{ "source": "Hugging Face official leaderboard API", "sourceUrl": "https://huggingface.co/docs/hub/en/leaderboard-data-guide", "syncedAt": "2026-09-19T07:21:06.403Z", "benchmarks": [ { "id": "swe-bench-verified", "label": "SWE-bench Verified", "domain": "coding", "dataset": "SWE-bench/SWE-bench_Verified", "sourceUrl": "https://www.swebench.com/", "metric": "% resolved", "datasetUpdatedAt": "2026-08-16T04:23:43.000Z", "rows": [ { "rank": 1, "value": 86, "verified": false, "modelId": "ornith-ai/Ornith-1.5-397B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-397B", "name": "Ornith-1.5-397B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 403397928944 }, { "rank": 2, "value": 85.6, "verified": false, "modelId": "mindlab-research/Macaron-V1-Venti", "source": { "url": "https://huggingface.co/mindlab-research/Macaron-V1-Venti", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 753329940480 }, { "rank": 3, "value": 85.6, "verified": false, "modelId": "mindlab-research/Macaron-V1-Coding-Venti", "source": { "url": "https://huggingface.co/mindlab-research/Macaron-V1-Coding-Venti/blob/0a7ec8fdf72e0757decabd90cc3305bed1fed1c6/README.md#L68-L76", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 753329940480 }, { "rank": 4, "value": 82.4, "verified": false, "modelId": "ornith-ai/Ornith-1.0-397B", "source": { "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-397B", "name": "Ornith-1.0-397B model card", "isExternal": true }, "lowerIsBetter": false, "parameters": 396802360816 }, { "rank": 5, "value": 80.6, "verified": false, "modelId": "deepseek-ai/DeepSeek-V4-Pro", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1598839674782 }, { "rank": 6, "value": 80.5, "verified": false, "modelId": "MiniMaxAI/MiniMax-M3", "source": { "url": "https://huggingface.co/MiniMaxAI/MiniMax-M3", "name": "MiniMax-M3 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 427040140160 }, { "rank": 7, "value": 80.2, "verified": false, "modelId": "moonshotai/Kimi-K2.6", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K2.6", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026879376368 }, { "rank": 8, "value": 80.2, "verified": false, "modelId": "thinkingmachines/Inkling-Small", "source": { "url": "https://huggingface.co/thinkingmachines/Inkling-Small", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 265956439090 }, { "rank": 9, "value": 79, "verified": false, "modelId": "deepseek-ai/DeepSeek-V4-Flash", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 290944616402 }, { "rank": 10, "value": 79, "verified": false, "modelId": "ornith-ai/Ornith-1.5-35B-A3B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B", "name": "Ornith-1.5-35B-A3B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 35951822704 }, { "rank": 11, "value": 78.9, "verified": false, "modelId": "XiaomiMiMo/MiMo-V2.5-Pro", "source": { "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1023244718976 }, { "rank": 12, "value": 78.4, "verified": false, "modelId": "dots-studio/dots3-note-prev", "source": { "url": "https://huggingface.co/dots-studio/dots3-note-prev", "name": "dots3-note Preview model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 288443400864 }, { "rank": 13, "value": 78, "verified": false, "modelId": "tencent/Hy3", "source": { "url": "https://huggingface.co/tencent/Hy3", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 298786155776 }, { "rank": 14, "value": 77.8, "verified": false, "modelId": "zai-org/GLM-5", "source": { "url": "https://huggingface.co/zai-org/GLM-5/", "name": "Model card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 753864139008 }, { "rank": 15, "value": 77.6, "verified": false, "modelId": "mistralai/Mistral-Medium-3.5-128B", "source": { "url": "https://huggingface.co/mistralai/Mistral-Medium-3.5-128B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 127704210176 }, { "rank": 16, "value": 77.6, "verified": false, "modelId": "thinkingmachines/Inkling", "source": { "url": "https://huggingface.co/thinkingmachines/Inkling", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 952377623626 }, { "rank": 17, "value": 77.2, "verified": false, "modelId": "Qwen/Qwen3.6-27B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.6-27B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 18, "value": 76.4, "verified": false, "modelId": "Qwen/Qwen3.5-397B-A17B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 403397928944 }, { "rank": 19, "value": 76, "verified": false, "modelId": "meta-models/Muse-Glimmer-30B", "source": { "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B", "name": "Muse Glimmer-30B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 29776626688 }, { "rank": 20, "value": 75.8, "verified": false, "modelId": "MiniMaxAI/MiniMax-M2.5", "source": { "url": "https://www.swebench.com/", "name": "SWE-Bench official evaluation", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 228703644928 }, { "rank": 21, "value": 75.6, "verified": false, "modelId": "ornith-ai/Ornith-1.0-35B", "source": { "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-35B", "name": "Ornith-1.0-35B model card", "isExternal": true }, "lowerIsBetter": false, "parameters": 664944 }, { "rank": 22, "value": 75.4, "verified": false, "modelId": "mindlab-research/Macaron-V1-Tall", "source": { "url": "https://huggingface.co/mindlab-research/Macaron-V1-Tall/blob/d0b2199c3572d336bcfe9e027ec519314cf608bd/assets/v1_benchmark.png", "name": "Model Card benchmark chart", "isExternal": false }, "lowerIsBetter": false, "parameters": 35951822704 }, { "rank": 23, "value": 74.8, "verified": false, "modelId": "Multilingual-Multimodal-NLP/IndustrialCoder", "source": { "url": "https://huggingface.co/papers/2603.16790", "name": "IndustrialCoder technical report", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 31992714240 }, { "rank": 24, "value": 74.6, "verified": false, "modelId": "poolside/Laguna-M.1", "source": { "url": "https://huggingface.co/poolside/Laguna-M.1", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 225795725568 }, { "rank": 25, "value": 74.4, "verified": false, "modelId": "stepfun-ai/Step-3.5-Flash", "source": { "url": "https://arxiv.org/abs/2602.10604", "name": "Step 3.5 Flash Paper", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 199384301376 }, { "rank": 26, "value": 74.4, "verified": false, "modelId": "tencent/Hy3-preview", "source": { "url": "https://huggingface.co/tencent/Hy3-preview", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 298786155776 }, { "rank": 27, "value": 74, "verified": false, "modelId": "MiniMaxAI/MiniMax-M2.1", "source": { "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.1", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 228689764864 }, { "rank": 28, "value": 74, "verified": false, "modelId": "inclusionAI/Ring-2.6-1T", "source": { "url": "https://huggingface.co/inclusionAI/Ring-2.6-1T", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1025657871744 }, { "rank": 29, "value": 73.8, "verified": false, "modelId": "zai-org/GLM-4.7", "source": { "url": "https://huggingface.co/zai-org/GLM-4.7", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 358337791296 }, { "rank": 30, "value": 73.4, "verified": false, "modelId": "Qwen/Qwen3.6-35B-A3B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 35951822704 }, { "rank": 31, "value": 72.8, "verified": false, "modelId": "zai-org/GLM-5", "source": { "url": "https://www.swebench.com/", "name": "SWE-Bench official evaluation", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 753864139008 }, { "rank": 32, "value": 72.4, "verified": false, "modelId": "Qwen/Qwen3.5-27B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-27B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 33, "value": 72.2, "verified": false, "modelId": "inclusionAI/Ling-2.6-1T", "source": { "url": "https://huggingface.co/inclusionAI/Ling-2.6-1T", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1025657871744 }, { "rank": 34, "value": 72, "verified": false, "modelId": "Qwen/Qwen3.5-122B-A10B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 125086497008 }, { "rank": 35, "value": 71.9, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 560524578816 }, { "rank": 36, "value": 71.3, "verified": false, "modelId": "moonshotai/Kimi-K2-Thinking", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K2-Thinking", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026408240256 }, { "rank": 37, "value": 70.9, "verified": false, "modelId": "poolside/Laguna-XS-2.1", "source": { "url": "https://huggingface.co/poolside/Laguna-XS-2.1", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 33442617088 }, { "rank": 38, "value": 70.8, "verified": false, "modelId": "moonshotai/Kimi-K2.5", "source": { "url": "https://www.swebench.com/", "name": "SWE-Bench official evaluation", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026879376368 }, { "rank": 39, "value": 70.6, "verified": false, "modelId": "Qwen/Qwen3-Coder-Next", "source": { "url": "https://huggingface.co/papers/2603.00729", "name": "Qwen3-Coder-Next technical report", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 79674391296 }, { "rank": 40, "value": 70.6, "verified": false, "modelId": "ornith-ai/Ornith-1.5-9B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-9B", "name": "Ornith-1.5-9B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 9653104368 }, { "rank": 41, "value": 70.4, "verified": false, "modelId": "upstage/Solar-Open2-250B", "source": { "url": "https://huggingface.co/upstage/Solar-Open2-250B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 250287810304 }, { "rank": 42, "value": 69.9, "verified": false, "modelId": "poolside/Laguna-XS.2", "source": { "url": "https://huggingface.co/poolside/Laguna-XS.2", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 33442617088 }, { "rank": 43, "value": 