faad5ca0d804e52efc4f202b","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75e22a9892b66c0e65dfd55d","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"edcff04c2243d437ad690a4d","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60d1bb31feedab5df58faad3","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43a3d3fe9aa6ddda6930bd0e","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d95912317d4bb5d72f9b21d","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5d3b3be768714fdf63001cf","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c7d5dd66f6c30384d34f3fd","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"345253b8f88be2712721eb6a","modelId":"ministral-3-8b","configurationId":"ministral-3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbe2eeeed1d775de800dcb31","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"348a6de2555440e02838cb61","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7a16d7e8dee63f9d55e9d63","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d63bb6149699d19daa535c35","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28e7e03881e741b0ee543153","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0ca3209dcb5204b311ef0d3","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"381cfdc71bbd8167f239652c","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13edbb09a0d6f48740227bf4","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05576a4ab91490da5b5f7e76","modelId":"mistral-large-2407","configurationId":"mistral-large-2407--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe50bbf18ffd82f1cdb29fa8","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2819c29ad8fdb7646a035be2","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bab6a467560df59ccde7382d","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42b857e698d4260f5223208e","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3437f9bc1e0ac1692f5c5bda","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a823311b9704e57063bf129","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ae2c33625f94d5842ef6f4c","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07149ebe5716925ff1f2d43b","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d565292efd326186f35512e8","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e982d1f0c2e679c26443a26c","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b95857dee1e294d54839285f","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"118e84cb8fab9c3a1fb4fa3b","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00443aa27838a4d61aa17081","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04902275b4289db5be2e8909","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe1a4682c062f12dbe7de410","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fac9bcbdc0f81c8e44b0ac55","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4eccbe09a60fef497d086249","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55e1c75933ec7e8373537acd","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a30580079b16a6231c310bb","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5906c4f5d64bad2845778a8","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f223a37edff3ec7188daa1f8","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bb842631418e84f512ae48a","modelId":"mistral-large-3","configurationId":"mistral-large-3--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8598ad2d6ffa40f68ee3112e","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd3eea1dc8c7bbb962e269d1","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dda57f94dfcd00bf84f043f2","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c500f8d1d9109499173dc22","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a627e4cf810decf4c58ca18","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32fb52a7ef7e80c24bf51218","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7ecce4ab23d7e0b1d66c046","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e80fbfd55ae35c4506737fb1","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77cc970d5bca332420c6f124","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"366f3b0107c0572f5d49886f","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98b8086ecdd729adb943befa","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ef1572ebbb7db6d1d5e0ea19","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"853fba57bc04b7caeed6606b","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54ae2b40694a6eddf2507953","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e4899ebbe0be74cfcc04447","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7008acf3eac0efcb0ed528e","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0060828c4561c3146a4d2fbe","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b3ef38d2b5d2fc9f19a3ed9","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab90f51570bba0df1c889314","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"640e064de235da086716563e","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"350c2c641e04fcb49688e650","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba265b790d9a002b971910c1","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a8b8a4a21798fb14026769d","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53fa70129bf83f83ab6219a3","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f9dfe82f4892e139fabc3f4","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dae076a0eacaa63ec8f192c9","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98f555a90b9ec68d099b3ccf","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"07b15db546d50bc3a15c79c9","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bc62ae3ef77f27ee9feb8c3","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02e0fffe433bd9bbb17718ce","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96d61f35ce89c5e402b475d3","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bcef63b769b65103b4ee5212","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ff2dfac5f466e44c25543b3","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b13b890114b7d4270d307654","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddec1a46d0c8daa3d68bf673","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30ef61afef7db6403f95ad14","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"567e2e221b95563a85e802ed","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3104fceb9c278740e37b41b3","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d258144824b33f3d3324f00a","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5df2fd6f09a89049a344da89","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bdde6072a786cea090d962b","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a4cfaa2b8cd211a9881e756","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1df964d67d6a114f0ae15fc","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"222ddda5db002b07344766ca","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e63c2ddb3ce5bb283ced808","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a46292af76538ed9cd457f74","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed8f320f4381500052c687c9","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"103f44c413960d3a1373d498","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df8c0054af3ea000e16148ed","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fe26eeb3eee7044147e39ad9","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46f40618c1d6eceefad11b5e","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8f431b7af5ced6f9c6ffda2","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"80753495b3c7881924eaa865","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"54f2e07eae2bee6eeebe5743","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1e4976e556451286cd3bdcf","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8696355798a7473fc208ccd1","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1ecc289157138b5f8e71437","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6da1b8d1b2167564bf428fb0","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53bc5a579aa23fead108267c","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e63a9f1379393c3cc66d6071","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"821ded825d6af49adc589ec6","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f90922973ea706908ad9cc65","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f66851101e2ef688b6c97a17","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c46cb1fb5b137f1522f36b9e","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39d3bdb6484f58e20f1c50fe","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"167f1a758c5db842ce1feca6","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68d2c1aeb87f2c629ac7672d","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b84c0ce3c4a5433cf625b30f","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"891301aed44b6f2989b8b04d","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d02db7530f0e9d255d63470","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34bd5ae77357e239d89ce014","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be0fd3096da38b78e3aef989","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"27cf85547226acfd3effbbb7","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a032bb7d27ac4f4a54dc043","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93d03cab54cbb7dfc0b435ab","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f595e0feb6f1773fe5a6fc61","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"340512192be278774e77e5da","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"832c778cd48cdca55f1c79c3","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e9568251c46a4d7f2d38ad5","modelId":"mistral-small-2506","configurationId":"mistral-small-2506--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9188eefd377f2e9c23d9a8b6","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1247fc165d860e12ba33ff29","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"213e91745b08c415820c541d","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"979d64a0eb75ed822e25c686","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f6658801d33d9c4bbf58519","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b914ad32f7c9e5f7d244d1d","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf81d819d89c15dd4fe6b89b","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f94ed73fa6de47d55b25077","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42a91169a22c22e7eed2f268","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6680a21e2f5f81331071ba82","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f6bef1401dd3c874f04eef8","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae1fa7961d49d684f2981dff","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8e3afa3aef8179b40e448f0","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1175374611f43823a69bb917","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5231791d1c29e104c93e1247","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f06380625c147eb9e14efb36","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"81f942ea40a39fe097e24d66","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2af0431ee57da42eb9cd13d5","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"50d33b56ae65630b7fd1e35d","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5bf3b46928f29139d0cfdd0e","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"301e793977c259094f7093c7","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2789b044f471f6a2756d4f1","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"211745cfecdb17b01d94607f","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70cdd67007153234faacd560","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"206a3af7332c726f2d612cb0","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e4e6f1b78b4531611aa9a8d","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6390ae449afa5ff6fecfd51","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2599f4ee8ffaec96bbf2b7aa","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7c7c53f6cba7efa0c09fcb8","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d28104ab178b34670aa619c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0c09f33ec395a21dfca2ae2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90f826dbdab369b8d36e712e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3db9f37231f6969e5af916c8","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6099fc5a6c629d98c4017a6a","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77cb0921403bb8eea32f98e2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"674c189b99daf251023acc62","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69c92bbf50967acf2ddea1e6","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1155696d61f97ace1c6685cb","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e482487bec614ab5161ed411","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d5c35ac642c8328a56d2cb1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51ae435e2accf7c476e8b700","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2ce1bb7d2f24ac399b6dd2e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa4da6d45fc3c9e23c5e0a1d","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fa6b5f2d5612bc7ff3ca112","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4db8c7b47a313e0e8d926986","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"5a5c40dc8bfa7420c7a73337","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f054375dfae2880d425145e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"545c640a1e97c757398c4c09","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77a5b3ed91707a9a184b6c15","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c29d3596152a94d0cb8ed7","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41b9ba5b3cc128b9746727fe","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"536612d6ef75df4fe26d8799","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b798a8a82c6bbbfe0f4543fe","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1598edcef4c4dc72d168db18","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"900af26141c1715a5245156e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ae131704ad1ec5583eb3702","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7778904266b2d0dafc5de1c3","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1ae73029fc1423754ddc150","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a4630ffdeb77234b578ed4c","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2150abdc6bed127d186f4fb9","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8ebf2449ddbb9b4d37ddf99","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1585a41209b88f2db63e82f8","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ce030d578bd60f3206f0e5d","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34a9bfb4a0aefff342dd0692","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bd6e35126e4ccd32c1da6ca","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8808b1d5e98602370d89e65","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68786c1903a88657f8d41e6f","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0c9af85c9501b1277d66dcc","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9b9ca830f4b083ec0d3a19a","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78635a322a120fc8164e338e","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96a191b13b418f3ffe2a1619","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ee44f567df8a617d3b7d8b2","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48d29f3f8db310a3a1875a50","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc6505e1b9377dac2b6b31d6","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"185633bd5d56a99bfbf2d82d","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33e20049c7e71a9ff1607422","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13797d3b6606164f2eb92c9c","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac6602798f51bcec5389b88e","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6366fd59f1a721ddd6257c9d","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"efb8e8efd155fca2f7ea6622","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8f618b1aaa8468a3b541214","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ee617d3b595752a50038d11","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"87a7cbeaeaa3a7635be20077","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"42853f38a1511935e572b88b","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38e66e19ced3d6f24c66d82a","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff504fc7288017403c059f79","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2056dd44c9f84527842f5e5b","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b339e4aa1d209e870cb52722","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"540c30f12f3af6a7b01f51b6","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0991fa8c74148bd87a523f4c","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05006804f6c11dff2fd76a84","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cd4630bb2973d2baeec9fbf","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29450743db5e9631e277eae8","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3df372e3699dbb72d0107949","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7794c31b12edebaf055cadae","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2093de0699953b27771c5c06","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb0cd457f42770f092325384","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8891413ad5cd82d8d171e25","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb4b24a95d446b8f38f48a4f","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be2d9f71ad2fc32c4685a3e8","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac0a28355ceae30603057943","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"141eae2f30ceb3d7b2bde165","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b46e094398644f85af26779b","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9b7eeb3faf1de8c8d016598","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"baf677e18985ef29d7904ae8","modelId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16","configurationId":"nemotron-3-nano-omni-30b-a3b-reasoning-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"330c9ea34b512489404a52c8","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"174357a19f43211840703ac1","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ab4998706916204907bddaf","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a53396aab5b755f3de4dee6","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33379178b6158f7ad04022e6","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"034db885626e3df3ca80c3b4","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ea2a53159a414f21eb5080f","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40e8b5d63690240383d7d403","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4cbe7ebbe159a64df52897d4","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"697a91584fa0dc97d799e81e","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51ea81ebfbd4d73fa92af147","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9896e0be3fe5460d4ed0ea51","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14ac5ca3a74e93eeb0b5d4ea","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d823713f33e043edf26a0f7","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d3fc36c3f92168bc3ee1be8e","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30b7b7ecf698984e25f319d1","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9c479a24e769b4d00767391","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25ac32575044be41804c364b","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3a5cd1a45f812308f2df5f7","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"857c5f249a729e596ef2a8e4","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d3e9fc29cd1b8b5326223cc8","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d732d01a1a91bbf216a9b322","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a17e10223ee1411771a3af5","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2dc7594e6af2cc119bbf07f","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a0f57a5757378689b26c0ef","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6942b61505042b6b4b415fa4","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"740ea85e8bb22f60c115f846","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4725e625f7ee2b6f05fc8d81","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04c131410c9c4622e4220c54","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"105df0aa2225f0561f8563cb","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8821961d17d37107b9cc0f93","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee3b105798bbfa2db43304ce","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc5659065cf79eedaaa45f2b","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"303aa21ce366cec63aaa88cc","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3bcc88ebddfd31d3a6afbaf9","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f396723527d1d08e73b2ade8","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faa9167f4773b2090ba9857d","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2d234d9d2b294ff915e8975","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"920d7dc6fe4b7a6441efce8b","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecfb7d6f27acde66bc3833ec","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cfb3235eb6f77d41014f6bc","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5cf104e5d3166bb18ea1ac1","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b34aa90172208f886564ae04","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"055179e91fb700bc3a6f59f6","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"691104d3d04d79d51b9cc955","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3b39cae17a85fc9da8893154","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e96872c29bb0036fc03afd9","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7592763efd7af6d017ddbac4","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d927cefa7d4ed8898286a1c","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afc36157fe035615d4c4dcfb","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"deb3f5b0ae380724472197f6","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36f02769540bd50aba5ce319","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8471a3b510bb8f93eb57bbf","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cae5947e36d58b255b600621","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72227cbdbda7131737c24853","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":"nvidia-nemotron-3-nano-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7085be742c2946fbbc31711","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fe21d4763c029be3e3150d3","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e2c2ed5165e11457bea1f14","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89190aafce97ca2ae081fd7a","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44a97e00847114128f35d524","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8faa35e0975d2edcb8c369dc","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a9e95986995916b5c3500760","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"74a2cfad0a1a8204637fd1e1","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13b5a452eb77a8d72c5aee9e","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"df2ed9679fa5e588c1a56afc","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc311965ffa7d6bd33acdb98","modelId":"nvidia-nemotron-3-nano-4b-bf16","configurationId":"nvidia-nemotron-3-nano-4b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1f86a0d6ed3aac7cfa5a9f0","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0d8ceb1e0ff885eb209f347","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22dcb321de77eebd96aca5cc","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e4aa8b40fd444337c32809b","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73ed6ba64bf2059d55d8be7e","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fce7835c797d7abb5d285155","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1cc0d1f19c8293a989d67698","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"000865eefbf0bb513f87e318","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e03108aae6e2496d2303c047","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f892e23b0db5ed5a425cd84f","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3227135ad004c9ae9505d2ba","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fb0bf7feab41fec0f6aa816b","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"310aba84e1b25c307bc27dbc","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c608bf4dd61434f7ad16f374","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d8569bb6a64e4b906358c8d9","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"deb1da1366abb23e09076986","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd4190abebbd6c254565fd40","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79e868c3529be4536f58ca91","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5803ab6f2e085b119e49725d","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f43288e9868e748c6d12ce8","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8565a66e2745e03531942d4","modelId":"nvidia-nemotron-3-super-120b-a12b-bf16","configurationId":"nvidia-nemotron-3-super-120b-a12b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1bbe5f5bd2168c15b29f2aa9","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21959688eb48ffff3fe84528","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af2766360679f1e677876ff9","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8328d0c67d5667e15aea1472","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb59004d5b0f5c683a653e25","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fa52eeea400c87c7dcac0f2","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83ebf96d953e9050e39fd2aa","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83dba6dbeba046f0f7d51cfa","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f70dadd761ac409f5b15d090","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ac3635f000bb105bf308376","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1606fde6708193b5680178c","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7132c5ebfae4d2f596ff0d23","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"685493fcb0926afc1fc64549","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7edad9d658746f2d63c7df37","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b950df4c5b583a803b26d5bb","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"328c4ebcaeafd433ae54b333","modelId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16","configurationId":"nvidia-nemotron-3.5-lightning-30b-a3b-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"feba9b16c718555279f17565","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f85bf97903a3efa738c3c09d","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c3995b50ac95fdbbe5a33a","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fccbf930a0cd235301fd9c30","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a002c70aa4a84b956eb1d7a4","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"947b304c37119f3e69f321e1","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91ab8f5ba0ad27187e93d250","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3864c283775f7f8392f8896","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c14b2fff22f134a398b1ba6","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39f85a1aa619cb4553d41337","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"959c553cf61235f930271918","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a93007cac0b3f2e36f76b61","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2bb6cd4194cb711be51eeefe","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a13875440065eb6af7f7070","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94684e452e66e092d884cf33","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdf6426314faa35ff1e8e3a9","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a091815e44913c3e3f3f3eb","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4d8805b551c7b4e396cd13e","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"794273354d8e571966e3c3cd","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"0afea5460705df6d4ceff65e","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"45875b87e9ce3fe9118e9ba9","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4aa3f76c32cc1abeba33a5cc","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a136762d0e55a8e533046dd3","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21db66dacfcddd9994ebaf85","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26ebef6866839033a02ce9af","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d03e56381bfc8647adb6de5f","modelId":"nvidia-nemotron-nano-12b-v2-vl-bf16","configurationId":"nvidia-nemotron-nano-12b-v2-vl-bf16--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce49848989035f224c0a9abe","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf3009a8f08e136dd031ca3e","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a318e72c061446677b7e820","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"097cde742534d8b869269f2c","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33327d7ad7ed35ac4c558fd3","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c31a0552226bd1dfa238efb5","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8701a0a6fca8a6f69f770e8e","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e197387edb4f2e7ff0aa63b0","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e44ddbffbe9cd84adbb0929","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ebb34a4287e8734ee82c77c","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8eda6116a8883034780a1873","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ec18de31c80adfa15c57028","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fee2a2c4e302f056e0af9649","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14b88287eaf9ef9d92720eb8","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"091ed4bb386bcf9a5a52226c","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5afa45ddf4b7f15df4d108f4","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c9b0458dabd028dcd7317d2","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"dd9503a5b07df03d5dd74bde","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"efdbda71278dabccbcce9c68","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21f2ccc498801a3c11aa79d5","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a617ac3d85cbb542b061ea8e","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9acb65ceba2998896351b43","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2784590b707e50b89ab8f946","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebdd1011cfb7d6007184a931","modelId":"nvidia-nemotron-nano-9b-v2","configurationId":"nvidia-nemotron-nano-9b-v2--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d43df74ab94b7ff5b19c51f5","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4b61d84c417f9d0cdad5d5d","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dff08073706a671e10ffd04f","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c51ba771a259cf9fda6b04e1","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a99adc9667d02b7495975f92","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95eccd5b098daf7dce5b90a0","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7edb809ee87346c119299a36","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d68b4dbd3f5e0035224e7c76","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe3b117476be77296f685c2b","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b253a77469ef4f301baed94b","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef4ce5d877f52434b3beb1fc","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b71a59f4c3b1e0589de4a70","modelId":"o1","configurationId":"o1--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"370cf31a2407efae21be583a","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f466d671d2eef974ea005b2b","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75946bb5200d898db3265c34","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f70a218b1f6a8fc2114d48e","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e92ab090534be36366d3ec","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd4f93e7f4f1a45735079084","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30ee4a241c6f54cb0ca85362","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"019b987204bf0a37c545c13c","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99c65e088b8907331a5c2554","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6f4e33c7c2b7b4ca2e20e28","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"350484fd270e9192ba0525d4","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7cf10f4304e8d80bbcf66d39","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a1204eb9a9a16442ef47947","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"001226139bfffd4e21b870af","modelId":"o3","configurationId":"o3--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7e49807f538aef93f8c591f","modelId":"o3","configurationId":"o3--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4c43e9a8ca07f6c7e48de89","modelId":"o3","configurationId":"o3--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44ec3c5d0da4e3f62912c05f","modelId":"o3","configurationId":"o3--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de6fe228603e9238b659ea7d","modelId":"o3","configurationId":"o3--effort-high","sourceUrl":"https://livecodebench.github.io/performances_generation.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01a156003da2d47b7c81895a","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e677a3227e6bacc4a0e9a40","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d80aa65c5a1e66963cd6340","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4250ae81639657e77c36aaf","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5b3e40b7466bcdf13bd150c","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2841993d80a9999de9f6ee7f","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"42f4c2c9076d696f07dc6783","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"811d9c240ea23b82e185a589","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a7f79808eefcb014ec3f0be","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e161b5a9b646a096149330a7","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a9234b7c969c2c1abb86d31","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d65babdfac67d23efa92d48","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"318e34735b7b00c4d11a9a09","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"745e69c691f9b694b7c9353f","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b03c9376d3f09d3c80e63a54","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00d8df98308d9c695c029966","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e266c73c6ec784e58caaf44a","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db1badd09c0ec2742a1bda68","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8d5a35515e13598e754d8782","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdf870defc76ce206427d252","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9939fced55db051e5e0be0c6","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19eb94c3b4a5578e45bc7056","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5d59a1795d09f33dd6e3fee","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14aa700efe22f08ce992bfb4","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4da7c16ca683432d6e1cd5ba","modelId":"o3-mini","configurationId":"o3-mini--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c0182a63d8db78a905b0380","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06585d01215ca9d0bce0d3f5","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2c3b8b661de8636e2ceca83","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78ba06f11057b6bec4542c33","modelId":"o3-mini","configurationId":"o3-mini--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e76fe3fd7aff227cd9253390","modelId":"o3-mini","configurationId":"o3-mini--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd98f3407d228d7b34d15a3b","modelId":"o3-pro","configurationId":"o3-pro--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"549730e49987d6154a62d579","modelId":"o3-pro","configurationId":"o3-pro--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"342bab39cacc26dd8a82dd79","modelId":"o3-pro","configurationId":"o3-pro--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5bae5777f5b932bda30b31f","modelId":"o3-pro","configurationId":"o3-pro--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db9246e68971e76beeba26d2","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcb3ed7e008063d590801660","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"efe3ee5e510a1f9d9309239d","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0129f1e1a13aeb775a53a55c","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77b640461cfce8756b234629","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48b638db61a973babc2ae6b7","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2012c98b7c0b198f7fca6c55","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c31fb5e1455b4c4ab80556f","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2116de3638350f5f74312fb0","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed9b2508389eebf3c69deacf","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed11d2a6911024075e30eda3","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5d14e1f9efd0488dbcec0d2f","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"957e1e7000b2a0aa69fbb665","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e42ac7bd5a7610c724d7104","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e74df9fbfd59b581eb76ffa2","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a03ef69f5f0bf9f19a64b6c1","modelId":"o4-mini","configurationId":"o4-mini--effort-low","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"904517858e9c5b0473e556b3","modelId":"o4-mini","configurationId":"o4-mini--effort-medium","sourceUrl":"https://arcprize.org/media/data/leaderboard/v2.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee9d1ca8d2407e02d504ac6b","modelId":"o4-mini","configurationId":"o4-mini--effort-high","sourceUrl":"https://livecodebench.github.io/performances_generation.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c16742f35a5ca0f1da2cd5d9","modelId":"o4-mini","configurationId":"o4-mini--effort-low","sourceUrl":"https://livecodebench.github.io/performances_generation.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbd3c0c14e4d3b745599aed7","modelId":"o4-mini","configurationId":"o4-mini--effort-medium","sourceUrl":"https://livecodebench.github.io/performances_generation.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77b72d8bb8f6229c4935bd1d","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7913c6e2413a96102bbbf1fe","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"834342d113eaeacdec6c68c2","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c45844e7e930f528caf96218","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92a3672a2fcdd9eae2cfe4c8","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70dd1ef196043632b7c37a03","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2fa14f24036f5ed63850347","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1300da3198b950627b64868","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e87a2d3e2af83fbba103ecc7","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4d5188cfd91b9b6ddb85ec5","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"aff564f7946147cb44a15141","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68eef27c9393c82acd930591","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0d8027ad98e252733a703ca","modelId":"phi-4","configurationId":"phi-4--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"516823481eb1495f3fb3c99c","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"601f36f2404c745b7bc714e7","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab4cc6c2aa36c216f8568f92","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2627d43541d47421d317811","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5438058f26b61c57fa0f9afc","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d6bf305ef56bc9d7d14e527","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1959c33d56b49b87d365a30","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cad43079054208b6d9bfa144","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b9dfce1492ec029021a05b9e","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8aa58d9564291e79f8c7d5aa","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ec4c88a12f8e0d0998cc68b9","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"70e69f2115f632139a54d1c0","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c13bc87ea7fbb9edee07b054","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"64dbb96bbf3ee55255c6a592","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53b7d3d06cae0753bfaa177b","modelId":"phi-4-mini-instruct","configurationId":"phi-4-mini-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be0d629d53023aac889d0050","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e56b10f487f5015dd377634","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c00cc4d194123d3e4240049","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b113a9a9d3b6af3846f819a","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88f07e63051ff123b88335b7","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"10aaef8ddcae5e8c1c02ab70","modelId":"phi-4-multimodal-instruct","configurationId":"phi-4-multimodal-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"95791dc88f64b23b16d4019b","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"528da2e0681c24dea179b207","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f3e5bc4908fb6b8e1788d00","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52b14f5c6812c2e2fb14b98f","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd0a839399405ae15ba9139d","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a7f996917775f67ba770d2f","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d563ff92ab0b6ba9cff379b5","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb614b4b073a151ea844b8a5","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3c6fe94a03132a6f2f3db5f","modelId":"pixtral-large-2411","configurationId":"pixtral-large-2411--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79ac39c316bced8f0d7c2cb9","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57435d7deb3cdff15c2a3a8b","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c09e4e33bd17b0d5c324b60","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79ab32eaa9b651d3342a99ff","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c03ba8504722b0e530cc22b0","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"074c885729617e4a79bc8333","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d96d19fdb68c550c1214c0cc","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9d1d3caf6ce2b25dfbb864f","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15fa3a1b83adaff4e8f742dc","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d70d4d6859dba0c566beeb24","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58633d857fd008646f1cc6eb","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"89c264b8b197f4d77c71a2c6","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d3819ebea45c3c63a94d80f","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ed822dd05e4a59aae023d79","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b38697af9ba8ab047240c165","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"401aa39daad5e621da7b61ae","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdf7a8eca4003c72a2a46e18","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e07d9dd5005dfa0df02827b8","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6f7a5f79bbca4f2a67412d9","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8d0f96fa682deeb06e51740","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecde6783ec0d47e1bf98a46a","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b338841b63f737ffb17ed7e0","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"902940590320d8648dca2883","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f04fd1b531b951f250617193","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d1a9de8bbd963f3c5f6bf0d","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90e7d8ad72bd6576a81f42eb","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6518f5de94545adfe1985361","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"230731584c91a733879819a5","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6bbd08d320ee6b9dfd559fd","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55a17c98e627b355cd8b17da","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c6f9d11fcb4e03bd1b8a9a7","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20398efbf3c87c56cf33356f","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e582fa9a22661b9a0279e7a","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a370fde9d0ef2c43e306e7f1","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9fa5e0ad520b1ed9244765c2","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"607485fd1a1b0b822e375d3e","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7427f5729e938d7772017aa2","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b50bf9a788cc1febbbb1372a","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"692d1a2005d56e466b6dc93b","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aaf8eb92ad1848d2c667404a","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62476ba134bc76ca975eaf3c","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cc385d16cc1b35f2bcc4b90","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d2875437a15ced44a23ebcc","modelId":"qwen3-0.6b","configurationId":"qwen3-0.6b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0903b0785448402e3ee7b14","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1708d3fe7d21b8dc9194f8c4","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b2f14005445f5c569f1b1ce","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6081c63272fd15a08492c8db","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd4f239d936984cd38e77d8c","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee141c0067f8a08b74460ce2","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d1130f0b8f0226c88c62a1e","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f5f56834853b82731dea301","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5605706863518eb467d8a1b5","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8661b817f3af2404661a7e11","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5392dc4a9cc4b181f5b920c6","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1f40f1a67da3871ed644d2c","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"88058002752a6680711097c0","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6d45937d0d15bb4efa4365c","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a87339e0e9504b36ddb6bded","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50e7de8cdf0b7ec58dc21ada","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2145165c64ee568b19fe04a","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30e97a4e868b3d4ca68973be","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c412281a2b4367841d9fc1eb","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"460ee126fa722ac88fa60ce9","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"33f988c4c7a2096720a36eb5","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"82004cae536a8489b3f16bc2","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b545a2bd1e66b5dcad42acc3","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5782bd6d71560bdef6e6bbf0","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7bac8d61f92b0d58d694350","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7a6bdbbd5bb164a640d8cff1","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8631ae15df88ea157c982d73","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c200f8f5974cced91b94c3a7","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7823070fce74572c14440227","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3309e13df52fd1fabb19ab86","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"360c4369d2880bd3f33bf48d","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93da3ff3c5d7b1bff4c94ecb","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b2a114e7d0f60358dc89582","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bafcc8253fd4f179cd575bd","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22963f5bec954903994c9380","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"28e79ab1e630d682cf1391f6","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19b97b3a583459ff567123aa","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76b7eda2e03b9fb81d741935","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e62d0d2d9690c57703bf9f13","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fff6cdef363e6e229f008d13","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29501eeeebecd801dc346bab","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c6cac11306b7bc7f25813687","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9662b1cbc42cb80f1003cb1","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a6b0f3481ccc7e6d3e485b4","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d182d825eeccc745161b2067","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f92bf192d6248fe1b4e85427","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41d90092001ad63411e08f39","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30b278ac1c8c5464b1a1def2","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1ac22cc2380f41a90cbfc68","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f9876ccbd46960970f8661c0","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fffa4d922bb3d13549db3532","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6c21071980d804a1d67a0c8c","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea5ca53936049bd3f26c2477","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a32d713ac22ff457128d16eb","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05dcd8e868462f666322c651","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cf6758bbc1a1642912303d1","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f1d3dd2bf9d082e2778499a","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57f6dbe626d153af997eff0b","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ce50946464c3e30979c50bf","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eee7a8e12e744a002d4d6b4","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b5bf342de1a14490bce8c1a","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38375a3f39d92c5ad2706da2","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89305b27a86a0ce63a7e4eb8","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56d76f45737dce7a63a667ff","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"14f9f716a2a328d472ca21e0","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca93a3563807fd6a9ff50462","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e658e6c4bd06b5c59d0cdf8b","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca162e62aabc277e7d0ea215","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c361e8d72495bb5786b6cf90","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fb4c5a3c327a127ebc0ebc9","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf462f7e796944884abc14f1","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"839df9c48331bc134df3997d","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b0696a5cc76427177558d015","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab7dc27978537cbe461952da","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87125f56c97261ce790af1db","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a5ec4ea7bfb7ef8568384a61","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43cf687682a8eb0a638a3c45","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe9af6c837da0b3d9cf4a593","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"227ee0acf1c6c720d1350ecf","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8b44554d63181fae5555e52","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c34a248fd9868cde08c5ce20","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"69f9f3d7ea24015d72835b85","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"860f80781817eb047ddb5ff5","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0326ce95ca6eb85d64c1291b","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ce73290decba9279d8cafa3","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b923b18effc8abc789063841","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a1ddf3972ddca61d88d99d3","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d77b602a8a35d0a4a648dd95","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67ad2e1e4f3abbfc96fd72d0","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d7d03c896b07879689bc033","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1622a07edd5343e87803e57a","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d64fc0c5fd25c6f3f2839386","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02dd73192a322d1d0f8c6c1d","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1461f99f24065e4929bc6f5","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d34742eb5d738ba73157d238","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8399cdab1190c86e4e1550d","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f17f8f143ab442b52c0ca93","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c7456329253fb027797f510f","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70d0cd044393c24c57a06146","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b42443b66c734d0f2d7c944","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":"qwen3-235b-a22b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6d1a4f33583a5e4cf8e7a06b","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ecc084f491a729e9b7a74c9","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a5ed8eea3db9089c7dbc5ff","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb8fa7dd28b53b28a7ead28e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1990682da03247d86412c31","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a399e93d52acd969298026c","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16c9acfa6c591aba2ddf7c2f","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0558174eaf2fcd898108553e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72ec400df622abf0993c0b92","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07bdaa927df321564f2c1d84","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44d7a6991cc91d58c55ff9a6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cabc23b6d1570087cdf40e87","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67ad8c31109848b751082bc1","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f706dbdb38fdc0c25ef1282","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"963e940e7972f41eb041f884","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e126146d0f6fd5e675ea5077","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"257a65544bb4192d4e6972b6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e51a19f3141204938b7e3a3c","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2acb2f76d344a5a0435308de","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c1071699ff2079d8fdebc1b","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2f2ba29d0427aaad4c86e0c6","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2209fa80f3ef69cff5c6933e","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e6dd137fbbb57f48edbb48f","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"192afae643d6adf6c2b4c358","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70efb52fb8f76af5b6b52a6e","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdf5b9f8d714afb06ad143b4","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae488d8b4035636896c7c04b","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4381440088e84230d7416ca0","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eba4f44d37ec442eae1c0b6","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fef3ec80ad899c411e920db","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eeeec44dbdcbcd1fec5088ff","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d7d919efd90d5c6c7d2d155","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebd843a2940c41c39943f6fc","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dca37a8019d4b22d0d4f863a","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"660d0d9d49749f2371fee225","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c9b11fa4972aba196c050ec","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85fa93b4a127efea07f4ee97","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faac05e386302fdce6abc902","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a744d10897af345ffbf1637e","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bafe260a148c38a7ada467f2","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be9c4f9166e8a88c6c27dc71","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"48c5c21ee84158570d29b986","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"811a45a5a0d28bd953acd4a1","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5dec5d5bb04db837fefe24f","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a9de0ffeb600f9f6945e64b7","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad5665745ea3639e88c0f813","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af5c211c7fbd820d3a9078a1","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8a719f06b81ca947a876e5a9","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e6194a0353b1168809b0b254","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77ce916db696117abf426908","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"727953477da1c7bfd3dddf55","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbff8e891ca3ce9fb273e4e0","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d5e8811e66cf17e31e93e44","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdacb847dded341069a86e17","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9119e88a171b62aff4d1d30f","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"04f2969c4b63ad25ed889181","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2d8294eaf80d456436b1a75","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4251c0820afca56a08be5811","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62854b9cc7a0052762824704","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"de8c589cdba00a5c5afca9c9","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"587a06eec8c56d9a9b6aedb0","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8383df5670c6809c2eef77c","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3550590d824ebcef07ed8d6e","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6db70276e35943ca61c814e","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2321ae88075ead248809d8e1","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f1f0c80edae6f3a634beda2","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"370b5b9bebce490bc7802be4","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4d7a3feb92d122e78ebcd62","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2591a46db7e7e1ce9c5d203","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82ee76c486480d1331cac8a7","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"694a6ae93a990d591913241b","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ece9316f357641df5610882","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4e0fece0be006e5564b5eea","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48efe4f78a59711b33996eb4","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1bfc9cea4d180f9ec285a7ad","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d309ffb9a64b671bdd150c8c","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a0c4514c75c30f131fadd06c","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97fe37c7f9321a9afbce9419","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2143491abf4fa705ee0ff478","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb94bdb3a73cbd6888dd9b81","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7da6e30fc453a9160b7fc090","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da91fae6c59400b775705b5c","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52eff8771abcc56b8e2ca851","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40395342c9fca4b8ab6ec126","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50bc16029e3f89646a8db5d5","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"236503dc2ece70ff04cb2662","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"467c0d1a8d9fbd1da7d58c18","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc2bbac9236f9e228cd498ce","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f14f0ee78f85450317855ae0","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32e698f91999aa66dbf0d33b","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2881dc70ef3c09ffe8b7aaf6","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d8b0c8bfd82a870c0e8e9fe","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef0a55af7e9bca42a6969898","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"09c94da7f63cc4f35fcaa8ef","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48c85cef75aca509424f96d8","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"532667768a038808e1c06a66","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc30d25c84e9b4477b649acc","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe95c5c72ff58ffbfe5f6823","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c013a49962eaeffd601049e4","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"366e308a05ab543e85742e62","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba8a236b0d865aa499356fe1","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b986f53a1a49d882b80d396","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"29346831ae44b3d310de7180","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"239624201d84931ac65ea002","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"864945a3e7a9e02b314d1f06","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7986bc6ac6e65fd08a7872d5","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f069f41ce299bb5371886aa","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49a11e10c53668cb78a23aff","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66b3f17222441498b28217a6","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0473d12b293f64f0a0d6891e","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"600f05c1a0f31fa75134db9e","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"051c088ca8dff8e607638eba","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3fb8f25022ef3577afaf7e10","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37ddd191ba8a7706c22ede89","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65f0ddfbfd712968af3079af","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91155b95de942a7455e43323","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6a3477ae7039d94212e11fec","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"603076858d0e2948a85c123d","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87904f931dc2ffb73802afcf","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eda1f86bc4fd88090113e80","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0bb53c1cf9d782756209f3d","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7989a07f2d2c06d46c14671","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4374f7d2c16022ba21b76a9","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"629a36632de288da7f71fb5d","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f46c6d830769a6c4e5c99df7","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32c6def6785bf325dc4f87ed","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b8304749e7352f154e474794","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15a1c599f7692208475bf7ec","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56d2377da4fb0704eb1ac2d3","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa65e4aae5f09070d5102301","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eb087a7abc8d597044257ee","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d43e7f62daa161d728080e2","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c10be8c55f9429f748beb6b9","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b204881e5210ee72604f1d6","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78d1af6fd684f7bf363b664e","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49c265837d27d2d2bf8e4efd","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cd9a6a9b734e8a05a1d62106","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be24a4e27b32bad48a266dab","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"37afc57a11a68563f8f2ef72","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96ebe1b6fbf2e0d343e3a601","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5545ac10fac2b93cda828d1","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73326f7b5805389fbe29ad4d","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e11def07dfa9e995c73e1bac","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"15a62e80d61f958a5049ebf7","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8942418d355ebf98c867b34b","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db6ac46ae5700dbe44444c52","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b9744f8d20c3175afe7b407","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3a3f857a9b6c30c32f5e781","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"fa0a36c238b7bcee88d55771","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cd71124c6978766c9d6d511","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6478507eb9c1b358f3b4a3c","modelId":"qwen3-4b-thinking-2507","configurationId":"qwen3-4b-thinking-2507--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6aec1ffa155c03633da8ddbc","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"77e57e37efff0800a4ac52e2","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ee738972827562727062ab4","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"810d82044b4b72e1d77b2229","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fff734316823fab5da7d9839","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"470d367830b121eff8410527","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"553d1656777ad9dd0b5fbd2e","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a71931fca8ea24e37311ccff","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebca0d32e1876250f09920a9","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d0248ab020e41ba3ca08e1c","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9607a0d57cad509ef28ad301","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f121713f6dd60580e421928","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f444a8a8c61adea63cb4e058","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07a8885a5754031517a535e8","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf779bb3e13563b175f0959e","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0a1791dc8cd498b60abbce8","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1b9be1ec2a8c4aba2017b1b","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c4376001c7ea7ed1c0c72d6","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3598c03b7e5214c93e9c72ca","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c030d0371f9e059436a36972","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbb6369c5b97ed3eb6f04b90","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3085e36820ee68bd4a102b22","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d82a974e643a8d0e079950e","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ab22b03c0bef227a91b34986","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"f261ae29c7c086c8c29aff0b","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5702032aa67edf32f4667d95","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f14ac71d6c0d2283748b9d25","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2a1189537534941d9d8a6cf","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2753d2f3b8d5e1cdf181a56","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"733f2508843a636f98ba5701","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e64c7478502eac8baee26e39","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25b23d6d1d47b76b25448251","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90aa8fa4b05c718ddfd307c8","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c8bf720b7385ebdeb270f69","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a5e53cf2346ee45d0c582775","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8639ec30f3a041013cccdecc","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdd2d19f3143bc2b076e5415","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2ae61a29f11e72de77a36c9d","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eec049bcf666ad4a78e12134","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c80de3cac3aa9982c6fbe1a","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe3e00ef3fb3a6b9d569105e","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2fb790d8ab3d3930b2000933","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b62d586150de22843349748","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"26f52aa824dc36a26b030308","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9b267017f4daf531a326f8af","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76caa5bcdaa62e0399c1cbd7","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"282d2dd5d0f2b0feec3a9bbb","modelId":"qwen3-coder-30b-a3b-instruct","configurationId":"qwen3-coder-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ece51f27224d12114df7c4a","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0de3521cedd608973feca387","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7bb1715f0274733e3390c12","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cfa076638384c0501b932837","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ce4d095b186c8dbb2109774","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9ccf3989be626311c527af4","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c826b7e819def2b96de0b1c1","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69c8dc453e9cd5a94a8bdbac","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/math-500","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c490527d77a38dba93e58b40","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b2034bca18006f3172a087a","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"13d73650a0ce5aadc74813ae","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c7d9e8d1215597f71eb1e20","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cef9782dc0d168133b8a20ff","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":"qwen3-coder-480b-a35b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d469c05a1795dc81f7c98893","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4023e37a7772337e40c94a66","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0813bddfc181d56d1e8b8a5","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b74549c8fd9f209dea3e7bc5","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f590ce5d0d46d0cce0006d8e","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"106d757c07493e32172fb22f","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7b3a1fbc5ff2942f395c61f","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5eee82bc106b4fb51416f3e","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1806e532fa8659866761b296","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fdb286556f7a859f007abc5","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6fb3b7bf91c4f655e0f9e5f6","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9dd3ea750813737b771bb546","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e73b78f68f384f26a35c1f23","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70885ee7997cb7f5413f9175","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bb4142bd1725e8cb824ec398","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c252534d9d58d5a8dc603c1","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0851b3e49721b62cf6fdcad2","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"48676396dd68515d0e746b37","modelId":"qwen3-coder-next","configurationId":"qwen3-coder-next--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"379f3e03c5a75e45500083ec","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"d0ee451e3d70f7acbd7160ad","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"41701e2d8384671332f59b80","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"873b3fc87079fb7d99451bb6","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"315935ae2fb0b8d9506630ce","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"618ec7df142e33dee8639477","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"4d4b86792ad7edf434ee2ac5","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ab71f78c9db94e51405eddb","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2fdb1293b42e7e45cbd183b","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18a603f0cb554eff82286b14","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"380908933be5913820054566","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"879326ff889e832b42641611","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c69c24d53e30040f4c162f6f","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"3659c33ae93ad5a386c4057d","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"eb581aed1e808fa587fdb05b","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"08a91161451f412505e30032","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2b16892f62e2b462f8dead01","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"520b99ee426c18dd7f263df5","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c010e27462d3d72e8f96c438","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4bbb94159adbed7fb9c2fd95","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"e392854706b6be7d554ebf84","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"12c287fe88bcaa562fa38631","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"8e7b03c9d5c0d8dea1a9ebd9","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"2bdf79ef92caebbcd2a7db59","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"c942c318ad1475140efa1310","modelId":"qwen3-max","configurationId":"qwen3-max--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"excluded","reason":"Conflicting values for this configuration in the same evaluation"},{"id":"bb0a0f706bcfacfc8bfbcb0b","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39324bf234452599e097140c","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0bebebb1c0d3d8c78f37ab1f","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6d6b7200e8855577137d44b","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3f87d78cfb9be15308174cc","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2dec37e2c4f881a390992157","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7902cc4d3470d6a216813a4e","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02254150ed5397242e653e1c","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2263e85fdc24b011ab25738f","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c5b9a37885e2ba0e8b3361a4","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ba187ae862e408223ddd229","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"32276506d0d1e55800cb28e1","modelId":"qwen3-next-80b-a3b-instruct","configurationId":"qwen3-next-80b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d89e459916593927b09df0d","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f45310222eab628315727a3","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7cd92797a65aa1b3546d034a","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8df0294fd65c5979676259e0","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b85018d49d57cf2e8050c2ad","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9c43e3dd521102061d12b83c","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a632fb2495b87e7d0e9989e0","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fd93cc59b58680c7cd8160d","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8725748b17d9c049319bc806","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"739cc3ae08400828dd7e34ad","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e71a0ae62a979c3a73340e0","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"52855ab9f5e4787364e91f02","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d68334084e3a4fcd1a96926","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cde368032b5e946e8016b135","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bdb9faad99b2ad6caa3e59e","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"53f02abbe152e698259000de","modelId":"qwen3-next-80b-a3b-thinking","configurationId":"qwen3-next-80b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66e1a70cfbb06ba377a24906","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e1994fe220192d4f648bc00","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cb01da84527cd626a88d69a5","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"207e511763a5de76dd47573d","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a52027c783bbeb79f5ee0053","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2f6bbcba92a230b64695fba","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a95606570c645f6594bdd527","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edacfa4d7f499e0fbdf77f56","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23cb074182ab575c2d998986","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96e0b755ad70d1c1e0ae9354","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c67b438ddcafcd62ab222e69","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44fe6f288cb432b5362daa11","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da85a712a2a928f8a0093ebe","modelId":"qwen3-omni-30b-a3b-instruct","configurationId":"qwen3-omni-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f78f496de1e6c875cbbb78f7","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffe8f1f73796df547f259cd9","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"debf36b3ff3a8afa229b244f","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25e5c20c242f402a50e10b5c","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d83fa0fcf5570fd9e34ce182","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8768eb7e5b3055cae4949a8c","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b8146bfa8634abeab45959f","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94e4190c5036843765fa2396","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e3a87793c1033e86adf1f22","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1648013dead8d8b7e3ccc5b7","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d60c61b3b2041a2b188d80da","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f872fe1f414e47d1ea0273fc","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a131db2197b9e48ad031e4c0","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":"qwen3-vl-235b-a22b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c9c62a5f652b687c1908560","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce2d0da396f1bad697146064","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bec8c4c730c568a6b901187","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b21bb8a42d86dea2ee62b68","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c8b57cbe46a5a65b9861cf57","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8edf38eeca7d9796ddf0e53e","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e5b735a0b87bf634aa6456a","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f977ec4daaaca0a87c90c23a","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d168904477178b1120a9f97","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d248649872ed9e5e376ce5b7","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f52b0d13a697ef0d9e0d6b8","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6bf0592349468ca8091cc9a","modelId":"qwen3-vl-30b-a3b-instruct","configurationId":"qwen3-vl-30b-a3b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4c021f4566a015478f0f03d","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d52a0dfa14f73e70c99eece0","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2cde6a74401fadb647be7203","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c5ba2f971eba83fe4e4cd779","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"652d921806364ca7568196c2","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f954718896851a2f87b497bd","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e26f300586ddb51b29981834","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a35028ffd4c5b0bd78f6503","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc8e92ab40faf29f9b4d4907","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"d6a9a7a1d698ec0f45749b16","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbcfcfc5a57e209927c93a91","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76bffec8df092259b0e2775e","modelId":"qwen3-vl-30b-a3b-thinking","configurationId":"qwen3-vl-30b-a3b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db2809519c432f97129f7f51","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0b8bc5d77324f5d4a6184e7","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f932e350d02270272a4699b5","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7346e21ff6039e7851f3cf0c","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cdf63b8df011f0ff87fb63b","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6fe04ab988c966bcc2cc8917","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d82e08723042532db00fbf64","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8435069f6714805a5bdcb8b3","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47a57d2d2d5bebced36433b6","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4eeb25e06a76789d08deef48","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"937f3deb6ec8769352a2f898","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"788b5a4a18e66ca329d23ccd","modelId":"qwen3-vl-32b-instruct","configurationId":"qwen3-vl-32b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e55ba0226be74935acdc897","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4094dd3667ddcfa668fe7e5","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d582a1e6ea952bdaa149da51","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"73203773c02c1803cc040e47","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90a23b0985eb873d6da4fbac","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a535d8fa36ad7b6f19efccfb","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f152c8b037230620cdf6612","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0833bcf585498456cc9d0564","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72340574c11bdf92b50a5b2f","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79f1b817a8bf3ed314092aa1","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6175e18fd0e66b677d391766","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91c0534b0a62fc3b88904ed9","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96aa9eb5f454deea7dce2ec5","modelId":"qwen3-vl-32b-thinking","configurationId":"qwen3-vl-32b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fdb356426f563f83f2ea4a01","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecb1b4b1085894574d2ede22","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3965d02265b8cd2f3fb53b31","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"048a32652d70416c7f411620","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3411bba2fa134fafbba0bb3a","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0cf5d2bad9846828c180e48e","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18d7349015832a249624fd5c","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"656a47fb67b2a19fef4e31ec","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d8e3953b819ae9ecb77cb33","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"edb4937174129ff14d58735a","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1d167a258f9e93c210f259ed","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1724ab099aea8608156fc956","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee07bf88a91e4495261d3439","modelId":"qwen3-vl-4b-instruct","configurationId":"qwen3-vl-4b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2016ac901838a157d54e1eb","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ecb9cf10e11fd05f5d7d8502","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5819e3fd8452136833f35718","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"57b61b1da9a2c9e3a3acb85f","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e959c69c4467ef5bf9ef4072","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45e7c304d53e99009f735f7b","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"500c1e917c2929e5059ee4d0","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"574bba91af7fe1baced3aeb5","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5937d980c6d4c9fbd919d5c9","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"362b4a14df3cdc84afbc71f4","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"be0266afffdd5c4ea60000a9","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ca54d8ad8a33c18db1d947ab","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd7f1bd0f1e410e21b9c5b0a","modelId":"qwen3-vl-4b-thinking","configurationId":"qwen3-vl-4b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a73112ccabc790faf47fc2ac","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5bc12952f1891bb0379aa9c7","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a3f4483f198c01a748200ab","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b9f2418d52839baa7a340b2","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2616cf11c1caf39e02f50c19","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa9589c76a8ee5e83bd7774c","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f7d1263f0ece557ae1ad4f4d","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"68113c3030360a2eb3a4d15a","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"adbe6ad89c794eda3ff9c001","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"36cb2e462ea1e247f9f8aa78","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"1cd485ab01810c1389e0f4d6","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cc01773941f38b549389bb9","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79091a97cdd8c46eb8496f8f","modelId":"qwen3-vl-8b-instruct","configurationId":"qwen3-vl-8b-instruct--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc7b91f0e6eb4ba4a8af2d29","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6070f6657824dddd8b696352","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70e25eae318c15611c90329a","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"96396a220f050f9c610a29b7","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"405328f5d7cbbe8ce56d7b17","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8ab8eba51f6cc002414295be","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ecac423e4e3317e14f55ad5","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f865331efe53ccc13479e7f9","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cffa767ba0a1e16e2db0137e","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc245f925590016dc55fa53a","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"bce789fbb94ae0834475783e","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0a268dca21cea302e2bdc4b","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6c738ba4e4e4ebda37da9cf","modelId":"qwen3-vl-8b-thinking","configurationId":"qwen3-vl-8b-thinking--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c79f005bd2c96b3dfac33ffa","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6526c4eb6102f766c4c1062f","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d0bdc890c6710da451dc8600","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60b7d90d07f72044a849d7a4","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07ef03c305071784ff828680","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"694b1c4ba5beca31bc0eb98e","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f1ad55633cc7a58851cd2c9","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cf0f7313bdb3bb306cf325b","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00910596b4c53cfe534ac0eb","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c91f30bb30bc36833d46e2a","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dedc8bed9daad7fda2892e8f","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b20cc339a7f979c41b1c036d","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6fa5f20a494fa9ecedcc7ee","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8aad14fd7116de2c2cfdeeef","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f04c11d1b1e78ba49a626d3e","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"937ba73b35a8ad5eb48af2c0","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"aff956fbf6dee32a521c6a67","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eb4731b4ea4ea831d5585e4","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c43d78ed5ec033460060cf6c","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ced6927af98788f28fec7064","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fe58f57624f6bfd77e4a529b","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f848e97ce77653c8903415bd","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0557d91e1328599eddeedaa0","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6c477d7a9ed5f790dea8bffe","modelId":"qwen3.5-0.8b","configurationId":"qwen3.5-0.8b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c98dbe8888cd28347bc8f571","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7570031879abad667cd8e969","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd77aa95b9c29c06a6b169cc","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1e2c1476fab5dba5c841fa6","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1434c5402cedf4ac2b4da110","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e4780dee2a81d7e9171107a","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc76f6471810c741012070f3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5f77b4f7b54fff6de405295d","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"128847b55a3390d3459c48df","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f7ad991264657d538d51832","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"89cbf8eb01c2697fd35c27a3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"712427354a54a3d7928dc9a0","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b2b75d84b4f7c03bc1bc751","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd859ec8921f41c450fecef8","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91a6a7e402d1e1cd935677c2","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e4d9fd1a2574d6a5ae7703f","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ad4b717ca4a435c0c7b6bf1a","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b5b2eded240cc84231225e2e","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"633304c9460583efb1a9d123","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"13945cfbd8edd56e3c0efd6b","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c7e647c2a4d2f6427799cdf3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"2680ab741c6710c6308ef76b","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dca6e42139718103b2bc6718","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"515eeda369aef75d1b3b90a2","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3bfff836c0b94cd19e1ab01","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3b2b0715095d52d58ac063b","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3dd3e9d4d8dcd772354db4ac","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"591bd1ccff3f9c16ac8904ce","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c6b2a6fcceb391533b9ccb6d","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dbcbfe85658c4ab468fa9ca3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a29311df8979dbac227d11e3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"928dfca300ef1cd20891bdf3","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"393b7eb4b3c229026330a49e","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70ec9dd22c9c9b201c491822","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3259eb613b9008d13bfb2fd","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52b6b150197775cfe5c91b8e","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e51ac2e0bcfc616f60fdbcb","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c1822f4f16b355f03b6b133e","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a55ccda11cad6f5dc83eb08","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4a6498ef78e583463717f583","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c89518098dd5dccb090f454a","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"78ef779c3fcd29db093d3844","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f49cf2685886f6ec4a83da8","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b21250eb9c4c108f04af43f0","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dc289d96ddc9b2f19861742","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6386fdf31a291d72b80c8bda","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e7a86835734ba4cfd98b502","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ae5bffa4ac662eed074e463","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"40ff7c5a40a01e803bb1cd8c","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"55cdfeeabac6031082ecb7d4","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6fe875ee0279a564bcd15685","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e5f70a0d9b318aca939682c","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd74023e1d36e1931e867b89","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d04bd91f3abbf17a30df7293","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3535372b77b4f10a2aae2f53","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"87314125e9b141d0f793b80a","modelId":"qwen3.5-27b","configurationId":"qwen3.5-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a7c022f322decc2d18aacdf5","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"340251b326024b7a69c3bf39","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6189f1ea70832a412f06340","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98ea8b4e38a123443727892b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d62f734d7f7d727dff607f0b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d4a80b838db126050c276e6","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1dc539f5096fa85e6092c50a","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1efb5443137143050e7ed17e","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"248d8fef7e7a90ae0e4e2295","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7bd48532b9a85b06d476758b","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67088604dbeb65c302440afb","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a54f47fe6f74069debb77e36","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dfcabb11e935b9d77c34307","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f426f85b359f8e2fe9579751","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0aba9d436f02774f10805fd1","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4ebd8fc4a160d868162f9b65","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"05ae862b6429e595ff8d2b84","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30a8a589ff73daf9b30088ef","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60624d170a81e918f4879de3","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f24913e7ca1a2f286dbdce8","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"20c954bf67b034614b5f10b0","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"050daa4bef2d46ebbccd176d","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"84335a8349dd1b9d4fa8d0d2","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31afa3a5ee4f8ddeb7c59185","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"518b3def44f7c280d9c2b344","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a6bb3e77e8089018687551e0","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0c4fc56597384246a3c510ea","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bca3df4c2afb6534b7ab2365","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fab70734378c4523a279cdfa","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52dac326b14ad8274e860038","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b6def33141d74b866cef6e3","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffa5a2f4c3d54a3e22f9ef1e","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1a4eac252ecd64ac0ec9fac3","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4bcadbf6a497277a67985f9","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e47d94c493c3d8efa18fed87","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b2a00224e4e77c869bb3525","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6429639babbd562974064492","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7eb289685e2f9e25fba62890","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3db7471df67389c685b88dbc","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71b06d1e69d3282835e9802d","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f638bda28b9ca9b449743a3e","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"eebdfc2b391ba014eacbdef5","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"cce73caaf54d5224ad13f618","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ef6e17ab8bf9c8ccebbad85","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"956b26763c1cc19ed48e62ee","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef170a6bbbf2157e05ffd6b9","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fe2b426e7191799fd5ad7b0","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"23b432199e2d041e6d0644b0","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f796f8cd0abdbccf18ef98f6","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab038381c16df8d1e510bd8a","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"76d6f70fae4e310ca7590def","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"acf644377690a4fb775a2880","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd62f190593255d149665e0c","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfb69334a23f689f666068a2","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"135958e9d5c43321eb1d8dbb","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75a41b8db9b3590c183008fc","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c99d476c058b4a89123fa646","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"83ea18f7ab43ad1f8b8722de","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"521a42cd831cbbe5b0e2060b","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27488df1427b0253553c87df","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"082b89a396ab2c1e7104c310","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7e0dbe0e88c6108996e40748","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"911a594d4aab2c408e3fd321","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bc7c4c940825fac880dcc166","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"98e5e9d937b9d54203e61f95","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79dce625ee6f0c2ed9c8245b","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba25e9f3d4d437738db9b852","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dfd2256c044cc016cd99b343","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3d4369851bced4c6f9e534d","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b395c95b8a65bb01a89133e0","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86340fbe3bc82bdd6b9d0f7d","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"721334010c9ce0613c28fb6c","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"263ebc7960a8a4cb108bd07c","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6a3a254fa11a7c706555dff3","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8ff8cfd69dedb3a094f26ced","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"028e196a79298f6522c3e81f","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b223f7629fdf1388f9bed2a9","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d1b866c502ba3c2b8352a96","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0cc3fbb604ccc3d914119e9","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f9e10389b596e289112755a","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1164bcd5a5aa3712ceea50a7","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4ce0b8becc8fdf948549228c","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"642a262fba6eeac8cd6c33a1","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee547f794b6f2b28ae9a8028","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ea8b264473dc425326ac154","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"897ab118ac1342a924d6112e","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"053597e91079b350b9341d09","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"92b1bbe4bab1236ee4b0635f","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e91f85c76ca2395e8d16bcd7","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"af08f36e4be4659803ff0480","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47153236c0ed4b07d1500751","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"642772c958d7cd65f97835cb","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dce15135abcbf97e2e75e164","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f54a0ec86853c159d448797","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a9e1f9b1809bcd29819a8408","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a1af20461c5aa98121c402cd","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7f8e4594adf9ffcf3ed6e8a","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ebe98a5e899b1dcb02f76998","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"ed5f4a1b29b3009ad0ceeed1","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"247c36abe2eb6e790cc417b2","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d28e385d70e803a765f7fc5c","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50e3c30102eb314283834c71","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f08a6b8acbba22210e4198c1","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2ed8afbd8136fb37d1c54bd","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6fe8b1efef057e8b67e8412","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f84ada02ed713f5b4df5e8b","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5776b4e242b36d7888d749b7","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6b92b80ee9f40384f85cdd13","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"987f147949570e5f033630d1","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35ab75c2d9610fd9d6afd707","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"51cceb0f761a19498f07f43b","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93e0ee1fea4ee49c409f7f30","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2c14147928ad0cbac8fa156","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2a233e0c283bc6f848ab7f8","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f70624165f1bfb5534f12d8","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d9e271b62a791eb7aa355fb","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"91f1614a6570830ed8587c39","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"405394a5fe3ae5cd4ffb5987","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b268faf0293cf763ce33c6d5","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bee5fa058648448b9abb72f4","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3271ebc988e5db1d40b6ee92","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"70c7c662608af8f632662f38","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5686f65f304b0ae905401fe5","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"37143e5c779711b1534cd2c0","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bbb1c791dbb001405e0b3785","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35b08aa160794079a7760a9a","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b6ad97d2e6b84fb5bfff38af","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ea96f71f7b8acf0e5c92135","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a9c2b5e5ea876f9675bbd0c","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0eb44799cf54377c7b779992","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9beec241281354166f7f4cdf","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"71565ab7921a7bff37fd8271","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c717dab863d029554a546f07","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b94f1d2228e900a6c2df44ae","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4828255fcd543335b20e8178","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5584d2dd8f205f5dfc703398","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ed7cbd32da3164f960078dd","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f03d2e976501ce3b51c34286","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ce044099dd1a13b985395372","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"de3e87fa1b992b3a661f0744","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4305e3ee57626ca07733f9a1","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e201fd8e88804cf432985b7","modelId":"qwen3.5-omni-flash","configurationId":"qwen3.5-omni-flash--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c82039a80845dab3eadfacd8","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e75afb685d3a3295079aa9b","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0f1a5a784a71c9e6676ed3fd","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4d99610acf5319007bb0aeea","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef689030a893d35e97f6f3d2","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4db50a094c083851e4fab68c","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62d333463f4ce6b2f02693ee","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"047dd20376f5c65c5e1a899a","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75ce6997f9a7d90791f02ea5","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08f342f50a739b3ac9528085","modelId":"qwen3.5-omni-plus","configurationId":"qwen3.5-omni-plus--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90ba7abd10ab7bfb8b7e1265","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9407d449239c38058843fede","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7a488abcf660ae289f3a24f","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"69a809df0aeb1b2ecf654222","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8f423f444a94a81a9c1a0a8","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"536bcb7f59ec5628dcee1463","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"448b575dcd1acd2a60fbb4cd","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6121ad64b0d2129d07648388","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0b4a0dd24a68180a17e59c72","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9f3b5a5650f0028b75e6627a","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ab44e7ebb36589f6af440d58","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"055fd1f94ed84235b0dd236b","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"511a91b9c33047739bda7f2e","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f8e8bc36191c7551f6b5cc4d","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a0cb4fe77de2668f3a7851d","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"147cff2e7b77dbe7a3ab9a02","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01d2afdc9f3d7512a2797f1c","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f330c240a2e147daf36750e","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3388bc6451fc50d48d32f80f","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"a670029bf642d55d2f29a869","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"8c5b10be361e3b52f4be8621","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ccb2b0ee8fb9a12d8d0b958","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db7758f0177deb0686de0fde","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef1ca5e4c1d0640e21632a3b","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e8af44f1827fd2b34c9c1f57","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3bdf7a8c944fd163c8dd47a8","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b302521289de79298a4c4a11","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"319dd147ad8ab4256d9e920a","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3e197f94e3c030d6c4c768f4","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c4e9d38c2e0b145c31db613b","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c666c345c763a37020abfa2b","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"44ce799a8b6dfb3736957ecf","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"abc2c041b38dbf315527e97e","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa3d8f5b093a68f35e1410fa","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc1010f44b620abdf26e9a2e","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e3c0a8de99217d5789e6006","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5e00d1d331c11537440b8cc4","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ade4f0426c6245254429d02","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6744996241ae0d03122039af","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba9f4904226ab6c8af5d97a7","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"010d7241edecdc97c2517e80","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"94ac74e00d580eaeef1daa5e","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22f962a63a0b5ff81b811a76","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2140cb653135c824c77c5a52","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65e97e60b864e0aeedbb1d77","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"39d90e1de15d33cb62e706b4","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4082640dc825a629a68d77ca","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e3238199ea24918db578f48a","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f021164defbe4c063630dc02","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eacdde9b4ef2d608c6c5db66","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"bd2c4bd715ab130b5a7baa31","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"60d26e69fe34430556065e73","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"794bebda292e3704b05c0a0d","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed5c9e27d2893228f1baa185","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"309240dbc037d56fbcb6b7b9","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5fd472847cba72707397312a","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ec8ec75f74ad4b9274f062ed","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c7fa9fd818e2d0e84c1b39f","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"948bee28800b4658a01a25ed","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"034278450a24f60e27015b1a","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2153c542957bfe883a91411","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34bbe6472870bee2df06ea3d","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50d69af85898178490384a19","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93638a70fa1bd2eb2973ebf3","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d22f57bac206134b0895962b","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b350b5042596f5ed2bb3dff4","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ea5751656e8fdb09476cde1","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b17e297aaf4c740f79979be4","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e50ff97c4425d2ebbf1223b7","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3eb7381b382205fba1f0fe65","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a62bce89fdb4d3abd526eb43","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"45436b8af16d8065711b3a43","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21437c6d099de4a38389b43d","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"489ee597fc16833ca2058214","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59391278a6dd9fcc53640072","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"08465a135acc9707f92293e4","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ad3e1f3423393d133f7b393","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-analyst-agent","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3965321e80f30621ed470e8f","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f305c1c4e37d27e61f689a4","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2a657017fa2edaf82956db37","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"870c96fc00ec0feb2f32dfb8","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"297e5cb842ccbb88ca618949","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6e30bc47e35c2d4bf9e1eb0a","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4be42440d0557b1c75f0a0e8","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2307b5abe75cf7cfc52c4986","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0dabc74907ca4392d902bfc6","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c0e30a179da19a4e7f3bfa4","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1b9110161c8cc2b19d6f2080","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3a4875b885ec50b15c8693a6","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4355bc5b1225c68cd10d5191","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"7baa3c2e804282809b3e549f","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9ca0c4c478ac4a52d15f4f0c","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41227f76cdd36be7d5ea2c15","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d5af817cd3c32f49b5984987","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f157407c28400fa2fac4f930","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f2e2da41746ec055e02aecf7","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3196d9aa5b9ad70ac47a6b65","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7aa87b0fb7770deb506f5b6","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9cedf613da4351040d1e92db","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"963077a2374e6ded6adff9ed","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fbe559fc5ce72b2613c6245","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a2ed5103fa0df8f7cfd0375e","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a1345f8a31fdf95832c6a86","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"defc9a7127c75101a72a75b1","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f961b4367e7279d1907c103f","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ccb7687f63b0c6d5ac1eecd7","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35f5a4346e3ce8ee05a96b41","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79ac3364e000c6cd672fbd91","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4945d0ef68fe56561ca877da","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d2243ff9337e95a2dd7edc4","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7a0d9322ace326caf2db310","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d6fc7a9f857efb4ea8a4d09","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"987027dbf8f699071447f03f","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ea57b2c6129ce72f6450114","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85e6bb415f16c9b56e03fef9","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"97acc2df5e24a7cda1402355","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f7cbb594499981fc7681ee1","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"85fb53fb3b36f8e29d58711e","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eb42639192e6f3b2becf6ef8","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9444d9b9256a7cd2e2918fda","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"27df0e5138bd5f8d7c930041","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff0811d93cce836318787010","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"190e54337ed7afe809ef9033","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bba6cdadf34a978f2014270","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1c96bec87c5b1f7f05ecaba5","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56238879c4a50c74046c5756","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a99e4925b9bb3d9b381f52ca","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1305aa179987856b5864ef92","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ea79d9a87da1399709e4fe4","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"215c0a040e1f469b97f5f0d1","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"3cb914a9e40ec3c843a24080","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"845e3104f356e8046a04495f","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72e55893e37d975afe2e59af","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc3f9005dc869c1b5547b4f0","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db82321f46121c82cac0b9d8","modelId":"qwen3.8-2.4t-a95b","configurationId":"qwen3.8-2.4t-a95b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b719f9e8b09e209b85b1a1f1","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"86bee422ce1951283a6eee66","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd81cc23b91a66f00c3f8c04","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19b0485cf1bfd20332a6d197","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f61543be64902b815e4737c","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ec9d3b365ddb11b5239f4ac","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"945088724c81324ac8f23ad1","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7c106e9436bf259deec9c01","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a11d07d00f37c70adccad7cc","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"03c3f0f74b136d54e7ef30d7","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee9a12dcf44b9eb2c8f122e9","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