69.7, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 302826566168 }, { "rank": 44, "value": 69.4, "verified": false, "modelId": "MiniMaxAI/MiniMax-M2", "source": { "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 228689764864 }, { "rank": 45, "value": 69.4, "verified": false, "modelId": "ornith-ai/Ornith-1.0-9B", "source": { "url": "https://huggingface.co/deepreinforce-ai/Ornith-1.0-9B", "name": "Ornith-1.0-9B model card", "isExternal": true }, "lowerIsBetter": false, "parameters": 1469680 }, { "rank": 46, "value": 68.2, "verified": false, "modelId": "MuVeraAI/Laguna-XS.2", "source": { "url": "https://huggingface.co/poolside/Laguna-XS.2", "name": "Model Card", "isExternal": true }, "lowerIsBetter": false, "parameters": 33442617088 }, { "rank": 47, "value": 67.6, "verified": false, "modelId": "CohereLabs/North-Mini-Code-1.0", "source": { "url": "https://huggingface.co/CohereLabs/North-Mini-Code-1.0", "name": "North Mini Code Model Page", "isExternal": false, "author": { "_id": "640ca1c93623f6a56ddab373", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png", "fullname": "Cohere Labs", "name": "CohereLabs", "type": "org", "isHf": false, "isHfAdmin": false, "isMod": false, "plan": "enterprise", "followerCount": 3721, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 30484303872 }, { "rank": 48, "value": 64, "verified": false, "modelId": "internlm/Intern-S2-Preview", "source": { "url": "https://huggingface.co/internlm/Intern-S2-Preview", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 36098254656 }, { "rank": 49, "value": 63.1, "verified": false, "modelId": "openpangu/openPangu-2.0-Flash", "source": { "url": "https://huggingface.co/openpangu/openPangu-2.0-Flash", "name": "openPangu-2.0-Flash model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 100136311993 }, { "rank": 50, "value": 62.4, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 51, "value": 61.2, "verified": false, "modelId": "inclusionAI/Ling-2.6-flash", "source": { "url": "https://huggingface.co/inclusionAI/Ling-2.6-flash", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 107494409216 }, { "rank": 52, "value": 60.7, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 53, "value": 60.47, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 54, "value": 60.47, "verified": false, "modelId": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 55, "value": 59.2, "verified": false, "modelId": "zai-org/GLM-4.7-Flash", "source": { "url": "https://huggingface.co/zai-org/GLM-4.7-Flash", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 31221488576 }, { "rank": 56, "value": 59.2, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 57, "value": 59.2, "verified": false, "modelId": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 58, "value": 57.6, "verified": false, "modelId": "openpangu/openPangu-2.0-Flash", "source": { "url": "https://huggingface.co/openpangu/openPangu-2.0-Flash", "name": "openPangu-2.0-Flash model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 100136311993 }, { "rank": 59, "value": 53.9, "verified": false, "modelId": "facebook/cwm", "source": { "url": "https://huggingface.co/papers/2510.02387", "name": "CWM technical report", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 32581097472 }, { "rank": 60, "value": 53.73, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 61, "value": 53.73, "verified": false, "modelId": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": true, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 62, "value": 53.2, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 63, "value": 52.8, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 17820210764 }, { "rank": 64, "value": 52.6, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 65, "value": 51.56, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 31577937344 }, { "rank": 66, "value": 47.9, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 67, "value": 37.4, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 } ] }, { "id": "gpqa", "label": "GPQA", "domain": "reasoning", "dataset": "Idavidrein/gpqa", "sourceUrl": "https://huggingface.co/datasets/Idavidrein/gpqa", "metric": "accuracy", "datasetUpdatedAt": "2026-03-05T23:06:58.000Z", "rows": [ { "rank": 1, "value": 93.5, "verified": false, "modelId": "moonshotai/Kimi-K3", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K3", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 2779931837184 }, { "rank": 2, "value": 92.8, "verified": false, "modelId": "ornith-ai/Ornith-1.5-397B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-397B", "name": "Ornith-1.5-397B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 403397928944 }, { "rank": 3, "value": 92.6, "verified": false, "modelId": "Qwen/Qwen3.8-2.4T-A95B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 2446182725504 }, { "rank": 4, "value": 