"74444598a5429e7c932561c6","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db23778fb38a738162c3739d","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5d09b30a62641fd043c20be","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1493b163b0b799c95096ee25","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62b4a85d1ee9d190988264d3","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f34a69bcff3a02bebb787c16","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee9581a4eac628d2891dc86e","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5a3eb5d8a89b57365845de17","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65e57ec334f4df9a4b3617de","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5277a02a57030f1526653932","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c4410504b14db530e88e38c","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3d2839bcc71d9bb7edd251b","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46f816a1e1c7631080155c28","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"149b9aed78a8b393be1ac340","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aaf557a7b57bbf68838151e6","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c14c8032c2a9477a91be02e2","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"45789802fc3895cbe31eb8ed","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b5e2ca909dc461cdc38a556","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"30ac372f7fb03d555903153b","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"395a465b3f1f60977613b6a5","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0a5895e3fbece4eaf4323c47","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7ff9c733e52387a7a5d3d1a1","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"135f2e02482f3c68bbcd884a","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8dcde2b92c7f4ab70a64854d","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a03d4ad0bd3a804b66a9b24a","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5d47e816e792f15b47d77830","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"369ef6b3e1de52e3da9e761d","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"035420d05ec2253ac495caa6","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"133afe96fba2e67c6aaa2ac0","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ffc6bf6a010111fb752652b","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"59fcf8705623283774907cd0","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"63e26c5f81acf9016f061b8c","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"811f19db6bfb655cc3a26d44","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0573143394705aeca6cd7ca5","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0b6f28261f842ffd221371f","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4fc56c008f264520aa21e8a3","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4dc87aed8e48c77a76e5b0ae","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a678d60ab97b56c3739d98dd","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ebdcbf46dd03ef58d97834a3","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d38663513b05928bf62032bf","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ded7cba3e8c6acf2681b027","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16a685d097b9257bece582b3","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"06d60c6c4c5a2369cf9b0093","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd22f232820d993578b5699c","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"125ea9db3e69a8e08b2b0147","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"72b5f2cbe66abb63e4d32772","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d6892a199b887a3e762e71aa","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1b2c60fd4d4f016e95db681","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1af1c14074eae9ab67bac2a5","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"100eb437023dad366f563363","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d7c9d2a0fd1760ad961f399e","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e21724aca11f3198eedbc6e7","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6deae3600f54d6cccf5a0be9","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e02c83aacb3a00e840a9af72","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"16d3fe3f51d36c136b12f8b5","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"653bd0d5164de68aa04fc91e","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"19beb3218856ab5fe419a3c9","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"6cd571f906fa29b42e3b182b","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"107f8908a0e4a7c541544f2f","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e600574b71b21a5cafdd9d49","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58c528b02767f71c2ef600cc","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50e7110e3b20dacde3b37e1e","modelId":"qwen3.8-flash-next","configurationId":"qwen3.8-flash-next--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ac0ddd5b5ae8b79a4ddc80c8","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aime-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd77bc1467dfe4486490d845","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e8614db68b3d211029ec88c","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"841cd6af604c06ea92463ab9","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"58e1dd8e3731504b07c5dfad","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17b50474af561818c94ee00f","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b0760998291d4c24b0a22a4","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ed488162479393e23b14bace","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/livecodebench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b64d48fbd23f04ac8eebe4df","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmlu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12f82b95be07624d144534f1","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"044431bb8ae976aa42349a89","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1de2302eae9a29fe88d82846","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bff8dce7b47e199123fa7411","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6ed7251fc836a13b8bda6c2c","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"75cb2fffbf1adac440b9c082","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d3eac54d4adb7c21226a10d","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6cc904fe0b8921985e0fbd2c","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b239e9e2e4dc4d96acb069c2","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7c6f3969a3bfb58f59e504a9","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"786415bc21ec9ec2f6bbed5e","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"c2348de9a5afccbf97deb29c","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"65366e28efa37bd0fc9304a3","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f28b14f230ca174c3535e105","modelId":"solar-open-100b","configurationId":"solar-open-100b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"541af6b48e4dd025e681a015","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e9ccf812e35cb29f130dc31f","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7460383ca07504611e1fa311","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b4701fb10f02abf0859e9d2b","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f5a8e2ba8b2c9185ba6e9900","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f706a5ffc62ecf11d8aa11fc","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"e1c44575202fa0dd5bbff5db","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"793184ef1385ac9eccdc0fef","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b72d75ebece38f24171ed19a","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2c76ce1b70fddc006955b7a","modelId":"solar-open2-250b","configurationId":"solar-open2-250b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"12d55ff49d0941524b330102","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/aa-briefcase","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"90113e320325aad453d0207c","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e1354b01691573102e86fac0","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2e642eb8e589b310afece9d1","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4762ee05df5eb38cf2f0a883","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b062943b8fc21bef0f9e486a","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"087acac2342dac2567f325c0","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6cc07e7f169228137b2d3cf","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6f529a5f931819bad160b6db","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cef5e234850298a63380a52c","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mlcr-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c646f44d8a2f54dd28f759a","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"5a972a37cc173c738ac9b70a","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c09d36e66a2605d0626b8874","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5326f847758818bf93448cfe","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b761794691d5cb615a77b75a","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b80c8dacf1f2ac3db0ea6ed","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2163d48791cfaa3ebdc1dcd6","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"124d3b5b3e2079c76cde89fb","modelId":"solar-pro3-260323","configurationId":"solar-pro3-260323--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b110864377b43b4a8709ce6f","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ebfe07bf9a4ff4606aeb50e","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/automationbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9dbd38e7eea0e005c8b08526","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9cf03ad155e2414076ae99c","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdp-pdf","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"daca0757544e83cd0db2dbf6","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"524276087f80ab9a7ec587fe","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b2f666197f0a616a41da848c","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"00db4ada432af3c8ba91468f","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"534053ff38c39bcf0e64b018","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f295d5a65cc60768acb6b130","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67316d10f432f15fe7c97a55","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f4dea894fcffe88ddf4ea8e7","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8c993fa6a419d236d83ac4af","modelId":"solar-pro4-260806","configurationId":"solar-pro4-260806--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v4-0","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4e4f7f66e12fa41c88b4ae62","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/apex-agents-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d03747357d4b99762e3c2c12","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"05f9d1f4588607425107e0cd","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f3f1d0a35cc4c49e68376e7f","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3bb0f7ade7fc2865154e49c7","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aea0451a4896d102b0043d1d","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7871ad7a9b4fdaee2e2800fd","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/harvey-lab-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9eaec21698f9c763849fc748","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a23d7538799febe12d9a6925","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9006b356b7c4957dcf096d9e","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/itbench-aa","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c87c7ea70afb04af4f026773","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f10ed77c5f2a457b4875815a","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"4cb090aa5d8a78b6a18f80f0","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"31c949451c135ca26418dd9e","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/scicode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6ad7a16a5446adada0a8818","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b38eb1018caf6cb002d9ea9","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau3-banking","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d29adfa107dd249d7fdf48ea","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ee468fde2438f81f9d3a5096","modelId":"step-3.7-flash","configurationId":"step-3.7-flash--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-v2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"43b322ea28a4a6f277552a05","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9132d81889bdde96600d5cfd","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a97b8f1ba39ced23967d346c","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"faa28dbbc9f9add21df2dc61","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5cd738dc348ca79f2c279d55","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0c789fed617bbde5f34bffc","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/mmmu-pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0fcf0db8250ffa3a4b7f5ba1","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"b442f2f7fef04eefeaf6dde1","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1d4647242d6328c3454120c9","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"33581c6317d1eb43fcadfe15","modelId":"step3-vl-10b","configurationId":"step3-vl-10b--effort-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"701a12cb5a469a4de2b81dcc","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/artificial-analysis-long-context-reasoning","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"803351c15f6911e960f59a82","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/critpt","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae198468c720d10bafa7d1ed","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/global-mmlu-lite","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"02b8e27c2385d10ab79bd4fb","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1e3007800bf6ad6160a38a16","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/humanitys-last-exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1438c051d28cc24285d0b24f","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/ifbench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"41c731de4263a48b615b716d","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"excluded","reason":"Benchmark family or source protocol has not been reviewed"},{"id":"9fbe07135ac2965896c34113","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/omniscience","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35cc8b451f8300f16237328f","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/tau2-bench","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e244a76401048b5127d71e98","modelId":"tiny-aya-global","configurationId":"tiny-aya-global--effort-non-reasoning","sourceUrl":"https://artificialanalysis.ai/evaluations/terminalbench-hard","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e654cd1466ae894d75cb1e8","modelId":"grok-4.5","configurationId":"grok-4.5--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"ffbbc7256f47ee72d321f094","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"6568b269cb7681ea39a1097c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"55c55b9ae75c2c789bb81880","modelId":"grok-4.5","configurationId":"grok-4.5--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"82ad7650319190ab8ebf8f1a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"07c58037116b0b06179f7fbf","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"758fa2580c85027d05e4247c","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://vulcanbench.com/benchmarks/08-kimi-k3.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"a5c39da8a1cf93a9c675f0ee","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"7177575f578b9a510d14e532","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"f20cb695188c6fb09c7bfde6","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"724e797747b99ab179cc86f3","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"fc3245dd2348d67c6fe183bd","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"42a596f42d31c722ee3e28df","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Source reports 55.1% and 38/64 completed runs; incomplete trials. Published percentage retained."},{"id":"1bef904009c6a794c1dd2f03","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"5f32740262d72bbbdbf60a38","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"d99fc9802ae6b1d7987cad39","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"47ae4c48e3377c9ee20c9652","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"69dd3899f972d5a522219937","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"d6e683f349eb46ae01149f20","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-medium","sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"5a6667c8022196c74f1a2ccf","modelId":"qwen3.8-27b","configurationId":"qwen3.8-27b--effort-xhigh","sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"f796e96bd180b4dd9bd12eff","modelId":"glm-5.3","configurationId":"glm-5.3--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"d783859010d571f133e77356","modelId":"glm-5.3","configurationId":"glm-5.3--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"3bde5c20893b402a0e56ffb5","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Source labels low/high/max; Z.ai API effort labels may be metadata only. Bare-bones API column, not ZCode."},{"id":"1b7ece23e8756e740abb6e39","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-low","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"970bc242697fc80101d9ac17","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-high","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"c5e80648923e0576c68a9c39","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Evaluator has not been reviewed for independent admission"},{"id":"00cd14ef96cfd2e8dfd5e845","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01c83861b72d5096082de252","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0acab77924c8fa3e469de011","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d5e49902497ab349126387e","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0d89a61a72b86a5fc22b7ebc","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0ed985881b62cd0bc3af4eb4","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"118142e09fa2bec781ac751e","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"126b238f0fce5e381a15f5c2","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"150f043c8b72655148c79768","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"17937afc9a71c653c9d4f6f2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"18ca9b5ee43fc4850d343f7b","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"190a41f349d6ec138ffcdc33","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1927548b0a16cd1479986cbd","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ca215d9d01741432bae9472","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1cf1455535fc32710e1965cf","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ed4c92e4aa05c76200a18bc","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f3aa6afe3bf07a0c02a7308","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1f438db0c3a8d74e269dc9c6","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1fb4cc080f6a704550c60899","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2105c7646f3a139187821073","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"212dafc406aab75cb58766c0","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"21ee231589903749e98387ba","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"25234df123a00777fcf34bce","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"255229c9fb97665746c2f311","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"276a6edb836c21a802685b40","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"28a8f1e475f0000b4b484058","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"2ab8119e321a20d7de8cf1c0","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b41628e867fcb824b023ab3","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2bd0af0abcc178550c64a1ac","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2c3bec9e4e0eff839c3ff4df","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d0594eef125dd86ef42cfcb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2d2cb54f2cced8ad23e6d7f8","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"303f27de5519d24ea6491389","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"304e04af8619e1665e7baa68","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"336011e6d0e94555b099f00f","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-none","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Source-reported None does not establish a supported Astra API setting."},{"id":"34af973aab00ee6e3f8d8bf8","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"35e4eb7c3f88bd81a2774079","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"35e9f237985104a6fd022a74","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"364834ea4ff4cde79854901b","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"37e808d11c66296c681ea587","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"391c90fa4b674dc1c3932918","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"395047417b94ee3b51adaa55","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3b38242e2298df478a3621e4","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3c433cf7df074c5af7c027bd","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3ca697c43da26b4e6144885f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3cfdd48cd8b66a487f18b2e9","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3d5e60cff8818bd0c8d67cc0","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3f43c11c9388f23914100624","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4089087bc0de296803ff3a88","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4348fbb897a2a59eae46e3f4","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"462443c5210915015b4c7bf9","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"46f65324a766a154476a00ad","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"47d55be1dd81aa1bf4bf5a74","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"49fac0a9cdee783034468784","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4b326191d83fb7c7b1f5d5b3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4bacad2a4162155bcf382a46","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4c92e3a3655317402e6e0fc6","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4eb55593e72129b9cfc2a23b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f12de502332d1a93cca6d84","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"4f8d2f40bdc3160cdf5b7a04","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"50b7158c541e4c1686f7c817","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"52da31a04b7d561b7573dc1f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5402da52d181b12603f15f33","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"541e90621a96734aecdd8834","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"55349c832862fc4d4b933188","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"56b0314f31e75a7aa19bd3b1","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5957688c8334d48ade93b3d5","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5b4b76daf2a598a3aa8925a7","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5c999b15cf49cd9ccd8eb829","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5ce108c441495c34dbedea2f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6080df646918e38cb77096c2","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"618440f872edf631f4f0df6a","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"61fd47e8efd909e62876c9b4","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62ebd59a104b5a031160d534","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"62f127539d56d2de5540a715","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"636572fdb50187d8620318cf","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6378f4d933273f336b571e3d","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"668028a9e1437683d6c27dea","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"66ba0759f64f15955b12acec","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"67d76f5adea449a9001331d3","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"6958a5ca37b2c58d4c9c3e9d","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6aa803cb83233f756479ec7d","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"6bc123e800f7cf03d59f006c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6bd6cfd3abfed443b703c64c","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6dd3175afce39f643aa12476","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"6de659b8ed7b026127969cf3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"739cb0ae8374d5569ce1d129","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"74826bf1588713bdce3f6257","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"750e6cc699e912bef459e45b","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7879d0685c077f756cc44783","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"78cbe45f9b9ed1991de85fd0","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"79f0600c94bfc8d4dbc0b58a","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7b0f1b3e720e4f33cde4257b","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d8be1469a7c57ca60300f6b","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7d95380d1954ae5d145cb859","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7da2111f1593f8d5dbf745f9","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7db12365ec82e0beae8240ba","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7f33b674105fc71448617806","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"7fe01339271092343301c357","modelId":"grok-4.5","configurationId":"grok-4.5--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8127d6db140d93c6a2a6f0fb","modelId":"glm-5.2","configurationId":"glm-5.2--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"8181883cb35a2a27684ba034","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"826615a0c654de07c920208e","modelId":"grok-4.5","configurationId":"grok-4.5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"82d8e132cdcc601f53c1c7d6","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8be54fd7c609e5e4264162aa","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8bfe922d1f0ae206b1b1ed3f","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8d972c585034853563988a88","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8e0070188f79ecf6c53cc2c3","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f27604b87c7e9ff3a19d10d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8f57b7f23dea1aca619ea9db","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8fa122a380d849f4f7cb625e","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"906266917f34d4a9235d8c64","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"909381319a7974fd682e23e2","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9183ca03c441d129fd6a8992","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"919bc7aa1df6867a3297a658","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"93062cdb2abb0e270b7b4742","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"938dfc674e40641fd737bed8","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"978ae4621dc780ed9f07a974","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"984e727c945e5302e01c261a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"99e65bc1e02ebf4fee08b548","modelId":"grok-4.5","configurationId":"grok-4.5--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9b3960b33adb0f097551e5de","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9bb740f8253baa1d17ef962a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9d0d05ab12b44fcb34eddc63","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9e535e58aacd4dc5813160b9","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a00271826c96f0bc443bc92d","modelId":"grok-4.6","configurationId":"grok-4.6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0921a61b310776b40a299af","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a0e5300dff64fa35e75d78f1","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a157cb960b29b4f9e0e482d3","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a24f67306456001f98c23e75","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a3f23bb0246903333cdc1388","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a4313e77019bc32a716730f9","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a445e097ad5e39979d7aa81d","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a47e1f9779f4cb809ad3770e","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a825739422e65a8fe0204db4","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a889d1ce384914e2806e70c7","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"aa2c038898f84e93e7834f06","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ae189fcaebaa21a3fe020a5f","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"afbecdd463048a0daf4430c6","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1f2936eb97f6064636f0b09","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b1f91824de3ef9411c7d0e7a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b21f635f0c1b98c573a8cec0","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b36e1936d9f1400c7a8303c6","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3e20f0dbe09ce936f270b9e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b3ef1bc9e68ff51e017bc544","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"DeepSeek V4 Pro checkpoint is unspecified; April and August must remain separate."},{"id":"b4505193e0e1f1e917b5cabb","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b54fdd6462a56cf9fbbff457","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b56938a2e49c9671f1657923","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7467edb46036b2935325b6c","modelId":"grok-4.5","configurationId":"grok-4.5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b769c16ec2b4277cdc9cd0c9","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b7d96566d6b6b34d9e314f79","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b911c4d9f13d8188e2de86a1","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b99056688b2b172aff603206","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"ba391b95e256d194ae244169","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba8ff35e294d29a743fa5c65","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bced9c84bedddd36c1d85054","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bd377043899ff0ae0b462963","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"be5258d2d7a78bcec434049d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf209e5b4b2da520e58b7863","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bf764fb9af20b8b9fff21eb8","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bfe462efb459731aff29651b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c02f418374e14634d8639cb0","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c0a21b210841792f09e6eaa9","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c16b09ec865ee083d20ed15f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c29400f51cb09e46a04ec2da","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c2cebdbb75fc439d384a1645","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"c30c3f0dc62b17786a57f7cc","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c3b6ec43cb1015de697c37c0","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c7981128f2cb3799b53b66ec","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9b43e92020f700c0d052db9","modelId":"grok-4.5","configurationId":"grok-4.5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9e1fea0c53568fa87547d39","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"c9ea93dd77a44efafd8b2823","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"ca8bd8b35520f3df29860eb1","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cba8b60609ec8ba2d384bac4","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cc50f474e4bed017002a068b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd453778d2e3302b302d0232","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cdcc8b915ddf149c14044a7f","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cf038268638355842fabacec","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d1018d5f46b97e159d2f0a02","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d2bdad5d6d457b8f28281e8f","modelId":"glm-5.2","configurationId":"glm-5.2--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"d4b90ed9c9a977ac490e95b4","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d4de4a5ced8821eb86459630","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d548bd134bae40904bdbe4de","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d667c01aa76eb58a13006db0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d9ff43c2ee3145f93fa639e1","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da08a3f2efd54d7cb540441b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dae492a117175343395ae164","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"daf9afd286691adc70b10a5b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"db8204b5e5c7174d88f5e8a4","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dc357b19b6bea4e41d45b423","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dcbdda875af63c9d559ccae4","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"dd27c86aaec46afa668fb3ed","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ddfef6cc7d43c0b169169e45","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"de359ceaf316774036c9cd92","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e0e844ac4fa5c437d7f9afe6","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e182040a6b20731b3805613d","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e2c3b944130f3a5e4b806d94","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e554b93428a677182f0b4906","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e5f0edaa48b4e6162542d4d5","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://cognition.com/frontiercode","status":"excluded","reason":"The evaluator reports no named effort control. This does not identify a non-reasoning configuration."},{"id":"e61670a23ffd1d53d4575c95","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e638e44f7a00fc2c77bd320a","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e78de1fe1b2913b438e8bfb4","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e7a90181ff22c2632f726d32","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e83c78ee104f6ac791b27a26","modelId":"grok-4.6","configurationId":"grok-4.6--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"e93116c3e86f122b9ce063bf","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-none","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"excluded","reason":"Source-reported None does not establish a supported Astra API setting."},{"id":"e97f395dde5500c89744b1bc","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ea6ce5e67b0ac25bebd66ef3","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"eaf538a9130f43391ba85bbf","modelId":"grok-4.5","configurationId":"grok-4.5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ec5579f64a5a32bfa01b650d","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ef3184b2503a57f0077f8932","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f019be82c0b7b5fcd5e1527b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f069bb43a49e2e73d5a979fd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f0c644f9ca0c8b80a60b8f6e","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1474950f0a1512219e1d401","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f197d86f96a3cd32ba83cf18","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://snorkel.ai/leaderboard/terminal-bench-4-0/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1edd38ed72382bd57766812","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f1f80cdfdf2fedc08b3c8e7d","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f38a139c5a520dd21aaf9132","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f555b0cbf804f18f2f97e3a6","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f55940d0d324a594d2e7cb02","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f6c40a31975168e070d2cb4c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa5c692bcb2cab6ed2609402","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fa6ed88eb7e904aa6955ebfb","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fd19565d5d4088b6dfc79064","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-medium","sourceUrl":"https://cognition.com/frontiercode","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ff9e159dda586ac4a0349062","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://arcprize.org/results/openai-gpt-6-astra","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"01e44fc757e76a75628ede29","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"07b714836f4d50d2545a5455","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"0e5a24ad5a3aa10c27a55eb7","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"excluded","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"0eb870f9f6496683cda2ff7a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"129ef34aa55c39c9f65a8288","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"1ce57fce710e63f4fde5f000","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22863bca1313db0d07725e03","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"22f827b71cc6c1cb3e229440","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"25753b4cde30cf31c9192afb","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"294120a57d522f24c679c51f","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"2b65412a084daf79b87e4b34","modelId":"gpt-5.1","configurationId":"gpt-5.1--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"308c1446bec689a5b5f02280","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3203239d5cb0c63824c2a86d","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"34bc44371787dfc935087f65","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3668be0998ee9f9dbe1cb4b4","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"3836c4d32eeadb2f5ad4990c","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"38da8dccc01df7999a09d824","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"445b1683e6ecba6cbf9f044a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"488e21e807236e118e34fcf6","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"595d203626f42c7eaf274a4d","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-refactoring","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5982871718a1d5284ac2e401","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"5d521eed35c933b8c0cf6ca3","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60804685f644d5cf0ad52320","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"60b0d52dd406e2a990549468","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"excluded","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"6c79741b5a7ecef0ff4d0346","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"79db12d910dc9b17468fc07c","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8141013d16a793653a973079","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8154d53aea81c7edfd9708c9","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8adcbb20f22ee3ada097baa2","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"8b77418f10a0d2c871504615","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"9a7a2837429ecbebf2d957b1","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-non-reasoning","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"a71c17d0e87547e9f30a79b2","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"b406780519719b231c94f076","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ba265c887f15f603db7f5f80","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"bfc3139a28a8c37b769ae912","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-qna","status":"excluded","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"c457ac399b0c7c755bf0adbb","modelId":"o3-mini","configurationId":"o3-mini--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"caa92a3ee80886991f302d07","modelId":"o3-mini","configurationId":"o3-mini--effort-medium","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cbc2db363833abfb6c9f650d","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"cd7d373c2c6d5a8b1501e762","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"d11e9cc7b5eb05e0e97dbb6d","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"da0ddcdb318167ad7f56f77a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/enigma_eval","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"f621460ea8cfcfd9a6843901","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam_text_only","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"fc3ef3bbe098fd394ff0d2c8","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"excluded","reason":"Starred protocol annotation requires row-specific review before ranking."},{"id":"fdcbe9f44fc9ad3996aa935f","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking","sourceUrl":"https://labs.scale.com/leaderboard/humanitys_last_exam","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"ffc0fa711ef42f89ea97e2b2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://labs.scale.com/leaderboard/sweatlas-tw","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ea6e6bc84b19cbbf13457f52","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6be887e1f44cda444a386e7b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c8dfdb832c728882285c9b8a","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b3c92aa9680c3988ba1d0614","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-47f44e2cf6028a348add9648","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c2408725a1995f2f76a38c0a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d19da72f8f3dcc7122fa23c7","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-727e4929c5b77b8d68e9616f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cac9ea3d75b90f9f8e22b2f6","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9ee205c15ad677241207d058","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4ef118c3fb039ddcd97965c7","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-51cb8fa9a9f00859384ed176","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f31c0e7a8f4e830bbd7f64c2","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9705c757dfdbd2feabac032e","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-96b3bfd402ebd013b9937af0","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fa6c72914cd97c024b6e360a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-277c823db47aca935fcfe21d","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-04f87e2aec3acc7b9cc4f944","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-79cea26fdffed0236a191bec","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8523e2132a25c138914b8459","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d24bd2a1ac9eaf9d9494ddaf","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0a6ba849134e0075a7f8d9bb","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7dbc7ec6565a0f02cf88e3df","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3f8750e2188da7c334cd0e4e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d1592c494c0bc37b96c4b13e","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5db4666fe0d22748d017fabf","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e21e4fca1c3e3b98e1bc5a8c","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-662dfda40adfc5a2caa14820","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-641076241a9a5fb731ab01d0","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d40fdcb405336ff7b0641bc7","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c7a6b32798ef20c70836ed4e","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d622ba2d226d053585bbe3b8","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-335d542464864769d1ca1bdf","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8dfe6e73a7070dd2ca731ec5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5c66ecc29c060d251f32641f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-090d54d836ee129f1e5e6609","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d3127514aeabe252e43231e1","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a02f6b51825ce2ca2fe0cc6","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-607345e5f467b95cf251d99d","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-37f739dcc05b39207d9d2861","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c117f17c51149f80018795a6","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3c33dcbb8642d300cb0bd6fa","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b6daeef5e5290527aac86f54","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-32aa6b03fa6b1e2b8df86c7b","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5babfb32a1f20b6e99a59e4e","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ab5cc700d3ab0b9b4f6bbc85","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-778414f94d6574b36b6dab61","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f33cd6ce63480f276b68ccdd","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c08eb2b8012e609064d33ada","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-09a415daaa3ba1bf4182a0f7","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e91cb820ea7d82b6f4b05678","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7e01c14d29d1b99014cf62ea","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-31199fc389abf8c37e97a1ef","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e762d325f86c557f5d10186f","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8a3152b9d28a7530dac28f3d","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-32989ffe22dc5dd32f1b1f83","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e7ab002c6f6098191728383d","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bfd076ce374bb30a922457d6","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3eeb212b0c0bb0dc2e478ffa","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e79c5684c29cd6b303b8c12e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6a2c68e12f2d8caab35e1330","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8e215924ae06b331fbc47123","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-794d65e981554bcb3f0e92e4","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2d4783c770d432f985707cfd","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4dca8fee9d98c7ddb0581ad6","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d93b113c1ffbccf10888778","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8326dae2469e1a9f74d18cfa","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7fc55c6792c58d44fdf6c60a","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-00e8a0af372be006ba3d084d","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-da3a0ed56d6a64f954659fa2","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e93f929cb0853d27c95d04b3","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-054ddbbb05cbeafd60110ea3","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-28232fc4ce54814ba09b4d62","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-52c6e1962b976902f29d09a8","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d63e27e1819ee0b204cf74ed","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ada0ae4411fcde2f346dd40e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ca7c8b7e35ea3b5ded4662c3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-353e8b3bee4e37d087e93bed","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6baf6c794bf4aaf644c7b7c3","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-90609ba61b59695b58129751","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d93f01d1e8e2402aaeb5616","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cfb0683f76806bf4fb0265d0","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ad218815ebcfbb1c50b5859c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d3216c623cce0c30a3549af3","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-02715a3959bcec12a2118d77","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fd74c890d8cbdc78ca4926f7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-de5882ae22989b74ec6dc0e7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-da44c7f3cf2a9599579e7cea","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-30450bbe2cd94e48badcae38","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4f59778a92b6497855298360","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6fb4bc1b60f839623c5d4381","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-828ad3db06596510a3a5b361","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-85e5f51bb280d552f8a1344b","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-99585dbf3dfb57868d6e94e8","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f4dc253f7a805058432fb239","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d73f7faa8106fea92f3fb4d","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-77f63d80977191cf2c481d68","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-424fc5747345bdb81336e06a","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7ad1f49952e339692c304819","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-342d090b1be63195b7fa706e","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f8a70bbbcd0f698be7bc1a43","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f55d9d7148753278f84c2df4","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-014e5b85ba751dcc8149108e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-de29cc4390253be5d2777e81","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c1b3d7f5a165e5b35bf2018b","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1cba090af30c55faf508a232","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bbd53ca4e345a1af051f9838","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d86a15e1a604826048816160","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-190855818b7e1222a48e2eae","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fd99f744a0c951b883b6eaea","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9fbf2f2774c52b4c65e96782","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-39728f4c4f0069938bbfdf20","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1b8be849869ca37987fe3c9f","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd863a0d16624af984380aa0","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2aa437a8829dbf56b4b5d351","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a9cff8685184797af933836","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dc52f3d94a18a75b842b27ef","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b70f7219a2898aed69af5a1b","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c0f6c7ecaaece53d8096cb1a","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-27b4ef02c7a063ec88c3ddc7","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-56f7440caf2be4e507c56b62","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c7924ab86a4819c0c3bc7f8f","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-147c821e2fbfd731f109691d","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a2b9872bb59a3f7ac3aff0c0","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-686153cb0b44a71199a0619d","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8afc38f69537e97bbf2c5a67","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7b24c6ef6a4016a1ce0ec99a","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8f65ef6ded7e915b5df1386a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ebc66a99e1b9d323c3fa4812","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1f6eb2d767a08535a94cb732","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cf82c90989f66444fdc5693d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ec9906abde481a797aa4cc9a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b0e641583182f918dc7c7607","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dbe6aa071a22ccaa40e097c9","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9b4dc6b2d88a35de49975d62","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1330ccf27b12cf2611c21dbe","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-65c52ed61e13ff7b3b9fb1e6","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1ee6676d7e81096dff4bb6b9","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fb548e320f80168b36d88c76","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cf976805e5a88ef22e6c1aa3","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5610f87659e4a35f39fc8224","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f717d2864a445467e54f0414","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e9fc47dbe181087a7a1a77db","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-130f53a4fe944096e9fb6b61","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4f12ebc87581a8b3fead6ca5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6ffc749529292fd222d18cba","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f573c5db18f106fe09304de4","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-45e2f893822c593c4ecd6e28","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-78e254545a2ae1a666fe3269","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-20246bf3e3306bd736a3c80c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2c75d7123d8291e5be81a00b","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ead1203dc409c40234d5fee4","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4305d4d3278517373e3f5b3e","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7934928ca32eaec604963700","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-87b260b8aea4065b7af8575f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bb3ced238358ea1c61780784","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e42b32e0c02a97ebf85ee088","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a9f487811c15538616e240dc","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a8d0032f7d3827254000690","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ff7deaad8514a735c60215cd","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-939b2284f37f61d8eb5f67b6","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ea3620ceae6503098460020c","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9e636b17bbcae275ecd8ee17","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dfcdc9973f2a0d00f0fc919c","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e7184a5ecfae339d037a2b4e","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6414676946387e29fa05c0a8","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-33d654882b80b1889204d2e4","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-af8e1e7afb22e13a8161b804","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1915dc0e10000252e26496f2","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-239cfd267c6875696e83c9cb","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e6a2705861cdce46400bf7cb","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-58aac2c2dde4fbb0c2408d75","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f9834bac2c8a90d6c7ce4e5e","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5c58f2a3098155c426bac27d","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f2c256a295bd7932f236f885","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-36628f2999915365afee11c0","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eaf227f5b755476d39c81ae7","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-49c4b3d4d02e77f4afa7ec01","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-53e2e2b8cbdb216a093034bf","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-422822cff2d0c951a07e107d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ed27fdf022a823e0abcb4c54","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1de01be8339431f506375fa6","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0468cbf93870ad38beab1059","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e366b9965c11ca7171a26c5e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b227ac7dafc453027f546347","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d0d17e92e62bfc0685fa0240","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6bdc2206bd256d34c7fd7650","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c37413eeb9c7e46ddfc253d2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e2b90ad9ff025816b82efbba","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fb6b440bc03b13ca1c9f354c","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8f0343e8b72f79cdda804ff7","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5391f4e5c06b72826fee1ad5","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f1f80cee7d1e762d01154e92","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4172bd2caec615ab3eff3b0c","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c3668fe9c1af9e1f815034dc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8b775d5d773456b6ab271308","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d4d1042248b561833a92f2c4","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e8a89b55eb0543d94e2cc816","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d524cc2ad780da119be2cf9","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-79730153cbde8d293d44213a","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-873971713d4ce0742cfd0e18","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-19da7fc7d58c0bfc47ec9a8c","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e23f33b25b7acb309969ee70","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4000faefeda3951617e07ec9","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-50a0a1f23eeb2eceab0f4c4a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ce06ee813be216293e7004cf","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-603dd81fba10b50320567b1e","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-76844476c511fb7c5531e3e8","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ad21b2b9b3a285f669bede29","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c2188e8931d7269e78bdf635","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-51a4f42f816be6130de2f015","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f9e413513f7da7d9e60b6964","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-60bacf6417f2d976a9991114","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eb8e759c8756c57a6678b38c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4a402a6edf729fb609faca1b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a608739b95a5826c41cbb0bc","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bdae59106882e6ce30423560","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-67e783f1c412af0bc138d97d","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f4611dea0f98ae60341b3497","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9af7f61af6179d5eac0c51be","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9266dd9fd15700366b37c0ed","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3dd977ca39f5c684439cf98e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-919a5557dc2a750353058ef4","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-61b37a37ffa13a56ab533193","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a2e219e671bd391642993295","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd35ef007b87680fc5d395d0","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-65f8d6e0729b9c5c42dba5c9","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d44be38166189727bb5717a2","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ef97c9d27235b86d73fda913","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6fcbe883dd2cc95616b54d6f","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-51fe9f895027fea4c0ae2759","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fbcbde600561c3d3696be83c","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-14b8986f6045509b1190f001","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1eb69e1e8bf07bc6c2dd0181","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-21ace49cde007a4ad2f4e1f5","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f845a78cc2cb4939b0d457d3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-336ccdda131c10a4ceb1c659","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b2d8d393da701a3f89530fc2","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a3408fd345658854b48ac897","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-49cb0eef818478e18b9fc73e","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a71dad62d416416d1786c72","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b4abe05d293dd2f434bf065b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eb4ce80a488879c6c664dde7","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-43a711c2e4bf1032ca789322","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6c18356f3e605ccf870bc0e4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-09c708f2367d5cdaf9f13aaf","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0d7a1d9d2a51aa4564298f91","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9569698400df06830af314ab","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-141f8c45edac9dc4154ac08a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-35992b4dd228235b40982727","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d9064929591d93f9978bec5","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6ade069d452324b81f97d2d0","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8272dd6e6a4ec9a8e6cbdc9f","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-43e3fa367afc5689d6e1a375","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c72b7981866ef805a49330cf","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c399a15bbae382124505b488","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b0cd868f837f3c8d3ba378c0","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0ebcff26b3dd1ee910c0e7d8","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e236e8906de2ac79a50c15e6","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-387ee41f45c34973406f6a99","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a9f74dc3ba9d5be73f6de46","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-261505d025f9d0d994bd7c1c","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f7afb6dfa5602fcbcc94b9b9","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f35f8aae0d8d575b94fd76cf","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5f7b8f51d17c740d7ce23328","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2ffe687d54dc27361f384c80","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c033816ccaa5e32d8fc2fa0d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5f2ebc6018d88a7989407282","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d6cb0c0f64f505b9a71b6ff","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ae4a0aa81365bb0ac625fdee","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2be4cdc484550578181f30a1","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7b21ddb3a6195cfe20acdf0f","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b7c7abb64ed26c981fa97ecb","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-53612080416a8a2c52255475","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-369a3b2d9f40c49f3783f859","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d1b3a97faa4ffcecfd7ad8f3","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1099925f01eec7849c621575","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c1f148c80800c7bb48207f5e","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-47835dba414723cbd89102e1","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6730b76b0480a9ddba9ceb60","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-54d0390b13496c156fa846ab","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e759c56964927bda6b798d1b","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-217316b453a05c8a737a5311","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0973b8fdc8a954215ca48936","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8e7c5485b183951578bf6f63","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c0d042721929915c8645b57d","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6212f1adcca2531c22bd97dc","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-20cb55fec83d1270c8d422e2","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6ffae1ead5b7afc06bdb440c","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-67db00b7f19613b66461ba0f","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f4035a99f61947c9e2d3a096","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aee7349a79f0e6aea04d06f6","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b9a05d343e2978f3dcffdc61","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-963e7b44cd565be1b3cc9695","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-64d9137045cdef710bd3ca92","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d10f6d2cdabb5ddb7e4899d2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d4235d275b78c1d09ff5b633","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-03a1e315c4f027dcfd8299b7","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d60952da8f212b02c5b80e5a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bd2cb017dd4aabc76d11d0f5","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5db103e8c0d0940f23c1c437","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9884a6b97b5686266ebc97bd","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4ed8370e5706671ee5d2dd82","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bf356ff8ba3d33e34d5d7695","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-57c9d66e18c45c4f050a462a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a7b7df43b105c928e66b1c2f","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0662502669451fa91c907b36","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e5935fb8a328a72c57a5ecc4","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7393786a27fc26872419dcaa","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f128b281d5845ab277063785","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b18397a1aab14698db6506d5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-21d2715c30bd186f37bdd468","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-91d118503479005ce69deb47","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6fda03e93661f6c58ea5e7e4","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-776124249647ccf9c51344bb","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-62a295778554ce1fab5fb5a5","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5990349629b3aae8b03c2734","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e05a7d89da690e9010835fcf","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-76fb0a8d12e96d2ae0671a45","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-32a3607710de8dca34022897","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-299ef4c22b4342670d0dae08","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3cfdcdd691354a0a5029cdd2","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b100b1155d4fad7945551d5b","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-01d19abcae8228176928ff95","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a2de81d0984e710daa10737b","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-03d6d7332196ab2b7940014a","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-344cfa519ab6003234bf074c","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b8667c26ba0685da759190a2","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-662364bb53927d6d913898d5","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-75a12802fa02fbeea400c4cb","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-679a950ffb35122c670ad6ba","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c9dec434280ecd1032922f0a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-667bd298eef009be052a0928","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-728ecc9a397966fe315b4b0a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f0a38c4adeea44226aae53f0","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0e6208d14f6ce63317052579","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8d9e48f418b10c02e9fa3a61","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eaef80a81b2207fafc6cf592","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aef8a69ac35010bb70d01430","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-09e4a65f3e19547b97c9aaf4","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cd52404d183578937e22deac","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e6821f14580e75e469839a58","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-26dd5319f2452d0d3e5920b6","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-843ad8b9e75ccb2e2e0290aa","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3b0a9ae45b36b943f938ebee","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c932d96633f436c5ab84fc2a","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e1f754b895ac409b7ff2d1f9","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d5ad12f947dad7a22a4caa26","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cb4d12433d4ef2158a779de3","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1c622171ac4a61c0905126a8","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-60b5fcefe36e164667e674a2","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c8fc51de7487c1b2d258c0f2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e497283877b2504635abf48e","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5df71994be4789f38c407267","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-19218562af1e33a655a35d87","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-74ec4158f36d43fe6107c6cb","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-69f8e076de1d08be8612d652","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c4700c0736a7c76bf94c8d04","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7395d6919946c2adfaf7424b","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-91e73f1dddb884058280f326","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0e57c643f0410832cbc9fb48","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7b35407610dfe74743495040","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5c1bdcb24909d99616ed5841","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ed8c7db295ec15f18a8163ae","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c238833b50dc00f09d833ac6","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-117a0e497718ad4b2bcd3af5","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-790eb22013b7deb683b85849","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6f5160d5e1a3874da330f091","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7f34159560b42fbf4f72e29d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-218cd2b7f3fa4ba48808e4fc","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7f78f88694ccc33fb7e0c3d3","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-332b86a089da785cdea3f402","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1bbc8f3b917da240bd97fec6","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-949d2db642838c34e2d944f3","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-759a23b0d450b5e3fb8ee226","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fd205044a78778402333b4ab","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c5de3c6d1577f440b4c8c784","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-21fd85624e4a16f80678eeb6","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-983329bcfa432e4151bc9bc2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a7d2871bbc6917780c8d21b3","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-870d52baedb6499434a24a51","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a794216ca56ac67f785dad20","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5d21ba95ec8fdb8b8e301fac","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c8c35a24dc4b0f79d4adbb2f","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ff77a6c3a9e65b6ccb8e3a7c","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a0dacead0b0fff9e77e638df","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6e17221392c2b73cb835e55c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6af50c99811132886f95297a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-779fc91b62607caad532fe71","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6a0b5beb7d2564d7dfeee8dd","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-62c1d3bad9ee9ff062c24b7c","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bcfd094cfd1370b8184eb917","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e0bda6cdff53e878f032c374","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8cb5768c95cfc9d9ee948a32","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-52f73ccb84c0dad0faf4db74","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cbdc096fb05b58e68fa0a78b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5871d8133517ae7eab0f50d6","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a54de73dfe62d0d252c262de","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6b6298d5105594af69577e2b","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aa139a442c1d74acd762316c","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d65e406870344792f02f74dc","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-29daa78a29277b8e3c4e1935","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-79c0b925029bc6018d77d2de","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-315c13eaf06cba3126de4186","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6c3961f5f7f2f61d3927bbf6","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2af525469b096e71b83c05f7","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cceb36ce7791a1eb1562144d","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e87a024bc711a8588ca5c4a5","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ba137339713465f06d96bfe2","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fb153f17dcaa7568a31cc10e","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f24c3abaf143433907c54872","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3e98d27984c5af805c065745","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-97a9005f0a93edb4193e1c8a","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6b40d917d05afe59030e43e3","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1daa1fc476d17b814e17715a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8db1335a3d1c4eb91f13f494","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c11b52096eae273aa28d6c38","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3b96713def9718e318008623","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-386333b19f9f51f693fcf5f9","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-717fe68688b1cd88d3865fa7","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eaa5fc61415b8aa88e767880","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-930496933f2794492ab365b2","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2d9a5f1ed5367f0741ff26d2","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7a8291feea5ecd53861d115b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ecbe45e5b2d5de3f475a6b9a","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cc1676839b16b4cae9c2b786","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f5913ad96576103aa18ce7e0","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-acc39098a765b02240f927e9","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ea75961dc8f3284bcade8e4d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-643a2b102ca96cc1c855d0d9","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6e422918805d22eb5f088d67","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-42a2d7c7037fb97d8e799de8","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dc7ca75625f95fde3437e823","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6c20b285e58d1c77b49b2468","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d11017bb0a00fabdb4412bad","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f627cd7090aff302ea1688bd","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2feb2a233295800339a769e5","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-520b3b60cfad57f258de5139","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f6473e04c058c6372d74263c","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-10dfde1dfd55d1050db26ccd","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a215fce1b280d87fa9122ee","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0ae689afa56fc1952d84c292","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-69d89ddfd6815cc3c5feb368","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-82b98df2935ac4c2e6f10aba","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-422f1455cd480504d8bec31c","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d4152f1599eec1bd1bc2db33","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-71ca1e47d78479714d961f87","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-14610010800749fab1e3696a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4844de203c7156b6d863ace0","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8c3e5d2106f12b3a8b88ef1b","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7c91d12d311b446ed2b720d6","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cf744fd7b4c62f6358037653","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2c494e13cd9d39187d4dfaf9","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-350f2da94844393f21c11f7e","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eea8659463585ccb5e9e0a4b","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-947aa825ea0ab05af778ef0a","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-87b456d84438ff05a853f952","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9e2379b2378edc420ca56706","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-753a406f6be326ef24fd319e","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-29667ef98b3f5bca5f681c85","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0deb807684d82cf80a5af7d2","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6e02eab7a3e609f6dd618035","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-83f1eb7d5def019910aba669","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f2174ccbca480f517cbd3ca4","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e90fea5b53cba5c187c6980e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3f2a9bc3bdb1688bb3f3d825","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2159cc97a8071f41f95b2bac","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-393d1ac80d2e548ca5be81d3","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-35844166e61bc0d5a71876d2","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d341295ae8ea744fc27e72c3","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6f800c82438e0951dfa9fdfc","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-40d49ac5b8305a87cd60dc70","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e7c14e2adb74037187f0ec1c","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-850a0242aec8243d437d32ec","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ef9a0693d34f00cba25d1252","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eca935ff02296892416ebe55","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5b692cff35fdaff8c4dbf68d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-96e3931bb0118e7f37553bc7","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4f0671e99c8eb258b957ac14","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a08e802836cc62463a64dce4","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b68a09f2b5c46d2ae1d93b4d","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-15c08139fc4d22bca2d29df2","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f50eede8d326b80321f28443","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-378ce00ff970314e97d7c872","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a4fc6c6ff3adc5d9f63e5f13","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a024960d51ddeaa1a98abbb1","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1b4c3991513f3ba7d226a43b","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c99273c2737ca494de2a88bb","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4e535ae7a8b06ef2cbfa9172","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4d1ffd4d663cda024c844433","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-656470dfae4f4b91de1cf550","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-502f63677ac7031d9e46c35a","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-af88304c0bd2108ce908a459","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a6622acee6854a8492d2d048","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-357d096335d24889fd34958c","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d205d81c52a64897f3ddf2c","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3e5264e1650bf46bf9444836","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e77cd1796c179d78dc2ff4d7","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e651b88f8758433c31ceeef5","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-61db091bb2c1f4799d64c0bc","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-968500870cb002c7a5b28066","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-31682b190232b4280ccd06b0","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd7582c72728fb5b3755e281","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-068a45e1f7235cccd90ff94f","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6db09ec2337dab314cc9e815","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-61761890b0724129ed2367e2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-372faf44f31cc0197fc03175","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3b4dca0a810d317164c9b966","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eb688c9af7ea6d23fe75bb6f","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1fc821825e1232dce70ea7f7","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5f71b89ede220ebd20a0c531","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-860ece53551bde0e2391fb57","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4e85d1ceaaff86a48099f140","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3677adeb13582e5bebeb40d9","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-16ade649934f26164cea7aa7","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9eb761881c53f420662c77f0","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ef6437efce9a4ee894b838eb","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7e46697958c6097bfdd5bb2c","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f91ef1733b24ae4b57da78dc","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3884a3a33eb9bae7cf35d1c8","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e5f6c6af7b7b6563cbd85d04","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ddb61e1c223050b01fe6a24d","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6f887f9f34bf0ced09693be5","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3130442bd69925da7c05ade7","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0ee4308b1b8e689522786fba","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6ca64d4b4bf1eb5d2a9614db","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e9a18d4e2485815fbe9dcb90","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7c589b3ec3b0735db386fb6c","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-46ee16e43dfcef55b9cdcc31","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-dd23f7bf3419e3011e2563f8","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1be1c1a4d35577ac29967650","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6dccf16089bfddf8511bc98e","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c5a26905a6b81729ce07eee7","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9f16b2319931415947e23f48","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1b3605fdbbfa24a01c0f8ed7","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0b801630aaf53bc41f3182dd","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8fabb53ed27c9588a99748d3","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a3b33640a7470089412d387c","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2e9188c4762961d8b305cb9d","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-edd291968902d4d1849cd16d","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-802d1135b4384df772d4deb2","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6edd971d60d57fb9f81575e2","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4556b91816ae6e8c2fc6246c","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0a0b1cc3b474cddeab9176c2","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a9f78e146b99566e8c8961cb","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-56a4d57c73bfc7aaac0a1a33","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ece90ea288dc3cb037efb07e","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f97c66befa16467a34a3d8f2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-85beb6c46f4ef1f3cb15eca8","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-da04aa901faef5abb22913ce","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-66a7edad755fbb5ac65ce9ed","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-430f81ce32b4f74a36ac8608","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-89ba0bd0c133f90bcefa0bbf","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7e1e202586c5c977d8ba4553","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-72a945c6670ce4413e2c9775","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-53a731259937b873fe9b238a","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a73cedae57299fa448f67d8","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-228b8932fc82372013ddad69","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7b17f5d1ffbaaf27acddab5b","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d531c1e72e94cbf4adfbe973","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d75beeb6ecb2a4aae441bdd4","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c9c58ab541711b7aacf86522","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5997db067bc91ad16df75ea2","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c494b83960b7daa2e65bbace","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ed41d716690c2b0b08f4b261","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7c980646387d7ffe0fbb8f07","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-026b7d686de16b86eee55e61","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1d9c88711562ca4bc4793bf0","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-77e6cef54a0db4bdbe46d00b","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-49a1a9a410cf8daaf0cf8f4e","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-025bcfd2e9a4b3b37fa9de55","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4a63a7797adf849e01ab6269","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5317018cf4f7cd8ae532c388","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2e71239f081d90f01235b7b9","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-21d30b7156f9abf0cc4dad65","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d7fb1cbe942c47c63bd72721","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ecfd0cf5293ccba5bfd04b78","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b0514842d51bae1d0371113f","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aa1c9bf038808a60c6fff323","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5e5c864b2d0837ecf9a3a2cc","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d73d21d7873e5d779a4c384","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-38523bc85154f445a6cde6ac","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cf1e57406dae14dbc01470ea","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-699ecb5439422ac056781a58","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6be68058cd3af8da1eca505d","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8a84c38764db6738f2389ed4","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9aa01fc84eae16b96abca291","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d01a35ef69f7df80895aaa00","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ce3efb571062193428082f97","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5cc0741a795c50acdfcdf9c2","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-0fef39ca040d37164c362ec0","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-607ac2b71c6861f6dfcf5271","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ca5efb697bbdbfd817a0dc54","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9a0cadd9cf939c95da4dccd3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8da717a8690707003f08a090","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a7ae39b18ff37882f52d61dd","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-e723dff4aa878aa3b1f555c0","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-64k","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f1903bf3ae7784fac180c5c6","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-a325f695a71ef6705d5a5597","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7aab7aefea402a837eb331c7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b76aa763373c89156231a6da","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9d65818b1f976a7825472a2f","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-fc47f8546d6a90f124e667fd","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-67097dc7f9543964f1eb66f1","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-99a523bc66fc8f9af24e40c7","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-bf109486b4ee154dd5bf538c","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2fadbe78a18174dfa36798ad","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d40d3cee5878b364f2758bf1","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1705e80b84b9b5b17c4be595","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cdd9ee7d07449e206cc9e3dc","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-high","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-52b264b698e93d9c6004f43d","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-cf093414bb1c79faa8013d1c","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-31bd5c440bbe0254845c74b9","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b6b4a2a1c5b5a3d4aa7ecec7","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-41dd83b36bf6c44b1f57ac1d","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2f9395d08746fc6829802981","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c3767e7e55780617f0ade91d","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1ffa9572fdf497d938c73d9d","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3ca3b50afff257eb11c4cb04","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5924987a533b33a47f789e7e","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1a10629747e118f97cfc0f67","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://livebench.ai/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eeaabbca375641a41f9d6033","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-df1f433349e12b715f87b8ca","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7aa0c89e21a5b4ba53c846fe","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8f5f1ae06f1007eabaadad12","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-462303d94f9258ff82feec79","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-6a5dad63f041041541673c1a","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8613396169af318add6485b7","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4b776aced4fe63c3161c7bb8","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-eeadcd73222785f2a270b0be","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-128f7a0af9b7fa3967594c52","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3e55e76525c8e98cf682c126","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7d9e8814bc198c5ebfeecf3a","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-105cf9d397ba788c03ce8531","modelId":"gpt-5","configurationId":"gpt-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5b22352026768409d27902f3","modelId":"gpt-5","configurationId":"gpt-5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-12e0ccd4a964c83e4b36650b","modelId":"gpt-5","configurationId":"gpt-5--effort-minimal","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c89e195031cf4c7684a9a9b0","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-b21a69a8ceeb7196e4fbdfc9","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9d3595bc411ad8842b5f1eef","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9f5fbd93e0f5873f7f2e34ad","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3158ebf36b887b27663bbccd","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-709e5e2b9100c29ff4ccf9e6","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-46441b51f4e16452b66da4d8","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-439f39520f3958e5a7901ccc","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-882148776d6b6bf196c8e72f","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c8b39cb9c7921b483f979a9c","modelId":"gpt-5-mini","configurationId":"gpt-5-mini--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8380ef3f8a50b6f89b396276","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2a5f25442a3b5295bfa02259","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9cfedefbaaad4dfb46e7ab3e","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-31ec105465e7a26d35da4265","modelId":"gpt-5.2","configurationId":"gpt-5.2--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ca4f23c7585afe314456c6ee","modelId":"gpt-5.3-codex","configurationId":"gpt-5.3-codex--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ef0926b5f5d004f8a5348da5","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-af6affc17d37d1ebceed5651","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-582529e031a763a72cb0c962","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-aa3ee5d91a696499570b9479","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-84d19d866a5f84d2e5157771","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-4e74e790b8c2ab2987cd3979","modelId":"glm-5.2","configurationId":"glm-5.2--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-91308a65440d721514f94949","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-082ec7a4e998253830c59d5e","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-03a4267243f5da43f4f0f916","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c4a47cfea3565c4484c1c8b8","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-d4309f168dc4babc6bc9d587","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-59f0399257b1743a621e4448","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-2e61455480fb766893d98afe","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7073ced98bba7f5b5d8c68cd","modelId":"glm-5.2","configurationId":"glm-5.2--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-f0febcfcf5b14d5f6f8f1b5e","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-1e3fa2d67e3e69ad184eb7a4","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-3f17e0eb43dae6ec089f2c0b","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-5d62ab6fe9c2e7d1f8fda50c","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9b20aa7050ddddd133712208","modelId":"glm-5.2","configurationId":"glm-5.2--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-7227c50a2326d0f76441e35b","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-79497e6cca80d008679179a1","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-8ea63df7cd359367585d2968","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-17c093bae14aabe9e7a0ba93","modelId":"deepseek-v4-pro-0424","configurationId":"deepseek-v4-pro-0424--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-9633b6cae80f96f07bdab378","modelId":"glm-5.2","configurationId":"glm-5.2--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-af745c954411352e8ff6dfe1","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-ed7429eba1da33d52494d3cd","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-medium","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"panel-c9c71176cdf68d6328da3f8c","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://swe-rebench.com/","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-26q7yB8XHAcmxWgEMFPMHP","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-272CatAfNpHUw44w7oJ2MM","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2AxSH8gojpyyzADeWfuSqu","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-2c4rvmf5N7QXTugrFLMZ83","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2CdomqtBVz2it7a2Zx2G2t","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-2fQJP3brRApfBdQq7Zy3bm","modelId":"llama-3.1-405b-instruct","configurationId":"llama-3.1-405b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-2gzNF2d53h2oCKDnojLtSP","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-2hbbp8z6PhB7c2T33os9q5","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2jTRxz7rW3B66a8smtz7Ya","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-2xfFf6KZAp2gUWYhHGkFgs","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-2y5jXmHGjyEyZvGjNDtRZe","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-2z7kL9DpfvY44T9Wo99FYx","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-35hRAbkceJM3Dpb2pWXnx9","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-37pJqPpXTE6ia9ikmmGPJ4","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3asQZd87VuKoH95e4x5Yfg","modelId":"phi-3-mini-4k-instruct","configurationId":"phi-3-mini-4k-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-3CGChL5vNDM6Df5C8Z8owN","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-3dXpsUjaVEbBN72dnw4Vzq","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3h8STJpG2VzY9LiBUzwotv","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3iRQkf5v7Wu7YuZhxa76Gg","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3L22tfAid5ZM42p92tqC73","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3mCgC7byPaZ3zzPM98bY5A","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3n5KDcBaKqJh3WTg7qU2rs","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-3QtkFWzSLzd4hgYGsNd5cL","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3UbYVQELDHAcQgu7sTTnRf","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-3UzTUnn6wx79jU3XoP7VFA","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-3y52KdaFo7gQZCccCQnNxp","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-3ZnPtGRJkvqHk8wvWWRgCe","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-452pB5w5ea6uy92e2q2NMv","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-4a3M8rRWUoPphCSr2dguXH","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4ACEC4x26HWRGiAepHGw43","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-4bLcFNu5zF6YuZf3qVKoHE","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4E5xGsuRMwMBhAfC4F2G4N","modelId":"kimi-k3","configurationId":"kimi-k3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4gZy2dAAT2EPZDGz5puD3H","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4hmmfwG9tgZJvKhL78nKzL","modelId":"glm-5.1","configurationId":"glm-5.1--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4HVvM9ZWKKPLQPcC8WYYMT","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4LjmaK4MRrxuDXUiZsvA3o","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4LWNorP8Fy8V8doxirNFcH","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-4MWuvJB4YXGnGz27Y74cqW","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-4mzBGLow3HkS8BmAYCzGTR","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4oSbA2RKFsfuAfVayAMAww","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-48k","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4QfM9qyeWGqNc8YTcQNV76","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, 53 samples did not complete. These were rerun until 51 of them completed. The remaining samples are scored as incorrect."},{"id":"epoch-run-4S3ZrJDkwh4gmGrmJQdvzR","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4S4GXbkRhLz8wWP97jYG57","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4uxDyWmq5f5azVYfWBGUHh","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-none","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-4vjzjypxWVWBVdAnwaDQYX","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-58eQmyCfPa3FufhXJFvAL2","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-58MQQiJ7vvgvP9e8LcG6eV","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5AijYw5bFJtSuahnbzNo6Z","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-5Ax3kMh4Lmw8KsrJVWbXqn","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-5e4Jp9dxtNisWx2wbRRZxM","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-5FGXKvXQwGPtcCX2PNrLR5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5FVmQUSS4uRd23f6nNgeRe","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-5kMRXeasRvtghXpDotCdgV","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5mmrBSQb7hVSJ9VYtNm46i","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-5Q9RNC2JfEmmvNFFE5CQCf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5sNRWemuVwb4adBaSwrLFf","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5u3LkMVq4Dy8CfiwA2EAVr","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-5yyuCCi2Dpfh6xLBMxqFyB","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-64rokFyL2L8Vd4SZVdayCy","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6cmgkNAQZekBr6e6rVdLe9","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6e3LDVuZwoZC4Sg7ushoVP","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6E989Xxeuw925T7cCV3XGB","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6iEkMa88YjLDgcde4bLm8B","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6phXzd4aCbnBUSQmBsaywa","modelId":"glm-4.7","configurationId":"glm-4.7--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-6pTYmQCw3EMbErvAqpivH5","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-6qgxJVk8HHLppb7hPqz9Tv","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-6rZFxNR3GjfhWey6DzEiYz","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-6XZAenohp9pCgQ3gVeUAi8","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-6YAzFq89fwWiJ3uJdptCMr","modelId":"llama-3.1-8b-instruct","configurationId":"llama-3.1-8b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-72DQVwbYiQW5pjhshjBaGU","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-79ZP6iwoBaF5t9a5VRqPnw","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-7aAKcnsCXoSumfAu8mr2un","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7cc6cDCXjsPjtKt36bbeMR","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7cL3BzoAaiHmdMNRCVLE6s","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7crLvnfQc987dC6mr3iGbf","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7czodbcgEF5zN68ppPFzBN","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-7DQNxGG5q6i7VtnzF7vNxA","modelId":"glm-5.2","configurationId":"glm-5.2--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7GiYWM7UagUsHpNsdymd4z","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7HWW3sjRstKzb9JpcnvLaV","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7iH4kjDYrjgRwQdKYgNACT","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Run-specific qualification requires review: Two samples did not complete, which is > than our 2% tolerance. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-7oUkeLfwMK3MtkSNHX6QPu","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7QkPRbRPpRx8nJT2ZcqSx6","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-16k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7RjsANKwwsePSstcZeSMhX","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-7vThbrtbczScg2UcsAYXtF","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-84ARuGyhQsjgh8umRmBvas","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-85fhMxLaebWtLoi6oLpTbi","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-86SY5JbPB49xXhHFQW6tHu","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-89zcekqEYnE8zhwG4pR5Nu","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-8grv57UmR89LXkEYhyssr9","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-none","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-8iiRQiAoCepDELQfUv3VDq","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-8o2J9uQLKDCTiCFwYdkJRK","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-8qwT2CF9U5zV99PFirnVsp","modelId":"llama-3.2-1b-instruct","configurationId":"llama-3.2-1b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-8UqaLobhmNJLuPGTTpeaCw","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-97t77hRrNae6Va8fBqBhPy","modelId":"minimax-m3","configurationId":"minimax-m3--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-99ys2jgQiPQ5UwrqnazfqA","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9cXtChGrowgGDwa9AcAecB","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9ekki5tJhyjmA7ZMLoUxzo","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-9F6GMXWPSzWo3evzcpAkTd","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9kErpmgQ42wTvgJaFn478v","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9kSgmUd9vh4CBXz3tJhctN","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9LWdzVN5w4ihNvncsaCWMu","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-9RfS3yHmzmP3azirghceFL","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9SSHEP95FYVZvHDdoHSRy3","modelId":"llama-3.2-90b-vision-instruct","configurationId":"llama-3.2-90b-vision-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-9uKmMPn6eiRPsfcLKod7M7","modelId":"glm-5.2","configurationId":"glm-5.2--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9WS6kHXT8XFtJWtE2wWLAo","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-9YJf2nviwjM6WVhw8qeJta","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-9zx2EXPTvPmxsL9qFCjP3x","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-A33om9MTYMC7xYeLv9X7Ha","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-a4uE6KgMhGSUjcnemRnbkA","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-a4uV8HMMBAcHXLVSmZfBgX","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-A4yUA9PfzRr92JAqDDo9ro","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-a5qR5FNnftfR8pk9HJ3JUz","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-a5YYZ3NSBGCUuALngGHhfZ","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ABT89ieSWGnGj4RYMduHiG","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-AczFCvkWR5SmdbV7eXruqj","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-adGE8rXdNuUFs96ioppbc5","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-aekViWbdqVVeXpEG5hrSbQ","modelId":"glm-5.2","configurationId":"glm-5.2--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-AfKJ2DGMhkjZmeFZxGoY3w","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-aftzew4ra4iax5D4R4vvfF","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-afxoicJc4C6caVDwUpsiME","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-agebmxGseTvmvN4AHN8i4m","modelId":"qwen3-235b-a22b","configurationId":"qwen3-235b-a22b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-aGRKHaq9uSawfYVpC565zU","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-AhtQ5ggs4pTfLDqHFjueGy","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ajQFZGMjvyMTH2ULDZhwtz","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-amkBg66TZcYjF26HaRAXfs","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-aMtSkxyLZPdf6o6f5zLP6A","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-AoAD5uVtgVDnXmwA7STuno","modelId":"kimi-k3","configurationId":"kimi-k3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-AoYLH4gxsYmhLYi9gyduiM","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":"qwen3-30b-a3b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-aPmR8fV49N98a6NVKpASAf","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ASLdzByzxxMxFeLc7dwTPi","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-awDKyKbPXRzBVZzfdQucef","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-axMdgNDC8UYYLnZYLHZpF5","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-aYau6EG7CCaWVSyVq3vvQc","modelId":"glm-4.7","configurationId":"glm-4.7--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-AZHoMLTNQEcKLwtv7QzBLZ","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-azk4theXxAsizmoi2HDD49","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-b3cBsiDi4D7NtisdffQqxV","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-B3Kno3buYWRYbZxU33STiX","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-b6yWmeFgsWeEiG9Qzs3NSf","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-b7Lw9ExxAhVY3hdExoh4MP","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-B8MaPUe3EYwUZASsNqE7C9","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-b9csPZ2c9CAsRXmzzfVoEW","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BAi4jidcT3F6reBkSXDJKv","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bAR85KQmEATQP8j764jpBA","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-BbM4xbJcS5sjrzZABGg8K7","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bbqokudairnKtbyjBjuWCx","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bBV5wCrrZtihrgxEsg9jPD","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BCCBjMXW674jF57sP4jf2h","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bCdwpRXgZtvQLYC4wA9JXr","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bcntamvGsSH6QgETdoaSph","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bDKKx7zTdW5WwMCfwqsLi4","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-none","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bDS2AGEf3AywbVcdDyAKZK","modelId":"phi-3-medium-128k-instruct","configurationId":"phi-3-medium-128k-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bdsZjrG4ayzP8NAJg5q586","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-beRGgJXTJggTi8PPEZNoZ5","modelId":"mistral-large-2411","configurationId":"mistral-large-2411--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bfftd5EzUK9yAekafEofvK","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bg3JRdd33iWfvRoGSvyXXE","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bggkB6SQyMaVNvB2Txr9Nd","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BgmrBFsbsaD8rNpebv49Da","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BiaKGj9CUTKhhNwW9SM4qt","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BJiQ8aRjMyCGPTBGYfBhyj","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bJV4D8SEo9zMJPEYTTXJNZ","modelId":"ministral-3b-2410","configurationId":"ministral-3b-2410--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BLjXudxuEyLbZiKBSZz326","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BnqWATgxsPzSF7ojBEMoG3","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BnX67AoZzgVbHgaM8F8Brz","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BP3KYD8rYyFg3LviNGtjLL","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bpZy8tAbh7UV6A6U7XZtBg","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bqiVinHXFcgyFGPstJwXJN","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Br3mjs2GrYcCwX9AMwcihU","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BSSNShjap29bDUHz4gA9oh","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BTeRdhgt6TFBj6QkGX2j6P","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bUATynSWVG53pxLCE2zeAD","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BUBiYK8WB8XDb9u7s9kTDf","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-buLf8Ne29xmzMZBRQkvrQG","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BVat526nF6NUGoVaLCp7DT","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BvShPsULJMkwxxf8vBSNfu","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bwak5Cq3LBthfoboicGZUo","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bWnggCv6to2QKSjngrtuos","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-BWz8uig4QyqPtke59pM88z","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-bXgZZgzRE3wXoSRUgrbsVf","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, no epochs completed for 2/45 samples. Despite several re-runs of these two samples, no epochs completed. All epochs for the other 43/45 samples were correct. The model's score was edited to be 43/45."},{"id":"epoch-run-bXrmQqzF9sXbuZfRrSc7NP","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-BxrNfyMffkVUq4n7U5eK3Q","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-bzuVVvmLtPCgofXqY7mTVR","modelId":"glm-4.7","configurationId":"glm-4.7--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-c2KVkMCWnpo6BbnMWgdaDH","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-c2YLifDU4zYCX5Jbi9HLL7","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-c5kpB4axzmygRywWqBKFmv","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CA5LW4phRnHSsZUGXEm8H6","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CAoLSNkdR27AmHb84fnr8B","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CAyLyhDHZiMQBZDB3qd8tG","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-CBbeMKRRSeRsXnvSfn7Png","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ccbx7KQY9bTD563vzBXwSg","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Run-specific qualification requires review: Two samples did not complete, which is greater than our 2% error tolerance setting. As such, the score has been manually edited to grade them as incorrect."},{"id":"epoch-run-CdmtwZ8NR8YeTXWiLVTRDJ","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CeDghdBk8CqtiFSbUzxNH5","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cF97JqHbFxxp7ePjYVK9HV","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CFBCC2QrkCAFBAvFj5pqPF","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cFbntXuxUtfreULvt7vEt7","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-CfmvbqzjpF6cCJQfzqdD4w","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CGac6TZg5qVdxNGULzfR6R","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cgnopvpB6mzsfb9yGnYK2z","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-chbh6XstiqtUa5W9zuyfjS","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cjUVqF2qQJ4qhFKBU5BQpW","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-none","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ckbZdkrXPwbFdjn6bmUQsi","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CmHy8cVECGkvQTwakfjRo2","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cMwETYmC6b4yKupyJfEHv2","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-coxYk5vK5cBhQ7iZohMtA5","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-CQhcUcXfPPJKuyt57AHZw5","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cqUZ6gcq2HBnShFRWvKjGr","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-csK2fe5T8p2R7WgoJUu6bZ","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cSTYZ3FKp5Mbs3xopn68NK","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-cUim7Aqc8ifJMM69uXSeSn","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-CVuujQbCY38ZStXnBcFex9","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-cXkPywkhy3NnW992ri73yG","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-16k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-cXn5zzns6VFwbTgotDwZjV","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-czNLsHc7tBqBWtWaoTSLXh","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-d23hYvSNGFo7rniLFyBWiu","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-d3m9Xip8cof4s77z6LKkEh","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-D3mtasTumfvjR4fjmnHWRy","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-D3YDUZSfEUDsS4frLbEKDu","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-D5cbXacPnJ8akq2jAtifEQ","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-D7WDyCr24AVdzr4eKAreJu","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-d8egYFK9XNSEHWvv4JFxWx","modelId":"kimi-k3","configurationId":"kimi-k3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-d9jMGFp8BwebW7sufdxbnC","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-none","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dagNWyu57ksu7gB7Q86eCx","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-DAyGUk5kLRdwNkSPZgqmos","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DB8ja6pEZWGocQbdciyisL","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dBHxnnTzLGz3nHis5LET6t","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DCJQMqipndGxwMXe8BDGeg","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DDfYPyKQW7vgDtGgkwcKSi","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-none","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DGEzZA6nvTne4MEGSuo3Tm","modelId":"ministral-8b-2410","configurationId":"ministral-8b-2410--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dgSJTFQ4UtuQKEhB9ss6K7","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DGSmhVxWsi7chsuKS64VLg","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DhJ248BX3ZPBHXvkRG4Qsz","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-DienatPbgfgn3EzM7Gvzxr","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DiXCMhdfhcjaCUSzYWgACy","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-djbbEqvBW9qux3pZwcZN2i","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DjFkVt62QwqQ4xXwzYR5Ng","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dKCWFaoGCWJTnD5CPWQGru","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dKZDn279PKuc2Kxm68D4r2","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dLDBahYBTGRNjbsXA5pyr3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DLvSYBHHLcHECeL5SpNgVK","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DmdKPD9Z9RXwYyATAoG4Uw","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-DMei2tkTbCqecGNjYCYYoW","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-DMjUrG6eZEqwcQ4SqUoViu","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-DmptTSPXx5uM5TYZoV59JT","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-doNrgGQY5SytQV22WRqw5L","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-doo2bL7TEHLCNNMwf7NbYN","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-DPwt4tRRKyqEjPE8Jc2Co9","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dqgqP2uEPswfECCVj2Kbr9","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-dQhoYvW3Wz2eZSZ89K6igd","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-dszRh7ELyCEukWnwYnUxMp","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dWG8tET6WnzXeT2WjcjWvT","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dWndu92zERWxzbpNa4BdJy","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dwyb2yzFewGT6w6oFdVMAc","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-dYYtcwENFRtm9jZTDA2p9C","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-E28uZiJvrPgKtawbJpoZQ8","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-e8MXnAM8HMF8eEzYtYA7xv","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EatRQnSaUpUwKzdtjYnQHo","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eB9e2mtd5nRwqdFyLEsz6k","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-64k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-ECdG3m8n5ABfWVZ55rPFmT","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EceR3NeHzSxacdmAmfRxgT","modelId":"deepseek-r1-distill-qwen-14b","configurationId":"deepseek-r1-distill-qwen-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-eCq63CuekohAswYftWXJVj","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EDFusDaaFkh5n2MqKNxMBD","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EEGf5SDiF8jXB6NX7eR6Sa","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eiLEpRUvK48wUKDh4sYkzV","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eiTYduCDNq3HgwTg4ZhEw6","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eJBzZyT5ohb8ieaJCum5rK","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eJvV6RezECZwh3b4ekg4pm","modelId":"seed-oss-36b-instruct","configurationId":"seed-oss-36b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EnbN27oUrNyfbxuPwtZey2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ENc5ZM5TpBYNKkTWN4xyQM","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ENh7ZPQj7ihBePjsC8a7HV","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-enhRcQmfN6RFB2zu7R3Uxr","modelId":"gpt-3.5-turbo-1106","configurationId":"gpt-3.5-turbo-1106--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Eo5cAQJK28CHpKDfCSDYG4","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EoSFpgFhJB7iDPLcMNuLH4","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Epg7eNLwwGPXtX3sSAwPf8","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ESnXA8LqMqhjcsoWQaMLVQ","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EtgrDq6ei6kZe8K7QbXUe3","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EUknGXXh3f2mHtv3dTufLg","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-120k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"epoch-run-eVKA2eavdRAbSN6AnzyBxA","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EWAyxFsRUvuu4NpmmLqWkn","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-EXpHB6kFqDjRfG9A5LsDf6","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eXVWr3RBeSsWy5DAU8ed46","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ExyL3GN8s34tizrXV3VmS3","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-EyKecrMhk7Yx25e5HGW43i","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-eYmgjYJfM7Utm46nfoRfZ6","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-EzMaDdXs4YQTMLgppBGxAb","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-F3CtjUceBrMi9iYmjULx7J","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-f46NQY9jSxyKqo9qzrmk6F","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-f6pnAATjxmrFJS353EjQKi","modelId":"deepseek-r1-distill-llama-70b","configurationId":"deepseek-r1-distill-llama-70b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-f6ZdMtRpdfskGbrBCzrKSn","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-f7BCT27LzcAtaLDP2tcrWF","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-f7dotY9NheKNKK2zz6bfKZ","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-F7v3JtKFb27j2YVmsndLM5","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-none","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-F83pa7Gfsb4UNVttTnS5Hk","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-f8Pac6hqib4t7x2s4HCRoT","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FA7pM9hKdkgTXmGHptcno7","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ff7GeS7rdperjxSBZ7MHZY","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FF8iU7vP5ecg6PdvDyE7XG","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FfAvNS5H9bMDSBF4JNNiDz","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Ffoxqm7YsZr3FimCGsGAJv","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FGEsLTxzZ7fE9aq7DhdqZb","modelId":"llama-3.2-1b-instruct","configurationId":"llama-3.2-1b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FHZCKbtfvpKGXU99vZFnXN","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-fjgo9DvKNgVAGtitPvgpY7","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-fJKhFRm5dn9wzbXojee7uj","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FkywQ2KS4AkLPzjSPmhHcS","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FLDt53waLTeshC7PK9uVy2","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FNMbfvEEm9PRnrJnrqk2PH","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FNMFJuzKKuNsWx9gQoLerW","modelId":"llama-3.2-1b-instruct","configurationId":"llama-3.2-1b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FNXAt76ZUS3sWhQDFMga7U","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FoMSS4FmH3VxpsvZiUJPCv","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-fPE4Zajhq5WfccSxEYXXR7","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-FQ3Suh2vKacz7UNqJybTWk","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-fQjoHKyUEPAuwdrBGfL8SG","modelId":"gemma-2-9b-it","configurationId":"gemma-2-9b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-frszScNxpHXXjSHawCt9Zb","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-fsZmzw8jjyUgMQGwxodBwN","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-fubPj2m5aKLCeXZAwb3xeD","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-FUE7jUup3RsXiXpYTjMKb5","modelId":"glm-5.2","configurationId":"glm-5.2--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-fxwRTtt8bLV4DNutwtMEox","modelId":"llama-3.1-8b-instruct","configurationId":"llama-3.1-8b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-fzoUFmy77NpEDtXyA6w6ap","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-G3dinPvwrci2Nu3m9pby2i","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-g4bbCaiFDqw2YYNDAcmn2a","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-g4iGoqwjeF5vqkdvtyytx5","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-g64kPFtWB7Adto8Y8Hi3XE","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-g7czyLHudHegzP9yRD939X","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-none","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-g7dXwZH2tWvqLg3X5idGs2","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-G8hwpomZQaMniWH5XUzTRe","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GbQrTQyihBUsb9sxbqT8pT","modelId":"gpt-oss-120b","configurationId":"gpt-oss-120b--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GdfzaHmiZht2DKPZDtQAET","modelId":"qwen3-1.7b","configurationId":"qwen3-1.7b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GEaAdb9UmoUFbEtBx7WzAR","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GEwyLqZT93Hp55fdtHrJhm","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-gG2B6fLUDBy5jRraxL2pz8","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ggG3n6WVPZn7Gu2RNyfQbK","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-GGpgwGRFVATVJdQr8TgRc9","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-GJ6YsSuzyRD9YXe6SBwvsu","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GL7htq7XRnbzqpAVK5f862","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-GMngscbSmqoPbGZWNv2Jvw","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-goZR5yGxZic9TZ23ezCL3w","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GQKsxFbdBWB546zE8ci49f","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GRQV9Q8gHoHnSEPWofiQuq","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-gRRQHECkYhz5UaYsRKDh2F","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Gs234P3jzGiLm68KjyzYZL","modelId":"deepseek-r1-distill-qwen-1.5b","configurationId":"deepseek-r1-distill-qwen-1.5b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-gsBidnvEcmCfLnn5sxePtk","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-GSde7u2Mb6GZGpubJjjPam","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GThtce6GAmRAS8srQyGQoA","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-gu39ndv9QxWP3NRxSUJRaX","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-gVdraDT3pXmaExP9VbqME4","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GVm7khGvtdnQKGfkgAHD8q","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-GVmgtgKMwEqc54f3jA7auP","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-GYzmrzMfeSjNjm2J6L9PeT","modelId":"glm-4.7","configurationId":"glm-4.7--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-gZ4bwozTKtpmZTqnqX3a33","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-gZERSAQwxBAevQzBsWfUie","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-gZMFRbVKnBmcnZU4YqqKMN","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-H2FvRXagQRQmiNa7WrNMU2","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-H3E7EjjXfGCPnm9ooLdmAo","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-h9aoDxyWEhybvARHpyuoco","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hDESmyGFrbZDomjff3rqzD","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-hFRxCUnXRNMcpQzUy8GYL5","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-HhiYxEx3Bf8YDPUh34K4DC","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hHnQVatVTbQjM4sfrjw7GH","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-hL24cexf97QKVLsv73H5TT","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hnP6Z88x8bPEBRZ2PW6kps","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hrRSYo5XSFrcs9fADb5Hox","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hVifTUdQZrFEYabgCRu8Qq","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-HVtbACyemDaTPW5XUDC6Jf","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hwrnvtEbDAocFtjcsHqsQh","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hYATFPeUnMq7Std2nLUVAJ","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-hYeysTWbJLkxwBrENz3Kie","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-i2ZUgMREKiFAnE2M54w3Py","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-i62SEaSpi6GbBmWqEDSDmV","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-i6i3gQf3ng2aAipvowPpws","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-i7MVHsH5pikQKjYn6LBqHS","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-i8CTho47u9qDcnXF3psREo","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iCysWvFJevNyw2dbYosU6J","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iE9NNTJWbGpRia2fUVGkPf","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ig7gQ23WRms9SQLLNPtbTi","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ii6JE9j57eSbuswEsJArTa","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ikUWdu6HJ2qRgZynfzDCFe","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-imPXZhfTfq9Q9G2kq3stdg","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iTY94tKhVEcZsUZivMwLJa","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ivr2LfmdZoCMfLME7jh2L8","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-iXvqUzwxAiA3Rg3dwnutFs","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-J2kUEjR9r6Spd594qDNTTf","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-J6evjTMgHkrun8txnEvzdN","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-J8hYKbXiGhetQRwu5bUSp6","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JarZHkwUMZ6HuA4ArMNT45","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jbyVWnEvvFVNNc8AEF6WcQ","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-JcgBDysccQrAnWQaUmoehs","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-JCMjXU6FRiiLV3xvs9R2Xv","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JcQMgXdZKU54u52B8TGQKp","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JcuoAWhcnngPEZBPmiUyLF","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JCwFm63cUipLHBfM6BdssQ","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jD6rJdvfNPErKEz9qkpssj","modelId":"gemma-2-27b-it","configurationId":"gemma-2-27b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jdFH2zZdssYKDVJQPKXvNB","modelId":"gemma-3-27b-it","configurationId":"gemma-3-27b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-JebA8dYLVov6H49ZQSLXh5","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jFJucVunfLgoQqoFvPVQWP","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JfkPdo29um2NkxdhT79AK2","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jGgkDRHbodcaTzQ3Mp6SxS","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ji3kMn49Jcr9t4whxcpjj4","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JiqgqBTfkGx797uowZgJbk","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JoraLb9y55QXpMg4Rrmr5x","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jrawnM2wHFbVfJFJsap4kS","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jRiWmBxtBAyiXiRBRMY8wX","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jtfdCURnwfZzak4BSiBKzx","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Ju7pUkkwYVj6ugi9Ri5Jjp","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JuM7FArkmhLqqKBqudySsC","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jUmmCNezoW7jWiK72SVCaP","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-juNVfKBcYTwaKnk9GRA2zL","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Jvdw6GAXiS6T79bkpbk6Ra","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Jvt5BNr4ERbE9QGgMcEbmT","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jWHk7BTYHQRXk2rXCbnpcS","modelId":"minimax-m3","configurationId":"minimax-m3--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jyCZnpXG2bh9G43X8pT75m","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Run-specific qualification requires review: All incorrect answers were actually cases of the model failing to submit an answer. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign a score of 0. Then we average these scores across all samples. The resulting score is 44/45."},{"id":"epoch-run-jYiGAFfUQKJuRStPzU3PX3","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-JYuFdyZZSiMvmSZNzMTywb","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-jyWVTGV3ZXhotEFLLGQsKi","modelId":"minimax-m3","configurationId":"minimax-m3--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-JzDofpJXt6d4f5kbRMSEmw","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-jzqDbWHvQXhMkpYHfTjnRE","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-k4zGHaXESxFRTRMkyDLZrz","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-48k","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-k5CCeHstJwo5wKpbMFZtfw","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-64k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-k7EnhoBbZyVFUVRBowA5Pm","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-K8zTckSXLKLesoLBv24TWc","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-KAPGpH2CLMafAt8MnAQJT3","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-KB62zrQQ5ccd7hCcUwkX8j","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-KbUNQf8nnwPa8ixg6AnEwB","modelId":"deepseek-r1-distill-qwen-32b","configurationId":"deepseek-r1-distill-qwen-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kCQr6ARwJyUfkwWqKAfuDX","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kDNNbUYXhrAH5uDBGykFaf","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KesKa5EXtFG7H4UMBFzgCh","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-none","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KFAFU6kX7qVekqq6QR524K","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-none","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KfQKr2ibCFMx5xBELoiM3Y","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kgJ2d6XbKj3dZutDcBYSKU","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KH7KfZvFc9kZbqiJFdfYTc","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kHUvo7vG9JDf7fQvWpeP7s","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Kk4oLoTLyDuqfnbqjPSvgZ","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KKm5DbPUgXo88eYr64g4SK","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KKzu5PGJQTEtfgMTqe7pnp","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-KM4G49tQZB8ce67RxYGyMy","modelId":"minimax-m3","configurationId":"minimax-m3--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kmHbjBrwGgEKNr65JrXcGX","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Knij32Jp6bQJ2V9NHpg5VS","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KptKXK5nE2Ns2WbiaSSnbc","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kQjrYCaa7yYyMXofeR23Dd","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kR9F3oHBCnwQW4AiTPKwpd","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Run-specific qualification requires review: In the initial run, 3% of samples failed to complete. Inspect defaults to not scoring these at all, but we override this behavior when >2% of epochs fail. For each sample, we average the score of the epochs that did complete for that sample. If none completed, we assign the random baseline of 25%. Then we average these scores across all samples. In this case, the resulting difference is very small: 94.1% modified vs. 94.4% original."},{"id":"epoch-run-kRPSnHnDdheajNdqmKsMjs","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-low","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-kwT2PhMLMheWkxaqwh8PKq","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Kwwo3UFcPDk6iLAeSeeRaa","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-KxvHAT9SV2dTDn7jBnTk6f","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-KxxB8kDa9obqrPuec4PEiv","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-kZ3VgrQJxfKQ5msjpmSaAz","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-L7kW8yxFKCjVXhxNnt3VTq","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LcttjHHzTyAW6MqNE29xiK","modelId":"qwen3-8b","configurationId":"qwen3-8b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Lgy52ZT4YpFrUqqKVu2qUs","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LHRL6nQJZXGJmYppR7kbGw","modelId":"llama-3.2-90b-vision-instruct","configurationId":"llama-3.2-90b-vision-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LiRiryJsGb3h5UuxX8bmJv","modelId":"deepseek-r1-0528","configurationId":"deepseek-r1-0528--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LjgJoDosTLkiGVT59smA7q","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LJyKf8Xy4dymxNHbGLwNdA","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LkVuUxvsHNzpcg3sUiH7f3","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-16k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LmRxqPrS2Gm6Gq2cSNc92G","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-none","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LPo74T9L3CawnKX5LLUrSZ","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LSKDetgzyVojru45w7RJhf","modelId":"gpt-5.5-pro","configurationId":"gpt-5.5-pro--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LsnPrukDADRTP8fsn8zD9S","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LurNQWcpKjLWQ7AXSD6Ab3","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-LWbCXNGMXtjQYxyM2uoFMV","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-LWkDtkmd3TNmLzMhfZD5HW","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-M8sY8vHnvSLxQUg3HTMTCp","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-McJyXLHBzx5VjAqXjmrrsb","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-MEhV5sh6nbM8cKJGQ6HzcS","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mEkZaYpiurQ6TEMAALK3su","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-MEwMcmSV32JHrsNoAq4BFL","modelId":"llama-3.1-70b-instruct","configurationId":"llama-3.1-70b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-MFTd4BUbtzbfcCky6d79d4","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Mg2yb9Tp3yc2H3ApJX6JBK","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mGXYSUNCMisvaRzhQp6g2L","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-MHAMdn52f7wLMZ6MSCs5E2","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-none","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-MhqeuRVx4JcRfxPQDYPq7Z","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Mhwme9odWJMzMjoYkW8r6B","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Mifz96Jm442bn43Qnxj5rT","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mKhVMEicZeGjdvJdTRd7mK","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mLLmVVvo6t23MM5yxq7ryW","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mLmUnBuX6DYKtb6x46GteM","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-mM6vdJpgjLY9prnetXzZJS","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Mmbo8x2A3WpafV5D6fvS7v","modelId":"glm-4.7-flash","configurationId":"glm-4.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mQ3UwD6hUioWSp2s2oELY4","modelId":"gemini-2.5-pro","configurationId":"gemini-2.5-pro--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-mqsc4vFuKtAHXxbYyX9WwK","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mRAASXsUuoJmc2oR5G89zR","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mS5EwCRZVpvUvJEehPUDZu","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mstwSH7noJfvhGcd6Lz5kd","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-MsXAXDEKP3xBKtiA7aTBBG","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-MvdunHkVURna3JuyDjhzEc","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-mvNb3hNgSZ2gS6jHMtvCdk","modelId":"kimi-k3","configurationId":"kimi-k3--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-MVZf59jt9uEoWG9w5W9apB","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-MYGuFuvkWEwLC7US5UR363","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-mZLWt2JSYvJyGhMvji7CT8","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-n4hyz75SVpwPEisKVVjvNg","modelId":"glm-5","configurationId":"glm-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-N5beL4W3WahAubJgDKivnE","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"epoch-run-n9gpXfUzo8SbWqvrG2q4xM","modelId":"mistral-large-2411","configurationId":"mistral-large-2411--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-NaNEVAYahYyobdLPgCeNK9","modelId":"gemma-3-12b-it","configurationId":"gemma-3-12b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-nb9LnDeeQyvRCqsbsTANGD","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NCikvVWc5SEyMEbCqvVNb2","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nDsNFM5ioGzyWcpeUKVotg","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-nE4hmJo3QV6X5jeGWAeAze","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nEJGtXGN588zynPkynZkxz","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NeYuqgQyWtFWAHEjQYPm5Z","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-neZvEzLi6yeL9z5KjGef7H","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NfN7VwMPjSVqViqrBQPWk2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NGhhhxcbTVcftKdk8S7rAX","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NGQ4Q8Wrb4aroMu5RecTS6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nhim2QCRgpir5cZdqrmUz3","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-njpkLAWZTvept6tnkraYrR","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NLiiJJSyA9wmg2FHENFpAq","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NMdaAXyqqPRmWfuxZUfHFF","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nrh3xa3Bn765Q6DXWoVfbS","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nSb2focDRMyPJXErk3MV94","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-nSLGeLNawfzhCbR33agwer","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nuKCgZReCBsXKCkNj9bK37","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-NV5tAZdTHYzP6F6Ym4dUus","modelId":"qwen3-32b","configurationId":"qwen3-32b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-nW39ZzuDQ3xTAGVoEfFG95","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-o5th8Rb9WiaDbv4oEMDoFa","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-o6migB5WP27uLr9nUWpCiM","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-o6VtA8qruLpoShhPy2JdLg","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-oAu9CZSNPZgwiwKnoNpM8Q","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-oB8tcqTgWoZYX7BTFj4c8v","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-opus-4-7-chess-puzzles-prelim-lower-bound","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Run-specific qualification requires review: Opus 4.7 hit its max_tokens limit of 128K without responding on 31/100 samples. We intend to improve elicitation in the future, and this score should be understood as a lower bound."},{"id":"epoch-run-oU38rqq2TvJTxvvPsnEQsH","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-oXZ7ZVZtADrwFPKAe6zTvL","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-P4LXQ9PyDDziEANMB5jVRd","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-P5L8qbXo42vTvbU3UvTNjk","modelId":"gemma-4-31b-it","configurationId":"gemma-4-31b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-P7kyrA6oQ68tVGHyekP7Qj","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-PBRdMZyz4L4CqPpXyLD2Lk","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-PBrQpAgRCXeUSNveEn4aDE","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-none","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Pc6CyTEYKbcdDUDKzGZnS9","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-PKSMspJiJdNThB6qNvaBSM","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-PPbjbUncV6qa9jNRKjYrfp","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-PppwnX7EjXx2SeTcFN8Ujn","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-PtxHF8BH8WuNdNfDnutGBb","modelId":"qwq-plus","configurationId":"qwq-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Q3WpHdurYNvawj6ycXyj6e","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Q8RAfong7NRCvww73BB3AT","modelId":"llama-3.1-8b-instruct","configurationId":"llama-3.1-8b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-QDZRoAVaEDtdS6nECEeE35","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QeVP4X52JBDZBdeefZjEmb","modelId":"qwen3.5-2b","configurationId":"qwen3.5-2b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QHfAMMDjjzQF6xitN2vBbA","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QJ5rJMVypB4PMxPcBGftc8","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QuqPmMUTbiEsUvoFYZx5Mk","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-none","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QUuykbQhKapHn3gjLFjTam","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Qw4tGw38pk4sdsEehhrLSR","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QWw65xeTn8x42SymMsVREN","modelId":"mistral-medium-2505","configurationId":"mistral-medium-2505--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-QX76VGMs6CYv9BGBKMCCNW","modelId":"gpt-oss-20b","configurationId":"gpt-oss-20b--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-QyJe5cEG4rYmwvZv9b3oyG","modelId":"gemma-3-4b-it","configurationId":"gemma-3-4b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-QYZ6wRuT7WMkaYPKc9dRPy","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-none","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-R2fMFAtRXah864hMifdQGV","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-R9XpD2PaYpPiokjjSWnMYT","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RA5MRbmWJpFPR29BQxfvZt","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-RAwuPRwJedy7P2KeQhEmr8","modelId":"phi-4","configurationId":"phi-4--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ReDAtJGGfRtrEGGWf4Zbsd","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RG2biwnmGybSVTVxxMdRWa","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-RiyrdXiqrXT98mKM9nMsmu","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RMcys99fv45vvgTgakXXWn","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RMeUVa4tq3fURqCMtQWkfe","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RoscWx4NUGVqcHdko6QhKd","modelId":"qwen3.6-flash","configurationId":"qwen3.6-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-RWjuCuVGvaRd4vDjJJ6aP2","modelId":"qwen3.5-35b-a3b","configurationId":"qwen3.5-35b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-RXsYuuSedkYZ5ubc8swxGp","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-S5pm7ctk9zgPfbyHrbD9AV","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-S5QYXSvQBRSbUbXSnAGbMm","modelId":"llama-3.1-405b-instruct","configurationId":"llama-3.1-405b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-S7wbot7JR53BAjM8F9gaws","modelId":"qwen3.5-flash","configurationId":"qwen3.5-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-SAZy8rk2HgyPjA8XZJFUmR","modelId":"qwen3.5-4b","configurationId":"qwen3.5-4b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SB6Qj6rCBDk8jZmFcCTzWc","modelId":"glm-5.2","configurationId":"glm-5.2--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SEePRKRcv8oqn5HpD2KFxB","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SEnvgtunRa5GwAtU2sHa87","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SFKXCPUu73mwxMoUotiZM2","modelId":"gpt-5.5-pro","configurationId":"gpt-5.5-pro--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SH5jr76ni3RnpXVMETMy2H","modelId":"claude-opus-4-5-20251101","configurationId":"claude-opus-4-5-20251101--effort-thinking-16k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-SLJyD8yew4TxcmprJfVvuE","modelId":"qwen3-4b","configurationId":"qwen3-4b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-SoCkYbcxzkYHXqcqnEQwFN","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-STxFZiSPAPScUuENvXBWLc","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-SX5FCWMk3HF83gGsP3WFA6","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-SZDgstFQJAGeGQwMXgNx6w","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-T2wFfuSkUdyjpyqurxNmNK","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-T3X5DeC47iqCaoRYXu5k8L","modelId":"llama-4-scout","configurationId":"llama-4-scout--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-T4y4iGHMqA8tXCdBKr5GjS","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-T56N3X4KLA3xz7tf5aCMGb","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-T7KJtht8Fesh35M5ayMPnE","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TAGZYToqgQmFZr7uYL4rSF","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TDT98jZXHbUMFYTphGEpqC","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TEVNDC9QXBh7PQvX9kHZip","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TijCafTTJUFrJ6jPGvBbgq","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TjoS7sNuqVTc4LVyGRo4wa","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-TMM3rPrAHcpBG5Pvw9kr4L","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TpHYtuPG6kYZFvMK7Z6Hqj","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TqFmiGvqozt7TSZYmhgF8m","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Tt8tBXHoCEYqGLePWXkM8u","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TTuCPacMDpNaCSs3Hpbdjp","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-TUPC8VdX4jApFa4MGfNP4t","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-thinking-64k","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-TxXS78Wg2pSCDbpmeJuzQn","modelId":"llama-3.3-70b-instruct","configurationId":"llama-3.3-70b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-TY8R8FV7zCwByEipkqyg2P","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-U5PsUdX2ak4kJ2hgnQkWnX","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-U8H8juE3Ko83jsR6TRntbh","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Ua5RK6JRxdyrHRa3hVFQwq","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UbTx6Qbh6T2uXoQbpGV8i3","modelId":"gemma-3-1b-it","configurationId":"gemma-3-1b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-UgqBt5cFjsC96ALwiTFCPR","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-UhmACN5spAPyAtWWBf4MAP","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UnKHyc2idtTmoTUGxGeNJV","modelId":"glm-5.2","configurationId":"glm-5.2--effort-low","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UnRUSuZzm2X27TUbpeMPva","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-URoWjw9Htc6QPwABVcrybw","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-Usx9KaiXvHZU4qrzgc4sLg","modelId":"gemma-4-26b-a4b-it","configurationId":"gemma-4-26b-a4b-it--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Utgs6DuaQDDdi98ZWH22qL","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UTVSgirxQpTgmTHbgE9EUk","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-UUq99Qhq3qizcoJo5vdhuK","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-UxakyoDNbLKtxnxeMsa7cU","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-V6YuGpcu8MCbJNXKoJMA6b","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-V8VuDYREHNne27eUQT8gir","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VBpT2WWYKBZtUxG9Z3svGh","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VcuyQvF8LWuYhQCx2FGDHh","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-low","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VFYhE54autgdYcMJNXicwU","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VGeF8Xac4WcSAGgSXVdEBi","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VhBM9HgJ2RuSVwXriRXMVJ","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-thinking-32k","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VhQBa9AViRt2UKSNpEAyjN","modelId":"qwen3-4b-instruct-2507","configurationId":"qwen3-4b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ViC6pxQZUVS3E9M9iEubF7","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-VJezHrJ5YPCbpui8pZgcJg","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Fewer than two distinct model identities remain in this evaluation"},{"id":"epoch-run-VjfWxdhdNerrh4huSHT8PT","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-VonoEhAsGSJ2FHU33qnhui","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-VRLKwMA8hJnNRpp8M3WDCw","modelId":"qwen3.5-397b-a17b","configurationId":"qwen3.5-397b-a17b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Vw7spGUnJyf3vuzSjTcj2F","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-W6mTanyjvXhasFBzHukv4S","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-WcCQQSHTFAhXk6qCWEeSLh","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WeP7Q27N5PzxSgg4ybgijX","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WfaJS4L7Xdz5ZBXgJMbRGb","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WgjFZzojpiv54XqUhvfuUG","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Wh3JxFdvxP688EWwE3t2Uk","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-WjXdTPMnJUAT27azUKo3Ka","modelId":"qwen3.6-27b","configurationId":"qwen3.6-27b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WNE7cveVN8rsi7DmsFsFVy","modelId":"gemma-2-9b-it","configurationId":"gemma-2-9b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-WueZbBM3NwMUZPveuagrZo","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-medium","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WYs83xB6NwrkMNyQJtuMcQ","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-WYTWr3Xk4qxymhMsm7vRQ2","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-X29V6KG3aVe5Nv5r3tsLHX","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-X2tQXGELXtEbc2VX6gARd7","modelId":"llama-3.1-70b-instruct","configurationId":"llama-3.1-70b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-X3HfncZtnLKUPoUuRc9YsR","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":"qwen3-30b-a3b-instruct-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-X3RxRkt2pBUXYJjAQHsUo6","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-X5FL4gkJQYjzJ7axz23rfd","modelId":"qwen3.5-122b-a10b","configurationId":"qwen3.5-122b-a10b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-X6WHjwmjSHe7pF8R7F3zsT","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-minimal","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XaGuWDxPtqVvyxqdMncKFj","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-59k","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XbtWdvRz65dbPPnHcSBvmF","modelId":"qwen3.5-plus","configurationId":"qwen3.5-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XCSWtbDquA7FUiWfd7kh9q","modelId":"open-mistral-nemo-2407","configurationId":"open-mistral-nemo-2407--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XfjRkSyP4ub4gDsWcgS7KY","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XGK9DjJHHVWr2LyT298ooL","modelId":"qwen3-14b","configurationId":"qwen3-14b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XjFqou6MyT2XLpkUsCrgxM","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XneEig6pACkAWeekvgCwNk","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XnQVH5qSfxVjpzoPwUEmnh","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XQEGUQjpXupjdyKoGuSmum","modelId":"claude-sonnet-4-5-20250929","configurationId":"claude-sonnet-4-5-20250929--effort-thinking-59k","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XRutLYUVUePe69APTSTw8S","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XRVSYnR4bhQ8Zb62Un7GrS","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-none","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-XwemU6ABotEuG9o5TRLG2r","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XWpHpVPCaVjcwPpdpXuuGH","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":"qwen3-235b-a22b-thinking-2507--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-XyVL3VffJ6UboY97vxpohL","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Y39ZRp553ULpUDBV2XrBbc","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YBMTDnW5LmCN6tBp2QYHzi","modelId":"qwen3.5-9b","configurationId":"qwen3.5-9b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YBqiCXPjMUSAgAjDUoz5sy","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YC2u9wykbYQg4gdkf76j26","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Yd3YzZmLa8D7eiZWo77WSm","modelId":"deepseek-r1-0528-qwen3-8b","configurationId":"deepseek-r1-0528-qwen3-8b--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-YdcyYXLzqfPUSSgGv4MTED","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YDQJAMgMjLaikPkeVDbAjr","modelId":"glm-5.2","configurationId":"glm-5.2--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YdyvoMQ4mA5V8Ymg6Tksxu","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YFmtuHAcUZeGwPBe9Jbcxw","modelId":"gemini-3.1-flash-lite","configurationId":"gemini-3.1-flash-lite--effort-high","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Yhds8GYkCXWgRQhuLiURua","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YLAk5J3Wd8EruVXee8bAQb","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YRvn36dmMyDbS5e4XkF4Xi","modelId":"qwen3.6-35b-a3b","configurationId":"qwen3.6-35b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-YwHKNFQjbat97wVLqachmi","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-none","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Z4xfwTke5pR6RrY952bttA","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Z5FAHm8aqmk8NUUm7tojng","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Z6S3nMC2tnkpKUixCPLiDj","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZavSMMq9jk5s9WSbARZr6X","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Zb2AKwa942D7dBTTcebAba","modelId":"grok-4.6","configurationId":"grok-4.6--effort-xhigh","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZczEhu69FQ9Cnns8NT6ew4","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ZfPv4GCnueHrnaoV2dBdVw","modelId":"qwen3.7-flash","configurationId":"qwen3.7-flash--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Zftz2yk4X5NF28JQzjN3hZ","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZgU8BagFmaj7BE94y3JDZA","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZjsXQpZ7SsejXDo52aetZZ","modelId":"llama-3.3-70b-instruct","configurationId":"llama-3.3-70b-instruct--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ZkNQ7GER7Mc9FSPmpUzgKH","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZMRExFd2WEEwTRSQPLXXwu","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ZQMcTQjHcDSevCN2dYYHKY","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-low","sourceUrl":"https://epoch.ai/benchmarks/mystery-game-puzzles","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZryXhNUpPedPvGhbqdNBEw","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-low","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-Zs5fCvNzaz8LhqgwDSAztU","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://epoch.ai/benchmarks/simpleqa-verified","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZS6cAYkdeNAeRNz7AWQ4LR","modelId":"magistral-small-2509","configurationId":"magistral-small-2509--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/chess-puzzles","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ZUJxsJDpHnLXxNiDcvj22W","modelId":"gemma-2-27b-it","configurationId":"gemma-2-27b-it--effort-unspecified","sourceUrl":"https://epoch.ai/benchmarks/gpqa-diamond","status":"excluded","reason":"Effort is not identified"},{"id":"epoch-run-ZUygpkXqg3NjchXXfedAWV","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://epoch.ai/benchmarks/frontiermath-tier-4-v2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"epoch-run-ZzbWv2QGVfg4o2DTX45nqV","modelId":"qwen3-30b-a3b","configurationId":"qwen3-30b-a3b--effort-non-reasoning","sourceUrl":"https://epoch.ai/benchmarks/otis-mock-aime-2024-2025","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"One run-task used an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-finance-agent-v2:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-finance-agent-v2:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-finance-agent-v2:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/fabv2","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-code-migration-v1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-code-migration-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/code-migration","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-research-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-research-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/legal_research","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-emb-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"excluded","reason":"Effort is not identified"},{"id":"vals-emb-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/emb","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"excluded","reason":"Effort is not identified"},{"id":"vals-mmlu-pro-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-mmlu-pro-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/mmlu_pro","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"excluded","reason":"Effort is not identified"},{"id":"vals-terminal-bench-2-1-v2.1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-terminal-bench-2-1-v2.1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/terminal-bench-2-1","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.7-code","modelId":"kimi-k2.7-code","configurationId":"kimi-k2.7-code--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-vibe-code-bench-v1.1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"excluded","reason":"Effort is not identified"},{"id":"vals-vibe-code-bench-v1.1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/vibe-code","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_2","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_3","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:meta/muse_spark_1_1","modelId":"muse-spark-1.1","configurationId":"muse-spark-1.1--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.6","modelId":"grok-4.6","configurationId":"grok-4.6--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.5","modelId":"grok-4.5","configurationId":"grok-4.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-fable-5","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Source discloses an Opus 4.8 refusal fallback; mixed checkpoint result excluded from ranking"},{"id":"vals-legal-agent-benchmark-v1:kimi/kimi-k3","modelId":"kimi-k3","configurationId":"kimi-k3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.8-flash","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-4-8","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.7-flash","modelId":"gemini-3.7-flash","configurationId":"gemini-3.7-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:deepseek/deepseek-v4-flash-0731","modelId":"deepseek-v4-flash","configurationId":"deepseek-v4-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.3","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:deepseek/deepseek-v4-pro-0813","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.2","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-4-7","modelId":"claude-opus-4-7","configurationId":"claude-opus-4-7--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.3-flash","modelId":"glm-5.3-flash","configurationId":"glm-5.3-flash--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-opus-5","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-fable-5-1","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-6-astra","modelId":"gpt-6-astra","configurationId":"gpt-6-astra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-sonnet-4-6","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-sonnet-5","modelId":"claude-sonnet-5","configurationId":"claude-sonnet-5--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M3","modelId":"minimax-m3","configurationId":"minimax-m3--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.5","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.6-flash","modelId":"gemini-3.6-flash","configurationId":"gemini-3.6-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.5-flash","modelId":"gemini-3.5-flash","configurationId":"gemini-3.5-flash--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-sol","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5-pro","modelId":"mimo-v2.5-pro","configurationId":"mimo-v2.5-pro--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:xiaomi/mimo-v2.5","modelId":"mimo-v2.5","configurationId":"mimo-v2.5--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:kimi/kimi-k2.6","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-max","modelId":"qwen3.7-max","configurationId":"qwen3.7-max--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-luna","modelId":"gpt-5.6-luna","configurationId":"gpt-5.6-luna--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.6-plus","modelId":"qwen3.6-plus","configurationId":"qwen3.6-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:anthropic/claude-haiku-4-5-20251001-thinking","modelId":"claude-haiku-4-5-20251001","configurationId":"claude-haiku-4-5-20251001--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.6-terra","modelId":"gpt-5.6-terra","configurationId":"gpt-5.6-terra--effort-max","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.3","modelId":"grok-4.3","configurationId":"grok-4.3--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:mistralai/mistral-medium-3.5","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3-flash-preview","modelId":"gemini-3-flash-preview","configurationId":"gemini-3-flash-preview--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.5-flash-lite","modelId":"gemini-3.5-flash-lite","configurationId":"gemini-3.5-flash-lite--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-nano-2026-03-17","modelId":"gpt-5.4-nano","configurationId":"gpt-5.4-nano--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:google/gemini-3.1-pro-preview","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:minimax/MiniMax-M2.7","modelId":"minimax-m2.7","configurationId":"minimax-m2.7--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:zai/glm-5.1","modelId":"glm-5.1","configurationId":"glm-5.1--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:grok/grok-4.20-0309-reasoning","modelId":"grok-4.20-0309-reasoning","configurationId":"grok-4.20-0309-reasoning--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:alibaba/qwen3.7-plus","modelId":"qwen3.7-plus","configurationId":"qwen3.7-plus--effort-unspecified","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"excluded","reason":"Effort is not identified"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-mini-2026-03-17","modelId":"gpt-5.4-mini","configurationId":"gpt-5.4-mini--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"vals-legal-agent-benchmark-v1:openai/gpt-5.4-2026-03-05","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://www.vals.ai/benchmarks/hlab","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-amazon-1491","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1492","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1493","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1494","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1495","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1496","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1497","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1498","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1499","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1500","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1501","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1502","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1503","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1504","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1505","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1506","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1507","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1508","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1509","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1510","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1511","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1512","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1513","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1514","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1515","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1516","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1517","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1518","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1519","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1520","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1521","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1522","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1523","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1524","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1525","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1526","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1527","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1528","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1529","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1530","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1531","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1532","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1533","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1534","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1535","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1536","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1537","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1538","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1539","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1540","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1541","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1542","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1543","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1544","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1545","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1546","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1547","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1548","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1549","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1550","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1551","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1552","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1553","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1554","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1555","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1556","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1557","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1558","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1559","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1560","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1561","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1562","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1563","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1564","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1565","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1566","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1567","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1568","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1569","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1570","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1571","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1572","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1573","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1574","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1575","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1576","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1577","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1578","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1579","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1580","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1581","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1582","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1583","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1584","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1585","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1586","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1587","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1588","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1589","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1590","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1591","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1592","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1593","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1594","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1595","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1596","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1597","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1598","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1599","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1600","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1601","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1602","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1603","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1604","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1605","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1606","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1607","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1608","modelId":"amazon-nova-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1609","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1610","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1611","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1612","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1613","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1614","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1615","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1616","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1617","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1618","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1619","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1620","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1621","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1622","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1623","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1624","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1625","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1626","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1627","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1628","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1629","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1630","modelId":"amazon-nova-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1631","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1632","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1633","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1634","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1635","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1636","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1637","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1638","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1639","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1640","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1641","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1642","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1643","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1644","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1645","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1646","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1647","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1648","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1649","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1650","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1651","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1652","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1653","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1654","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1655","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-amazon-1656","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1657","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1658","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1659","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1660","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1661","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1662","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1663","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1664","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1665","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1666","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1667","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1668","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1669","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1670","modelId":"amazon-nova-2-lite","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1671","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1672","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1673","modelId":"amazon-nova-premier","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1674","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1675","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1676","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1677","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1678","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1679","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1680","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1681","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1682","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1683","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1684","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1685","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1686","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1687","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1688","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1689","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1690","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-amazon-1691","modelId":"amazon-nova-2-pro-preview","configurationId":null,"sourceUrl":"https://cdn.amazon.science/c5/3d/84514a224666b5be6de4b43ef4aa/nova-2-0-technical-report2.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-0","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-anthropic-fable-5-1-card-1","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-10","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-100","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-101","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-anthropic-fable-5-1-card-102","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-103","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-104","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-105","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-106","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-107","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-108","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-109","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-11","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-110","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-111","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-112","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-113","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-114","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-115","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-116","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-117","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-118","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-119","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-12","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-120","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-121","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-122","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-123","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-124","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-125","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-126","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-127","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-128","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-129","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-13","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-130","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-131","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-132","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-133","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-134","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-135","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-136","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-14","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-15","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-16","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-17","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-18","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-19","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-2","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-20","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-21","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-22","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"System card section 8.6 cites the public Codex CLI result for Sol, while the Claude rows are internal Claude Code --bare reruns. Different agent harnesses and runs cannot form a matched comparison."},{"id":"launch-anthropic-fable-5-1-card-23","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-24","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-25","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-26","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-27","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-28","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-29","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-3","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-30","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-31","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-medium","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-32","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-33","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-34","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-35","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-36","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-37","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-38","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-39","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-4","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-anthropic-fable-5-1-card-40","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-auto-thinking","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-41","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-42","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-43","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-44","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-45","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-46","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-47","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-48","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-49","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-5","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-50","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-51","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-52","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-53","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-54","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-55","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-56","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-57","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-58","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-59","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-6","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-60","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-61","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-62","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-63","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-64","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-65","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-66","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-67","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-68","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-anthropic-fable-5-1-card-69","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-anthropic-fable-5-1-card-7","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-70","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-anthropic-fable-5-1-card-71","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-72","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-73","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-74","modelId":"claude-fable-5","configurationId":"claude-fable-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-75","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-76","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-77","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-xhigh","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-78","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-high","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-79","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-8","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-80","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-81","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-82","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-83","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-84","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-85","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"System card section8.15.5 confirms11of324trials were partly or fully completed by Opus4.8fallback; actual mixed-model execution, not merely available fallback."},{"id":"launch-anthropic-fable-5-1-card-86","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-87","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"System card section8.15.5 confirms11of324trials were partly or fully completed by Opus4.8fallback; actual mixed-model execution, not merely available fallback."},{"id":"launch-anthropic-fable-5-1-card-88","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-89","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"System card section8.15.5 confirms11of324trials were partly or fully completed by Opus4.8fallback; actual mixed-model execution, not merely available fallback."},{"id":"launch-anthropic-fable-5-1-card-9","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-anthropic-fable-5-1-card-90","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-anthropic-fable-5-1-card-91","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"System card section8.15.5 confirms11of324trials were partly or fully completed by Opus4.8fallback; actual mixed-model execution, not merely available fallback."},{"id":"launch-anthropic-fable-5-1-card-92","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Metric turns is outside the task-success core"},{"id":"launch-anthropic-fable-5-1-card-93","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-94","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-95","modelId":"claude-opus-5","configurationId":"claude-opus-5--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-anthropic-fable-5-1-card-96","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-97","modelId":"claude-fable-5-1","configurationId":"claude-fable-5-1--effort-max","sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-anthropic-fable-5-1-card-98","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-anthropic-fable-5-1-card-99","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1429","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1430","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1431","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1432","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1433","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1434","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1435","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-cohere-1436","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1437","modelId":"command-a-vision-07-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1438","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1439","modelId":"command-a-vision-07-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1440","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1441","modelId":"command-a-vision-07-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1967","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1968","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1969","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1970","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1971","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1972","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1973","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1974","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1975","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1976","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1977","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1978","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1979","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1980","modelId":"command-a-reasoning-08-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-cohere-1981","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1982","modelId":"command-a-vision-07-2025","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-cohere-1983","modelId":"command-a-plus-05-2026","configurationId":null,"sourceUrl":"https://cohere.com/blog/command-a-plus","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1136","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1137","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1138","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1139","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1140","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1141","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1142","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1143","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1144","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1145","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1146","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1147","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1148","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-deepseek-1149","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1150","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1151","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1152","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1153","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1154","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1155","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1156","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1157","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1158","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1159","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1160","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1161","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1162","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1163","modelId":"deepseek-v4-pro","configurationId":"deepseek-v4-pro--effort-max","sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-deepseek-1164","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1165","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1166","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1167","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1168","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1169","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1170","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1171","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1172","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1173","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1174","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1175","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1176","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1177","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1178","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1179","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1180","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1181","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1182","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1183","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1184","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-deepseek-1185","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs."},{"id":"launch-deepseek-1186","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1187","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1188","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1189","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1190","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1191","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1192","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1193","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1194","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1195","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1196","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-deepseek-1197","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813/blob/72e1d3230f6c080a530b0a1d46f8eb4602340597/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1357","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1358","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1359","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1360","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1361","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1362","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1363","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1364","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1365","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1366","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1367","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1368","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-1369","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-1370","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-1371","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-1372","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-1373","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-1374","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deepmind.google/models/gemini/flash/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2040","modelId":"gemini-3.8-flash","configurationId":"gemini-3.8-flash--effort-high","sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-google-gemini-3-8-card-2041","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2042","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2043","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2044","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2045","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2046","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2047","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2048","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2049","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2050","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2051","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2052","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2053","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2054","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2055","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2056","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2057","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2058","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2059","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2060","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2061","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2062","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2063","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2064","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2065","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2066","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2067","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2068","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2069","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2070","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2071","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2072","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2073","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2074","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2075","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2076","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2077","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2078","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2079","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2080","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-google-gemini-3-8-card-2081","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Card reports agentic result but linked methodology describes only static no-tools protocol."},{"id":"launch-google-gemini-3-8-card-2082","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit."},{"id":"launch-google-gemini-3-8-card-2083","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit."},{"id":"launch-google-gemini-3-8-card-2084","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit."},{"id":"launch-google-gemini-3-8-card-2085","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Mixed source task revisions and best-of-three versus provider reporting prevent a uniform common-core unit."},{"id":"launch-google-gemini-3-8-card-2086","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Provider-sourced OSWorld task revision is unverified; cannot join a known-version comparison."},{"id":"launch-google-gemini-3-8-card-2087","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Provider-sourced OSWorld task revision is unverified; cannot join a known-version comparison."},{"id":"launch-google-gemini-3-8-card-2088","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2089","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2090","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2091","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2092","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2093","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2094","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2095","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2096","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2097","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2098","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2099","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2100","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2101","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2102","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2103","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2104","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-google-gemini-3-8-card-2105","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-8-Flash-Model-Card.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-702","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-703","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-704","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-705","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-706","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-707","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-708","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-709","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-710","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-711","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-712","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-713","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-714","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-715","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-716","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-717","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-718","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-719","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-720","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-721","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-722","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-723","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-724","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-725","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-726","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-727","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-728","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-729","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-730","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-731","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-732","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-733","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-734","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-735","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-736","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-737","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-738","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-739","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-740","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-741","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-742","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-743","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-744","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-745","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-746","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-747","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites GLM release blog, Artificial Analysis or OpenAI, per model; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-748","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-749","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-750","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-751","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-752","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-753","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-754","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-755","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-756","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-757","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-758","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-759","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-760","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-761","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-762","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-763","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-764","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-765","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-766","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-767","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-768","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-769","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-770","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-771","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-772","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-773","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-774","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-775","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-776","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-777","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-778","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-779","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-780","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-781","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-782","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-783","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-784","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-785","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-786","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-787","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-788","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Anthropic or OpenAI release reports; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-789","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-790","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-791","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-792","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-793","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-794","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-795","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-796","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-797","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-798","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-799","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-800","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-801","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-802","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-803","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-804","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-805","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-806","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-807","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-808","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-809","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-810","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-811","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-812","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-813","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-814","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-815","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-816","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-817","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-818","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-819","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-820","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-821","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-822","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-823","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-824","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-825","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-826","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-827","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-828","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-829","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-830","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-831","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-832","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-833","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-834","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-835","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-836","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-837","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-838","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-839","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-840","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-841","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-842","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-843","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-844","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-845","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-846","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-847","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-848","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-849","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Kimi K3 Evaluation Details cites Artificial Analysis / APEX-Agents leaderboard; retain as published context, not a new Moonshot comparison."},{"id":"launch-kimi-850","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-851","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-852","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-853","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-854","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-855","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-856","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-857","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-858","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-859","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-860","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-861","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-862","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-863","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-864","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-865","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-866","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-867","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-868","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-869","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-870","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-871","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-872","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-873","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-874","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-875","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-876","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-877","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-878","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-879","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-880","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-881","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-882","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-883","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-884","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-885","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-886","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-887","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-888","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-889","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-890","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-891","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-892","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-893","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-894","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-895","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-896","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-897","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-898","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-899","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-900","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-901","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-902","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-903","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-904","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-905","modelId":"glm-5.2","configurationId":"glm-5.2--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-906","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-907","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-908","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-909","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-910","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-911","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-912","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-913","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-914","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-915","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-916","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-917","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-918","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-919","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-920","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-921","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-922","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-923","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-924","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-925","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-926","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-927","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-928","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-929","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-930","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-931","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-932","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-933","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-934","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-935","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-936","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-937","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-938","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-939","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-940","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-941","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-942","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-943","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-944","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-945","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-946","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-947","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-kimi-948","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-949","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-950","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-951","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-952","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-953","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-954","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-955","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-956","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-957","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-958","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-959","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-960","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-961","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-962","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-963","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-964","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-965","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-966","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-967","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-968","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-969","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-970","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-971","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-972","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-973","modelId":"gpt-5.5","configurationId":"gpt-5.5--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K3/blob/f831ab66814297da540d832a5235f8e904f29d06/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2106","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2107","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2108","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2109","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2110","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2111","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2112","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2113","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2114","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Agent swarm execution is not an individual model configuration."},{"id":"launch-kimi-k26-card-2115","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2116","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2117","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2118","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2119","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2120","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2121","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2122","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2123","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2124","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2125","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2126","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2127","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2128","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2129","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2130","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2131","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2132","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2133","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2134","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2135","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2136","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2137","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2138","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2139","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2140","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2141","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2142","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2143","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2144","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2145","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2146","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2147","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2148","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2149","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2150","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2151","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2152","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2153","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2154","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2155","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2156","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2157","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2158","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2159","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2160","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2161","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2162","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2163","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2164","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2165","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2166","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2167","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2168","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2169","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2170","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2171","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2172","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2173","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2174","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2175","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2176","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2177","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2178","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-kimi-k26-card-2179","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2180","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2181","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2182","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2183","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2184","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2185","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2186","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2187","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2188","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2189","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2190","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2191","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2192","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2193","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2194","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2195","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2196","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2197","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2198","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2199","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2200","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2201","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2202","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2203","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2204","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Cited comparator requires original evaluation provenance; not a new matched run."},{"id":"launch-kimi-k26-card-2205","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-kimi-k26-card-2206","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2207","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2208","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2209","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2210","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2211","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2212","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2213","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2214","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2215","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2216","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2217","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2218","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2219","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2220","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2221","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2222","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2223","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2224","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2225","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2226","modelId":"kimi-k2.6","configurationId":"kimi-k2.6--effort-reasoning","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2227","modelId":"gpt-5.4","configurationId":"gpt-5.4--effort-xhigh","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2228","modelId":"claude-opus-4-6","configurationId":"claude-opus-4-6--effort-max","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-kimi-k26-card-2229","modelId":"gemini-3.1-pro","configurationId":"gemini-3.1-pro--effort-high","sourceUrl":"https://huggingface.co/moonshotai/Kimi-K2.6/blob/7eb5002f6aadc958aed6a9177b7ed26bb94011bb/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1875","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1876","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1877","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1878","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1879","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1880","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1881","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1882","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1883","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1884","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1885","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1886","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1887","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1888","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1889","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1890","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1891","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1892","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1893","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1894","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1895","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1896","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1897","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1898","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1899","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1900","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1901","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1902","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1903","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1904","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1905","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1906","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1907","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1908","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1909","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1910","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1911","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1912","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1913","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1914","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1915","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1916","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1917","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1918","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1919","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1920","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1921","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1922","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1923","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1924","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1925","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1926","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1927","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1928","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1929","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1930","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1931","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1932","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1933","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1934","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1935","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1936","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1937","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1938","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1939","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1940","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1941","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1942","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1943","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1944","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1945","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-1946","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1947","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1948","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-1949","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-1-evaluation-report","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1984","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-meta-muse-1-3-report-1985","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-meta-muse-1-3-report-1986","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Secondary GDPval-AA v2 leaderboard report; the original evaluator already supplies this exact configuration. Reprinted or rerated board snapshots are not additional evaluation evidence."},{"id":"launch-meta-muse-1-3-report-1987","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-1988","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-1989","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1990","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1991","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1992","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1993","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-1994","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-1995","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-1996","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-1997","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-1998","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-1999","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2000","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2001","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2002","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2003","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2004","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2005","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2006","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2007","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2008","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2009","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2010","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2011","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2012","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2013","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2014","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2015","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2016","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2017","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2018","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2019","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2020","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2021","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2022","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2023","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2024","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2025","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"contributing","reason":"Positive comparison weight in the overall connected graph"},{"id":"launch-meta-muse-1-3-report-2026","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2027","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-meta-muse-1-3-report-2028","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-meta-muse-1-3-report-2029","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-meta-muse-1-3-report-2030","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2031","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2032","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2033","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2034","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-meta-muse-1-3-report-2035","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-max","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"launch-meta-muse-1-3-report-2036","modelId":"muse-spark-1.3","configurationId":"muse-spark-1.3--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"launch-meta-muse-1-3-report-2037","modelId":"muse-spark-1.2","configurationId":"muse-spark-1.2--effort-xhigh","sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"launch-meta-muse-1-3-report-2038","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"launch-meta-muse-1-3-report-2039","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://research.meta.ai/static/muse-spark-1-3-multimodal-evaluation-methodology","status":"excluded","reason":"Different native coding harnesses are mixed; exact shared agent configuration is not established."},{"id":"launch-microsoft-1375","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1376","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1377","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1378","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1379","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1380","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1381","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1382","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1383","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1384","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1385","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1386","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1387","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1388","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1389","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1390","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1391","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1392","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1393","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1394","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1395","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1396","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1397","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established."},{"id":"launch-microsoft-1398","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1399","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1400","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1401","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1402","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1403","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1404","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1405","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1406","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1407","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1408","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1409","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1410","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1411","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1412","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1413","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1414","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1415","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1416","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1417","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1418","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1419","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1420","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1421","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1422","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1423","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1424","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1425","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-microsoft-1426","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-microsoft-1427","modelId":"mai-thinking-1","configurationId":null,"sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-microsoft-1428","modelId":"claude-sonnet-4-6","configurationId":"claude-sonnet-4-6--effort-maximum-reasoning","sourceUrl":"https://microsoft.ai/pdf/mai-thinking-1.pdf","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1692","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1693","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1694","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1695","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1696","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1697","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1698","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1699","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1700","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1701","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1702","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1703","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1704","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1705","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1706","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1707","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1708","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology."},{"id":"launch-minimax-1709","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology."},{"id":"launch-minimax-1710","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"MiniMax cites this comparator from the official Terminal-Bench leaderboard; a common protocol with its internal Terminus 2 run is not established. See MiniMax M3 benchmark figure, Terminal-bench 2.1 methodology."},{"id":"launch-minimax-1711","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1712","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1713","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1714","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1715","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1716","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1717","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1718","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1719","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1720","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1721","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1722","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1723","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1724","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1725","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1726","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1727","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1728","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1729","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1730","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1731","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1732","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1733","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1734","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1735","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1736","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1737","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1738","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1739","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1740","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1741","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1742","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1743","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1744","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1745","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1746","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1747","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1748","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1749","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1750","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1751","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1752","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1753","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1754","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1755","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1756","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1757","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1758","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1759","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1760","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1761","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1762","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1763","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1764","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1765","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1766","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1767","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1768","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1769","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1770","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1771","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1772","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1773","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1774","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1775","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1776","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1777","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1778","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1779","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1780","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1781","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1782","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1783","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1784","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1785","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1786","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1787","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1788","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1789","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1790","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1791","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1792","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1793","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1794","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1795","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1796","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1797","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1798","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1799","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1800","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1801","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1802","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1803","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1804","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1805","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1806","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1807","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1808","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1809","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1810","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1811","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1812","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1813","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1814","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1815","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1816","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1817","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1818","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1819","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1820","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1821","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1822","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1823","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1824","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1825","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1826","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1827","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1828","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1829","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1830","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1831","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1832","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1833","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1834","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1835","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1836","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1837","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1838","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1839","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1840","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1841","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1842","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1843","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1844","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1845","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1846","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1847","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1848","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1849","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1850","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1851","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1852","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1853","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-minimax-1854","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1855","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1856","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1857","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1858","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1859","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1860","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1861","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1862","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1863","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1864","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1865","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1866","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1867","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1868","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1869","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1870","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1871","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1872","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1873","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-minimax-1874","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/MiniMaxAI/MiniMax-M3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1442","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-mistral-1443","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1444","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1445","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1446","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1447","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1448","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1449","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1450","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1451","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1452","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1453","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1454","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1455","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1456","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1457","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1458","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1459","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1460","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1461","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-mistral-1462","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1463","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1464","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1465","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1466","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1467","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1468","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1469","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1470","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1471","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1472","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1473","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1474","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1475","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1476","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1477","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1478","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1479","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1480","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1481","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1482","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1483","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1484","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1485","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1486","modelId":"mistral-medium-3.5","configurationId":"mistral-medium-3.5--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-mistral-1487","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1488","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1489","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1490","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1950","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1951","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1952","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1953","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1954","modelId":"magistral-medium-2509","configurationId":"magistral-medium-2509--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-mistral-1955","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1956","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1957","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1958","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1959","modelId":"mistral-small-4","configurationId":"mistral-small-4--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-mistral-1960","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1961","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1962","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1963","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-mistral-1964","modelId":"mistral-medium-2508","configurationId":"mistral-medium-2508--effort-maximum-reasoning","sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"admitted","reason":"Matched, but no positive comparison weight in the overall connected graph"},{"id":"launch-mistral-1965","modelId":"devstral-2512","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-mistral-1966","modelId":"labs-devstral-small-2512","configurationId":null,"sourceUrl":"https://huggingface.co/mistralai/Mistral-Medium-3.5-128B","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1000","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1001","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1002","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1003","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1004","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1005","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1006","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1007","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1008","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1009","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1010","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1011","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1012","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1013","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1014","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1015","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1016","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1017","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1018","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1019","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1020","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1021","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1022","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1023","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1024","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1025","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1026","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1027","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1028","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1029","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1030","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1031","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1032","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1033","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1034","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1035","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1036","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1037","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1038","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1039","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1040","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1041","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1042","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1043","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1044","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1045","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1046","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1047","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1048","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1049","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1050","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1051","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1052","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1053","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1054","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1055","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1056","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1057","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1058","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1059","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1060","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1061","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1062","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1063","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1064","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1065","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1066","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1067","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1068","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1069","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1070","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1071","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1072","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1073","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-1074","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1075","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1076","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1077","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1078","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-1079","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1080","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1081","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1082","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1083","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1084","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1085","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1086","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1087","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1088","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1089","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1090","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1091","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1092","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1093","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1094","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1095","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1096","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1097","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-1098","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1099","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1100","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1101","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1102","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1103","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1104","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1105","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1106","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1107","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1108","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1109","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1110","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1111","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1112","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1113","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1114","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1115","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1116","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1117","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-1118","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1119","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1120","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1121","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1122","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1123","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1124","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1125","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1126","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-1127","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1128","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1129","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1130","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-1131","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1132","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1133","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1134","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-1135","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-974","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-975","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-976","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-977","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-978","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-979","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-980","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-981","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-982","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-983","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-984","modelId":"nemotron-3-ultra","configurationId":"nemotron-3-ultra--effort-thinking","sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-nvidia-985","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-986","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-987","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-988","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-989","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-990","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-991","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-992","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-993","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-nvidia-994","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-995","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-996","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-997","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-998","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-nvidia-999","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-137","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-138","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-139","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-140","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-141","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-142","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-143","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-144","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-145","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-146","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-147","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-148","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-149","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-150","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-151","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-152","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-153","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-154","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-155","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-156","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-157","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-158","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-159","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-160","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-161","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-162","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-163","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-164","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-165","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-166","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-167","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-168","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-169","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-170","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-171","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-172","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-173","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-174","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-175","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-176","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-177","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-178","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-179","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-180","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-181","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-182","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-183","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-184","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-185","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-186","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-187","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-188","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-189","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-190","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-191","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-192","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-193","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-194","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-195","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-196","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-197","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-198","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-199","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-200","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-201","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-202","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-203","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-204","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-205","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-206","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-207","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-208","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-209","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-210","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-211","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-212","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-213","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-214","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-215","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-216","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-217","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-218","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-219","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-220","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-221","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-222","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-223","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-224","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-225","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-226","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-227","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-228","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-229","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-230","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-231","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-232","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-233","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-234","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-235","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-236","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-237","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-238","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-239","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-240","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-241","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-242","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-243","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-244","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-245","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-246","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-247","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-248","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-249","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-250","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-251","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-launch-252","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-253","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-254","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-255","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-256","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-astra-launch-257","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-258","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-259","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-260","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-261","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-262","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-263","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-264","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-265","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-openai-astra-launch-266","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-267","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-268","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-astra-launch-547","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-astra-launch-548","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-astra-launch-549","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-6-astra/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-489","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-490","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-491","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-492","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-493","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-494","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-495","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-496","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-497","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-498","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-499","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-500","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-501","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-502","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-503","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-504","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-505","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-506","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-507","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-508","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-509","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-510","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-511","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-512","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-513","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-514","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-515","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-516","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-517","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-518","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-519","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-520","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-521","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-522","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-523","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-524","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-525","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-526","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-527","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-528","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-529","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-530","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-531","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-532","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-533","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-534","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-535","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-536","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-537","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-538","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-539","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-540","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-541","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-542","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-543","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-544","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-545","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-astra-system-card-546","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deploymentsafety.openai.com/gpt-6-astra","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-269","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-270","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-271","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-272","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-273","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-274","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-275","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-276","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-277","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-278","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-279","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-280","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-281","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-282","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-283","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-284","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-285","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-286","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-287","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-288","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-289","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-290","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-291","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-292","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-293","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-294","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-295","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-296","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-297","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-298","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-299","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-300","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-301","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-302","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-303","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-304","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-305","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-306","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-307","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-308","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-309","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-310","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-311","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-312","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-313","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-314","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-315","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-316","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-317","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-318","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-319","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-320","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-321","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-322","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-323","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-324","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-325","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-326","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-sol-launch-327","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-328","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-329","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-330","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-331","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-332","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-333","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-334","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-335","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-336","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-337","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-338","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-339","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-340","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-341","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-342","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-343","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-344","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-345","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-346","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-347","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-348","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-349","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-350","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-351","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-352","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-353","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-354","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-355","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-356","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-357","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-358","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-359","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-360","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-361","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-sol-launch-362","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-363","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-364","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-365","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-366","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-367","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-368","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-369","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-370","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-371","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-372","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-373","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-374","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-375","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-376","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-377","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-378","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-379","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-380","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-381","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-382","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-383","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-384","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-385","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-386","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-387","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-388","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-389","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-390","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-391","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-392","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-393","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-394","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-395","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-396","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-397","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-398","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-399","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-400","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-401","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-402","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-403","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-404","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-405","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-406","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-407","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-408","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-409","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-410","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-411","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-412","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-413","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-414","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-415","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-416","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-417","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-418","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-419","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-420","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-421","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-422","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-423","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-424","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-425","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-426","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-427","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-428","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-429","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-430","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-openai-sol-launch-431","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-432","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-433","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-434","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-435","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-436","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-437","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-438","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-439","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-440","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-441","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-442","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-443","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-444","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-445","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-446","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-447","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-448","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-449","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-450","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-451","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-452","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-453","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-454","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-455","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-456","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-457","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-458","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-459","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-460","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-461","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-462","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-463","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-464","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-465","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-466","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-467","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-468","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-469","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-470","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-471","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-472","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-473","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-474","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-475","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-476","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-477","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-478","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-479","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-480","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-481","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-482","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-483","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-484","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-485","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-486","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-487","modelId":"claude-opus-4-8","configurationId":"claude-opus-4-8--effort-high","sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-openai-sol-launch-488","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-openai-sol-launch-550","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-551","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation."},{"id":"launch-qwen-552","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation. The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-553","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation."},{"id":"launch-qwen-554","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation."},{"id":"launch-qwen-555","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"launch-qwen-556","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-557","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-558","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-559","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-560","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-561","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-562","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-563","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-564","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-565","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-566","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-567","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-568","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-569","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-570","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-571","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-572","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-573","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-574","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-575","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-576","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-577","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-578","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-579","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-580","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-581","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-582","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-583","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-584","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-585","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-586","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-587","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-588","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-589","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-590","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-591","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-592","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-593","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-594","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-595","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-596","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-597","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-598","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-599","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-600","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-601","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-602","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-603","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-604","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-605","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-606","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-607","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-608","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-609","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-610","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-611","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-612","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-613","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-614","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-615","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-616","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-617","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-618","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-619","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-620","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-621","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-622","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-623","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-624","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-625","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-626","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-627","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-628","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-629","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-630","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-631","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-632","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-633","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-634","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-635","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-636","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-637","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-638","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-639","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-640","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-641","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-642","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-643","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-644","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-645","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-646","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-647","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-648","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-649","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-650","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-651","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-652","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-653","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-654","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-655","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-656","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-657","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-658","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-659","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-660","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-661","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"The source states that Fable 5 results may involve fallback execution; an exact configuration is not established."},{"id":"launch-qwen-662","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-663","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-664","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-665","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-666","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-667","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-668","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-669","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-670","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-671","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-672","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-673","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-674","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-675","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-676","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-677","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-678","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-679","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-680","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-681","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-682","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-683","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-684","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-685","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-686","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-687","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-688","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-689","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-690","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-691","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-692","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-693","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-qwen-694","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-695","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-696","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-697","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-698","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-699","modelId":"gpt-5.6-sol","configurationId":"gpt-5.6-sol--effort-max","sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-qwen-700","modelId":"qwen3.7-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-qwen-701","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B/blob/207bd685a7e3696cfaff12ded7c6a7ea0f88c996/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1318","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1319","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1320","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1321","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1322","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1323","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1324","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1325","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1326","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1327","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1328","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1329","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1330","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1331","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1332","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1333","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1334","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1335","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1336","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1337","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1338","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1339","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1340","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1341","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1342","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1343","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1344","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1345","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-xai-1346","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1347","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1348","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1349","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1350","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1351","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1352","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1353","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1354","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1355","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-xai-1356","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://x.ai/news/grok-4-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1198","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1199","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1200","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1201","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1202","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1203","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1204","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1205","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1206","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No matched, identified effort unit; duplicates and unnamed comparators do not add evidence"},{"id":"launch-zai-1207","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1208","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1209","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1210","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1211","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1212","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1213","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1214","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1215","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1216","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1217","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1218","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1219","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1220","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1221","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1222","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1223","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1224","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1225","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1226","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1227","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1228","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1229","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1230","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1231","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1232","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1233","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1234","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1235","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1236","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1237","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1238","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1239","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1240","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1241","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1242","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1243","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1244","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1245","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1246","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1247","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1248","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1249","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1250","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1251","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1252","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1253","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1254","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1255","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1256","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1257","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1258","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1259","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1260","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1261","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1262","modelId":"kimi-k3","configurationId":"kimi-k3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1263","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1264","modelId":"qwen-3.8-max","configurationId":"qwen-3.8-max--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1265","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1266","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1267","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1268","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1269","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1270","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1271","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1272","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1273","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1274","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1275","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1276","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1277","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1278","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1279","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1280","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1281","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1282","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1283","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1284","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1285","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1286","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1287","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1288","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1289","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1290","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1291","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1292","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1293","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1294","modelId":"glm-5.3","configurationId":"glm-5.3--effort-max","sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1295","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1296","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1297","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1298","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1299","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1300","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1301","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"launch-zai-1302","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1303","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1304","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1305","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1306","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1307","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1308","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1309","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"launch-zai-1310","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1311","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1312","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1313","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1314","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1315","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"launch-zai-1316","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison. The source column includes fallback execution without a documented exact effort."},{"id":"launch-zai-1317","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://huggingface.co/zai-org/GLM-5.3/blob/aca966e4e02791568aa6a4ced368624b3d897f42/README.md","status":"excluded","reason":"The GLM card attributes this evaluation to Artificial Analysis; it is not a new Z.ai comparison."},{"id":"reported-20260901-claude-fable-5-1-deepswe-v1.1-deepswe-v1.1-anthropic-reported","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-1-hle-hle-no-tools","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-1-hle-hle-with-tools","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-1-swe-bench-pro-swe-bench-pro-anthropic-reported","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-hle-hle-no-tools","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-hle-hle-with-tools","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-fable-5-swe-bench-pro-swe-bench-pro-anthropic-reported","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-opus-5-hle-hle-no-tools","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"reported-20260901-claude-opus-5-hle-hle-with-tools","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-arc2-claude-fable-5-1-efebf61be277","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-fable-5-efebf61be277","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-haiku-4-5-20251001-efebf61be277","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-opus-4-8-efebf61be277","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-opus-5-efebf61be277","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-sonnet-4-5-20250929-efebf61be277","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-claude-sonnet-4-6-efebf61be277","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-deepseek-v3.2-efebf61be277","modelId":"deepseek-v3.2","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-deepseek-v4-pro-efebf61be277","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-2.5-flash-efebf61be277","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3-flash-preview-efebf61be277","modelId":"gemini-3-flash-preview","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.1-pro-efebf61be277","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.5-flash-efebf61be277","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.5-flash-lite-efebf61be277","modelId":"gemini-3.5-flash-lite","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.6-flash-efebf61be277","modelId":"gemini-3.6-flash","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gemini-3.7-flash-efebf61be277","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-glm-5-efebf61be277","modelId":"glm-5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-glm-5.2-efebf61be277","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-4.1-efebf61be277","modelId":"gpt-4.1","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-4.1-mini-efebf61be277","modelId":"gpt-4.1-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-4.1-nano-efebf61be277","modelId":"gpt-4.1-nano","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-4o-efebf61be277","modelId":"gpt-4o","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-4o-mini-efebf61be277","modelId":"gpt-4o-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5-efebf61be277","modelId":"gpt-5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5-mini-efebf61be277","modelId":"gpt-5-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5-nano-efebf61be277","modelId":"gpt-5-nano","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5-pro-efebf61be277","modelId":"gpt-5-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.2-efebf61be277","modelId":"gpt-5.2","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.2-pro-efebf61be277","modelId":"gpt-5.2-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.4-efebf61be277","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.4-mini-efebf61be277","modelId":"gpt-5.4-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.4-nano-efebf61be277","modelId":"gpt-5.4-nano","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.4-pro-efebf61be277","modelId":"gpt-5.4-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.5-efebf61be277","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.5-pro-efebf61be277","modelId":"gpt-5.5-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.6-luna-efebf61be277","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.6-sol-efebf61be277","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-5.6-terra-efebf61be277","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-gpt-6-astra-efebf61be277","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-grok-4.6-efebf61be277","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-kimi-k3-efebf61be277","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-llama-4-maverick-efebf61be277","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-minimax-m2.5-efebf61be277","modelId":"minimax-m2.5","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-o3-efebf61be277","modelId":"o3","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-o3-mini-efebf61be277","modelId":"o3-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-o3-pro-efebf61be277","modelId":"o3-pro","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-o4-mini-efebf61be277","modelId":"o4-mini","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-arc2-qwen3-235b-a22b-instruct-2507-efebf61be277","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://arcprize.org/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-fable-5-eb88d1c756c0","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-opus-4-8-eb88d1c756c0","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-opus-5-eb88d1c756c0","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-sonnet-4-6-eb88d1c756c0","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-claude-sonnet-5-eb88d1c756c0","modelId":"claude-sonnet-5","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-deepseek-v4-flash-eb88d1c756c0","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-deepseek-v4-pro-eb88d1c756c0","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gemini-3.1-pro-eb88d1c756c0","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gemini-3.5-flash-eb88d1c756c0","modelId":"gemini-3.5-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gemini-3.6-flash-eb88d1c756c0","modelId":"gemini-3.6-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gemini-3.7-flash-eb88d1c756c0","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gemini-3.8-flash-eb88d1c756c0","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-glm-5.2-eb88d1c756c0","modelId":"glm-5.2","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-glm-5.3-eb88d1c756c0","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-glm-5.3-flash-eb88d1c756c0","modelId":"glm-5.3-flash","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-5.4-eb88d1c756c0","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-5.5-eb88d1c756c0","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-5.6-luna-eb88d1c756c0","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-5.6-sol-eb88d1c756c0","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-5.6-terra-eb88d1c756c0","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-gpt-6-astra-eb88d1c756c0","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-grok-4.5-eb88d1c756c0","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-grok-4.6-eb88d1c756c0","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-kimi-k2.7-code-eb88d1c756c0","modelId":"kimi-k2.7-code","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-kimi-k3-eb88d1c756c0","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-muse-spark-1.1-eb88d1c756c0","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-muse-spark-1.2-eb88d1c756c0","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-deepswe-qwen-3.8-max-eb88d1c756c0","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://deepswe.datacurve.ai/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-ds-aa","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/models/comparisons/deepseek-v4-pro-vs-o3","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-ds-browse","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-hle","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-lcb","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-swepro","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-swev","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-ds-tb21","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gdpval-agnes-2.5-pro-alpha-58c478670eac","modelId":"agnes-2.5-pro-alpha","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-claude-opus-5-58c478670eac","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-deepseek-v4-pro-58c478670eac","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-devstral-2512-58c478670eac","modelId":"devstral-2512","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-diffusiongemma-26b-a4b-58c478670eac","modelId":"diffusiongemma-26b-a4b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-exaone-4.5-33b-58c478670eac","modelId":"exaone-4.5-33b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-2.5-pro-58c478670eac","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-3.1-flash-lite-58c478670eac","modelId":"gemini-3.1-flash-lite","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-3.1-pro-58c478670eac","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gemini-3.5-flash-lite-58c478670eac","modelId":"gemini-3.5-flash-lite","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-glm-5.3-flash-58c478670eac","modelId":"glm-5.3-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gpt-4-58c478670eac","modelId":"gpt-4","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gpt-4.1-mini-58c478670eac","modelId":"gpt-4.1-mini","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gpt-4o-mini-58c478670eac","modelId":"gpt-4o-mini","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-gpt-5.6-sol-58c478670eac","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-grok-4.6-58c478670eac","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-hy3-58c478670eac","modelId":"hy3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-kimi-k3-58c478670eac","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-labs-devstral-small-2512-58c478670eac","modelId":"labs-devstral-small-2512","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-llama-4-maverick-58c478670eac","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-magistral-medium-2509-58c478670eac","modelId":"magistral-medium-2509","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-magistral-small-2509-58c478670eac","modelId":"magistral-small-2509","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mimo-v2.5-58c478670eac","modelId":"mimo-v2.5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mimo-v2.5-pro-58c478670eac","modelId":"mimo-v2.5-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-minicpm5-2b-58c478670eac","modelId":"minicpm5-2b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-minimax-m2.7-58c478670eac","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-minimax-m3-58c478670eac","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-ministral-3-14b-58c478670eac","modelId":"ministral-3-14b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-ministral-3-3b-58c478670eac","modelId":"ministral-3-3b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-ministral-3-8b-58c478670eac","modelId":"ministral-3-8b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mistral-large-3-58c478670eac","modelId":"mistral-large-3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mistral-medium-2508-58c478670eac","modelId":"mistral-medium-2508","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mistral-medium-3.5-58c478670eac","modelId":"mistral-medium-3.5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-mistral-small-2506-58c478670eac","modelId":"mistral-small-2506","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-nemotron-3-ultra-58c478670eac","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-qwen-3.8-max-58c478670eac","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-qwen3.8-flash-next-58c478670eac","modelId":"qwen3.8-flash-next","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-solar-open2-250b-58c478670eac","modelId":"solar-open2-250b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-solar-pro3-260323-58c478670eac","modelId":"solar-pro3-260323","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-solar-pro4-260806-58c478670eac","modelId":"solar-pro4-260806","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gdpval-step-3.7-flash-58c478670eac","modelId":"step-3.7-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gdpval-aa","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gem31-aa","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/artificial-analysis-intelligence-index-v4-1","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gem31-browse","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gem31-swev","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gem31-tau2","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://deepmind.google/models/model-cards/gemini-3-1-pro/","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gpqa-claude-fable-5-1-41e862296ea6","modelId":"claude-fable-5-1","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-claude-fable-5-41e862296ea6","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-claude-opus-5-41e862296ea6","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-deepseek-v4-pro-41e862296ea6","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gemini-3.1-pro-41e862296ea6","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gemini-3.5-flash-lite-41e862296ea6","modelId":"gemini-3.5-flash-lite","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gemini-3.7-flash-41e862296ea6","modelId":"gemini-3.7-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gemini-3.8-flash-41e862296ea6","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-glm-5.3-41e862296ea6","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-glm-5.3-flash-41e862296ea6","modelId":"glm-5.3-flash","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gpt-5.6-luna-41e862296ea6","modelId":"gpt-5.6-luna","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gpt-5.6-sol-41e862296ea6","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gpt-5.6-terra-41e862296ea6","modelId":"gpt-5.6-terra","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gpt-6-astra-41e862296ea6","modelId":"gpt-6-astra","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-gpt-oss-120b-41e862296ea6","modelId":"gpt-oss-120b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-grok-4.6-41e862296ea6","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-kimi-k3-41e862296ea6","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-minimax-m3-41e862296ea6","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-mistral-medium-3.5-41e862296ea6","modelId":"mistral-medium-3.5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-muse-spark-1.3-41e862296ea6","modelId":"muse-spark-1.3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-nemotron-3-ultra-41e862296ea6","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-qwen3.8-2.4t-a95b-41e862296ea6","modelId":"qwen3.8-2.4t-a95b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpqa-qwen3.8-27b-41e862296ea6","modelId":"qwen3.8-27b","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/evaluations/gpqa-diamond","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-gpt56-aa","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/grok-4-6-benchmarks-and-analysis","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-gpt56-browse","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gpt56-swepro","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gpt56-tb21","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-gpt56-tb21-ultra","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://openai.com/index/gpt-5-6/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-grok46-aa","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/grok-4-6-benchmarks-and-analysis","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-grok46-tb21","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/grok-4-6-benchmarks-and-analysis","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"s-hle-claude-opus-4-5-20251101-f549f30a8404","modelId":"claude-opus-4-5-20251101","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-claude-opus-4-7-f549f30a8404","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-claude-sonnet-4-5-20250929-f549f30a8404","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-gemini-3.1-pro-f549f30a8404","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-gemini-3.8-flash-f549f30a8404","modelId":"gemini-3.8-flash","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-gpt-4.1-f549f30a8404","modelId":"gpt-4.1","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-llama-4-maverick-f549f30a8404","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-hle-mistral-medium-2505-f549f30a8404","modelId":"mistral-medium-2505","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/humanitys_last_exam","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-kimi-aa","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/grok-4-6-benchmarks-and-analysis","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-kimi-browse","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://www.kimi.ai/blog/kimi-k3","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-kimi-hle","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://www.kimi.ai/blog/kimi-k3","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-kimi-tb21","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://www.kimi.ai/blog/kimi-k3","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-lcb-deepseek-r1-0528-ad3f286332a4","modelId":"deepseek-r1-0528","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-exaone-4.0-32b-ad3f286332a4","modelId":"exaone-4.0-32b","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-gpt-4-turbo-ad3f286332a4","modelId":"gpt-4-turbo","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-gpt-4o-ad3f286332a4","modelId":"gpt-4o","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-gpt-4o-mini-ad3f286332a4","modelId":"gpt-4o-mini","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-o3-ad3f286332a4","modelId":"o3","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-o3-mini-ad3f286332a4","modelId":"o3-mini","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-o4-mini-ad3f286332a4","modelId":"o4-mini","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lcb-qwen3-235b-a22b-ad3f286332a4","modelId":"qwen3-235b-a22b","configurationId":null,"sourceUrl":"https://livecodebench.github.io/leaderboard.html","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-llama4-gpqa","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-llama4-lcb","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://ai.meta.com/blog/llama-4-multimodal-intelligence/","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-lmarena-c4ai-aya-expanse-32b-465fe8c26c46","modelId":"c4ai-aya-expanse-32b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-c4ai-aya-expanse-8b-465fe8c26c46","modelId":"c4ai-aya-expanse-8b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-chatglm-6b-465fe8c26c46","modelId":"chatglm-6b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-chatglm2-6b-465fe8c26c46","modelId":"chatglm2-6b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-chatglm3-6b-465fe8c26c46","modelId":"chatglm3-6b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-fable-5-465fe8c26c46","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-haiku-4-5-20251001-465fe8c26c46","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-opus-4-5-20251101-465fe8c26c46","modelId":"claude-opus-4-5-20251101","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-opus-4-6-465fe8c26c46","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-opus-4-7-465fe8c26c46","modelId":"claude-opus-4-7","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-opus-4-8-465fe8c26c46","modelId":"claude-opus-4-8","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-opus-5-465fe8c26c46","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-sonnet-4-5-20250929-465fe8c26c46","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-claude-sonnet-4-6-465fe8c26c46","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-command-a-03-2025-465fe8c26c46","modelId":"command-a-03-2025","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-command-r-03-2024-465fe8c26c46","modelId":"command-r-03-2024","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-command-r-08-2024-465fe8c26c46","modelId":"command-r-08-2024","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-command-r-plus-04-2024-465fe8c26c46","modelId":"command-r-plus-04-2024","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-command-r-plus-08-2024-465fe8c26c46","modelId":"command-r-plus-08-2024","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-r1-0528-465fe8c26c46","modelId":"deepseek-r1-0528","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-v3.2-465fe8c26c46","modelId":"deepseek-v3.2","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-v4-flash-465fe8c26c46","modelId":"deepseek-v4-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-deepseek-v4-pro-465fe8c26c46","modelId":"deepseek-v4-pro","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-ernie-5.1-465fe8c26c46","modelId":"ernie-5.1","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-2.5-flash-465fe8c26c46","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-2.5-pro-465fe8c26c46","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-3.1-pro-465fe8c26c46","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemini-3.5-flash-lite-465fe8c26c46","modelId":"gemini-3.5-flash-lite","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-1.1-2b-it-465fe8c26c46","modelId":"gemma-1.1-2b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-1.1-7b-it-465fe8c26c46","modelId":"gemma-1.1-7b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-2-27b-it-465fe8c26c46","modelId":"gemma-2-27b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-2-2b-it-465fe8c26c46","modelId":"gemma-2-2b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-2-9b-it-465fe8c26c46","modelId":"gemma-2-9b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-3-12b-it-465fe8c26c46","modelId":"gemma-3-12b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-3-27b-it-465fe8c26c46","modelId":"gemma-3-27b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-3-4b-it-465fe8c26c46","modelId":"gemma-3-4b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gemma-3n-e4b-it-465fe8c26c46","modelId":"gemma-3n-e4b-it","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.5-465fe8c26c46","modelId":"glm-4.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.5-air-465fe8c26c46","modelId":"glm-4.5-air","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.5v-465fe8c26c46","modelId":"glm-4.5v","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.6-465fe8c26c46","modelId":"glm-4.6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.6v-465fe8c26c46","modelId":"glm-4.6v","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.7-465fe8c26c46","modelId":"glm-4.7","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-4.7-flash-465fe8c26c46","modelId":"glm-4.7-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-5-465fe8c26c46","modelId":"glm-5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-5.1-465fe8c26c46","modelId":"glm-5.1","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-5.3-flash-465fe8c26c46","modelId":"glm-5.3-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-glm-5v-turbo-465fe8c26c46","modelId":"glm-5v-turbo","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-3.5-turbo-1106-465fe8c26c46","modelId":"gpt-3.5-turbo-1106","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.1-465fe8c26c46","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.2-465fe8c26c46","modelId":"gpt-5.2","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.4-465fe8c26c46","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.5-465fe8c26c46","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-5.6-sol-465fe8c26c46","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-oss-120b-465fe8c26c46","modelId":"gpt-oss-120b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-gpt-oss-20b-465fe8c26c46","modelId":"gpt-oss-20b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-grok-4.3-465fe8c26c46","modelId":"grok-4.3","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-grok-4.5-465fe8c26c46","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-grok-4.6-465fe8c26c46","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-hy3-465fe8c26c46","modelId":"hy3","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-kimi-k2.6-465fe8c26c46","modelId":"kimi-k2.6","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-kimi-k3-465fe8c26c46","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-3.1-70b-instruct-465fe8c26c46","modelId":"llama-3.1-70b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-3.1-8b-instruct-465fe8c26c46","modelId":"llama-3.1-8b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-3.2-1b-instruct-465fe8c26c46","modelId":"llama-3.2-1b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-3.2-3b-instruct-465fe8c26c46","modelId":"llama-3.2-3b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-3.3-70b-instruct-465fe8c26c46","modelId":"llama-3.3-70b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-4-maverick-465fe8c26c46","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-llama-4-scout-465fe8c26c46","modelId":"llama-4-scout","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mimo-v2.5-465fe8c26c46","modelId":"mimo-v2.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mimo-v2.5-pro-465fe8c26c46","modelId":"mimo-v2.5-pro","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-minimax-m2-465fe8c26c46","modelId":"minimax-m2","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-minimax-m2.5-465fe8c26c46","modelId":"minimax-m2.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-minimax-m2.7-465fe8c26c46","modelId":"minimax-m2.7","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-minimax-m3-465fe8c26c46","modelId":"minimax-m3","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-ministral-8b-2410-465fe8c26c46","modelId":"ministral-8b-2410","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-large-2407-465fe8c26c46","modelId":"mistral-large-2407","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-large-2411-465fe8c26c46","modelId":"mistral-large-2411","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-large-3-465fe8c26c46","modelId":"mistral-large-3","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-medium-2505-465fe8c26c46","modelId":"mistral-medium-2505","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-medium-2508-465fe8c26c46","modelId":"mistral-medium-2508","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-medium-3.5-465fe8c26c46","modelId":"mistral-medium-3.5","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-mistral-small-2506-465fe8c26c46","modelId":"mistral-small-2506","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-muse-spark-1.1-465fe8c26c46","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-nemotron-3-ultra-465fe8c26c46","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-nvidia-nemotron-3-nano-30b-a3b-bf16-465fe8c26c46","modelId":"nvidia-nemotron-3-nano-30b-a3b-bf16","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-o3-mini-465fe8c26c46","modelId":"o3-mini","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-phi-3-medium-4k-instruct-465fe8c26c46","modelId":"phi-3-medium-4k-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-phi-3-mini-128k-instruct-465fe8c26c46","modelId":"phi-3-mini-128k-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-phi-3-mini-4k-instruct-465fe8c26c46","modelId":"phi-3-mini-4k-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-phi-3-small-8k-instruct-465fe8c26c46","modelId":"phi-3-small-8k-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-phi-4-465fe8c26c46","modelId":"phi-4","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen-3.8-max-465fe8c26c46","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-235b-a22b-465fe8c26c46","modelId":"qwen3-235b-a22b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-235b-a22b-instruct-2507-465fe8c26c46","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-235b-a22b-thinking-2507-465fe8c26c46","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-30b-a3b-465fe8c26c46","modelId":"qwen3-30b-a3b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-30b-a3b-instruct-2507-465fe8c26c46","modelId":"qwen3-30b-a3b-instruct-2507","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-32b-465fe8c26c46","modelId":"qwen3-32b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-coder-480b-a35b-instruct-465fe8c26c46","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-next-80b-a3b-instruct-465fe8c26c46","modelId":"qwen3-next-80b-a3b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-next-80b-a3b-thinking-465fe8c26c46","modelId":"qwen3-next-80b-a3b-thinking","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-vl-235b-a22b-instruct-465fe8c26c46","modelId":"qwen3-vl-235b-a22b-instruct","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3-vl-235b-a22b-thinking-465fe8c26c46","modelId":"qwen3-vl-235b-a22b-thinking","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.5-122b-a10b-465fe8c26c46","modelId":"qwen3.5-122b-a10b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.5-27b-465fe8c26c46","modelId":"qwen3.5-27b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.5-35b-a3b-465fe8c26c46","modelId":"qwen3.5-35b-a3b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.5-397b-a17b-465fe8c26c46","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.5-flash-465fe8c26c46","modelId":"qwen3.5-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.6-plus-465fe8c26c46","modelId":"qwen3.6-plus","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.7-plus-465fe8c26c46","modelId":"qwen3.7-plus","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-qwen3.8-27b-465fe8c26c46","modelId":"qwen3.8-27b","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-solar-10.7b-instruct-v1.0-465fe8c26c46","modelId":"solar-10.7b-instruct-v1.0","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-solar-pro4-260806-465fe8c26c46","modelId":"solar-pro4-260806","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-lmarena-step-3.5-flash-465fe8c26c46","modelId":"step-3.5-flash","configurationId":null,"sourceUrl":"https://lmarena.ai/leaderboard","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mistral-gpqa","modelId":"mistral-large-3","configurationId":null,"sourceUrl":"https://vals.ai/models/mistralai_mistral-large-2512","status":"excluded","reason":"No matched opponent in this evaluation unit"},{"id":"s-mmlu-pro-c4ai-aya-expanse-8b-df03094a9acf","modelId":"c4ai-aya-expanse-8b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-deepseek-r1-0528-df03094a9acf","modelId":"deepseek-r1-0528","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-exaone-3.5-2.4b-instruct-df03094a9acf","modelId":"exaone-3.5-2.4b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-exaone-3.5-32b-instruct-df03094a9acf","modelId":"exaone-3.5-32b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-exaone-3.5-7.8b-instruct-df03094a9acf","modelId":"exaone-3.5-7.8b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemini-2.5-pro-df03094a9acf","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemini-3.1-pro-df03094a9acf","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-2-27b-it-df03094a9acf","modelId":"gemma-2-27b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-2-2b-it-df03094a9acf","modelId":"gemma-2-2b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-2-9b-it-df03094a9acf","modelId":"gemma-2-9b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-3-12b-it-df03094a9acf","modelId":"gemma-3-12b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-3-1b-it-df03094a9acf","modelId":"gemma-3-1b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-3-27b-it-df03094a9acf","modelId":"gemma-3-27b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gemma-3-4b-it-df03094a9acf","modelId":"gemma-3-4b-it","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-glm-4-9b-chat-df03094a9acf","modelId":"glm-4-9b-chat","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-glm-4.5-air-df03094a9acf","modelId":"glm-4.5-air","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-glm-4.5-df03094a9acf","modelId":"glm-4.5","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-glm-5-df03094a9acf","modelId":"glm-5","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-4-turbo-df03094a9acf","modelId":"gpt-4-turbo","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-4.1-df03094a9acf","modelId":"gpt-4.1","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-4o-mini-df03094a9acf","modelId":"gpt-4o-mini","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-5.1-df03094a9acf","modelId":"gpt-5.1","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-5.2-df03094a9acf","modelId":"gpt-5.2","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-gpt-5.4-df03094a9acf","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-3.1-405b-instruct-df03094a9acf","modelId":"llama-3.1-405b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-3.1-70b-instruct-df03094a9acf","modelId":"llama-3.1-70b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-3.1-8b-instruct-df03094a9acf","modelId":"llama-3.1-8b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-3.3-70b-instruct-df03094a9acf","modelId":"llama-3.3-70b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-4-maverick-df03094a9acf","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-llama-4-scout-df03094a9acf","modelId":"llama-4-scout","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-mimo-7b-rl-df03094a9acf","modelId":"mimo-7b-rl","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-minimax-m2-df03094a9acf","modelId":"minimax-m2","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-minimax-m2.1-df03094a9acf","modelId":"minimax-m2.1","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-minimax-m2.5-df03094a9acf","modelId":"minimax-m2.5","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-minimax-text-01-df03094a9acf","modelId":"minimax-text-01","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-phi-3.5-mini-instruct-df03094a9acf","modelId":"phi-3.5-mini-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-phi-4-df03094a9acf","modelId":"phi-4","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-phi-4-reasoning-df03094a9acf","modelId":"phi-4-reasoning","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-phi-4-reasoning-plus-df03094a9acf","modelId":"phi-4-reasoning-plus","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3-235b-a22b-df03094a9acf","modelId":"qwen3-235b-a22b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3-235b-a22b-instruct-2507-df03094a9acf","modelId":"qwen3-235b-a22b-instruct-2507","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3-235b-a22b-thinking-2507-df03094a9acf","modelId":"qwen3-235b-a22b-thinking-2507","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3-30b-a3b-thinking-2507-df03094a9acf","modelId":"qwen3-30b-a3b-thinking-2507","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-0.8b-df03094a9acf","modelId":"qwen3.5-0.8b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-122b-a10b-df03094a9acf","modelId":"qwen3.5-122b-a10b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-27b-df03094a9acf","modelId":"qwen3.5-27b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-2b-df03094a9acf","modelId":"qwen3.5-2b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-35b-a3b-df03094a9acf","modelId":"qwen3.5-35b-a3b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-397b-a17b-df03094a9acf","modelId":"qwen3.5-397b-a17b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-4b-df03094a9acf","modelId":"qwen3.5-4b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-qwen3.5-9b-df03094a9acf","modelId":"qwen3.5-9b","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-mmlu-pro-seed-oss-36b-instruct-df03094a9acf","modelId":"seed-oss-36b-instruct","configurationId":null,"sourceUrl":"https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-nv-aa","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/models/comparisons/nvidia-nemotron-3-ultra-550b-a55b-vs-kimi-k2-6","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-nv-browse","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-nv-hle","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-nv-lcb","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-nv-mmlu","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-nv-swev","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-nv-tau2","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-nv-tb21","modelId":"nemotron-3-ultra","configurationId":null,"sourceUrl":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-opus5-aa","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://artificialanalysis.ai/articles/grok-4-6-benchmarks-and-analysis","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-opus5-browse","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/news/claude-opus-5","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-opus5-hle","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/news/claude-opus-5","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-opus5-hle-tools","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/news/claude-opus-5","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-opus5-swepro","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/news/claude-opus-5","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-opus5-swev","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://www.anthropic.com/news/claude-opus-5","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-osworld-claude-fable-5-42c386263956","modelId":"claude-fable-5","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-claude-opus-5-42c386263956","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-claude-sonnet-4-5-20250929-42c386263956","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-claude-sonnet-4-6-42c386263956","modelId":"claude-sonnet-4-6","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-muse-spark-1.1-42c386263956","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-osworld-o3-42c386263956","modelId":"o3","configurationId":null,"sourceUrl":"https://os-world.github.io/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-qwen-aa","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://x.com/ArtificialAnlys/status/2085270415614828675","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-qwen-gpqa","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-qwen-hle","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-qwen-osworld","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-qwen-paper","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-qwen-swepro","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-qwen-tb21","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://qwen.ai/blog?id=qwen3-max","status":"excluded","reason":"Legacy self-report lacks a reviewed comparison configuration"},{"id":"s-swepro-claude-opus-4-6-6112d01393e8","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swepro-gemini-3.1-pro-6112d01393e8","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swepro-gpt-5.4-6112d01393e8","modelId":"gpt-5.4","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swepro-muse-spark-1.1-6112d01393e8","modelId":"muse-spark-1.1","configurationId":null,"sourceUrl":"https://scale.com/leaderboard/swe_bench_pro_public","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-claude-haiku-4-5-20251001-077d8c0cfcca","modelId":"claude-haiku-4-5-20251001","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-claude-opus-4-5-20251101-077d8c0cfcca","modelId":"claude-opus-4-5-20251101","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-claude-opus-4-6-077d8c0cfcca","modelId":"claude-opus-4-6","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-claude-sonnet-4-5-20250929-077d8c0cfcca","modelId":"claude-sonnet-4-5-20250929","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-deepseek-v3.2-077d8c0cfcca","modelId":"deepseek-v3.2","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-devstral-2512-077d8c0cfcca","modelId":"devstral-2512","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-gemini-2.5-flash-077d8c0cfcca","modelId":"gemini-2.5-flash","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-gemini-2.5-pro-077d8c0cfcca","modelId":"gemini-2.5-pro","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-gemini-3-flash-preview-077d8c0cfcca","modelId":"gemini-3-flash-preview","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-glm-4.5-077d8c0cfcca","modelId":"glm-4.5","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-glm-4.6-077d8c0cfcca","modelId":"glm-4.6","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-glm-5-077d8c0cfcca","modelId":"glm-5","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-gpt-oss-120b-077d8c0cfcca","modelId":"gpt-oss-120b","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-llama-4-maverick-077d8c0cfcca","modelId":"llama-4-maverick","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-minimax-m2-077d8c0cfcca","modelId":"minimax-m2","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-minimax-m2.5-077d8c0cfcca","modelId":"minimax-m2.5","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-o3-077d8c0cfcca","modelId":"o3","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-o4-mini-077d8c0cfcca","modelId":"o4-mini","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-swev-qwen3-coder-480b-a35b-instruct-077d8c0cfcca","modelId":"qwen3-coder-480b-a35b-instruct","configurationId":null,"sourceUrl":"https://www.swebench.com/","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-tb21-gemini-3.1-pro-a98710a64150","modelId":"gemini-3.1-pro","configurationId":null,"sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-tb21-gpt-5.5-a98710a64150","modelId":"gpt-5.5","configurationId":null,"sourceUrl":"https://www.tbench.ai/?version=2.1","status":"excluded","reason":"No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately"},{"id":"s-vulcanbench-claude-opus-5-10-opus5-effort-high-2f58434bbe3d","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-claude-opus-5-10-opus5-effort-low-2f58434bbe3d","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-claude-opus-5-10-opus5-effort-medium-2f58434bbe3d","modelId":"claude-opus-5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/10-opus5-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-high-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-low-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-glm-5.3-18-glm53-zcode-harness-max-2f58434bbe3d","modelId":"glm-5.3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/18-glm53-zcode-harness.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-gpt-5.6-sol-07-grok-fable-sol-high-2f58434bbe3d","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-gpt-5.6-sol-07-grok-fable-sol-low-2f58434bbe3d","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-gpt-5.6-sol-07-grok-fable-sol-medium-2f58434bbe3d","modelId":"gpt-5.6-sol","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.5-07-grok-fable-sol-high-2f58434bbe3d","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.5-07-grok-fable-sol-low-2f58434bbe3d","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.5-07-grok-fable-sol-medium-2f58434bbe3d","modelId":"grok-4.5","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/07-grok-fable-sol.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.6-14-grok-46-effort-high-2f58434bbe3d","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.6-14-grok-46-effort-low-2f58434bbe3d","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.6-14-grok-46-effort-medium-2f58434bbe3d","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-grok-4.6-14-grok-46-effort-xhigh-2f58434bbe3d","modelId":"grok-4.6","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/14-grok-46-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-kimi-k3-08-kimi-k3-max-2f58434bbe3d","modelId":"kimi-k3","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/08-kimi-k3.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-high-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-low-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-muse-spark-1.2-19-musespark-effort-xhigh-2f58434bbe3d","modelId":"muse-spark-1.2","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/19-musespark-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen-3.8-max-12-qwen38-max-low-2f58434bbe3d","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen-3.8-max-12-qwen38-max-medium-2f58434bbe3d","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen-3.8-max-12-qwen38-max-xhigh-2f58434bbe3d","modelId":"qwen-3.8-max","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/12-qwen38-max.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen3.8-27b-17-qwen38-27b-effort-low-2f58434bbe3d","modelId":"qwen3.8-27b","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen3.8-27b-17-qwen38-27b-effort-medium-2f58434bbe3d","modelId":"qwen3.8-27b","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"},{"id":"s-vulcanbench-qwen3.8-27b-17-qwen38-27b-effort-xhigh-2f58434bbe3d","modelId":"qwen3.8-27b","configurationId":null,"sourceUrl":"https://vulcanbench.com/benchmarks/17-qwen38-27b-effort.html","status":"excluded","reason":"Supporting evidence outside the reviewed capability core"}]}