92.3, "verified": false, "modelId": "tencent/Hy4-preview", "source": { "url": "https://huggingface.co/tencent/Hy4-preview", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 779960992733 }, { "rank": 5, "value": 91.7, "verified": false, "modelId": "Qwen/Qwen3.8-Flash-Next", "source": { "url": "https://huggingface.co/Qwen/Qwen3.8-Flash-Next", "name": "Qwen3.8-Flash-Next model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 179999981459 }, { "rank": 6, "value": 91.2, "verified": false, "modelId": "zai-org/GLM-5.2", "source": { "url": "https://huggingface.co/zai-org/GLM-5.2", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 753329940480 }, { "rank": 7, "value": 90.9, "verified": false, "modelId": "FINAL-Bench/Darwin-398B-JGOS", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-398B-JGOS", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 403397928944 }, { "rank": 8, "value": 90.9, "verified": false, "modelId": "deepseek-ai/DeepSeek-V4.1-Flash", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash", "name": "DeepSeek-V4.1-Flash model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 763205315794 }, { "rank": 9, "value": 90.5, "verified": false, "modelId": "moonshotai/Kimi-K2.6", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K2.6", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026879376368 }, { "rank": 10, "value": 90.4, "verified": false, "modelId": "tencent/Hy3", "source": { "url": "https://huggingface.co/tencent/Hy3", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 298786155776 }, { "rank": 11, "value": 90.1, "verified": false, "modelId": "deepseek-ai/DeepSeek-V4-Pro", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1598839674782 }, { "rank": 12, "value": 89.5, "verified": false, "modelId": "thinkingmachines/Inkling-Small", "source": { "url": "https://huggingface.co/thinkingmachines/Inkling-Small", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 265956439090 }, { "rank": 13, "value": 89.39, "verified": false, "modelId": "FINAL-Bench/Darwin-28B-REASON", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-28B-REASON", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 26895998464 }, { "rank": 14, "value": 89.2, "verified": false, "modelId": "Qwen/Qwen3.8-27B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.8-27B", "name": "Qwen3.8-27B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 15, "value": 89.2, "verified": false, "modelId": "ornith-ai/Ornith-1.5-35B-A3B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B", "name": "Ornith-1.5-35B-A3B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 35951822704 }, { "rank": 16, "value": 88.4, "verified": false, "modelId": "Qwen/Qwen3.5-397B-A17B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-397B-A17B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 403397928944 }, { "rank": 17, "value": 88.4, "verified": false, "modelId": "FINAL-Bench/Darwin-36B-Opus", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-36B-Opus", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 34660610688 }, { "rank": 18, "value": 88.38, "verified": false, "modelId": "FINAL-Bench/Darwin-60B-DUO", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-60B-DUO", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false }, { "rank": 19, "value": 88.27, "verified": false, "modelId": "inclusionAI/Ring-2.6-1T", "source": { "url": "https://huggingface.co/inclusionAI/Ring-2.6-1T", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1025657871744 }, { "rank": 20, "value": 88.1, "verified": false, "modelId": "deepseek-ai/DeepSeek-V4-Flash", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 290944616402 }, { "rank": 21, "value": 87.9, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 302826566168 }, { "rank": 22, "value": 87.8787878788, "verified": false, "modelId": "zai-org/GLM-4.7-FP8", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/97/fa/97faabc6-a7ca-4cad-8d29-307103287d91.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 358458391872 }, { "rank": 23, "value": 87.8, "verified": false, "modelId": "Qwen/Qwen3.6-27B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.6-27B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 24, "value": 87.6, "verified": false, "modelId": "moonshotai/Kimi-K2.5", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K2.5", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026879376368 }, { "rank": 25, "value": 87.3737373737, "verified": false, "modelId": "moonshotai/Kimi-K2.5", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5c/4b/5c4b9bd9-14db-4c11-bf99-9661461459f6.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 1026879376368 }, { "rank": 26, "value": 87.2, "verified": false, "modelId": "tencent/Hy3-preview", "source": { "url": "https://huggingface.co/tencent/Hy3-preview", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 298786155776 }, { "rank": 27, "value": 87.2, "verified": false, "modelId": "thinkingmachines/Inkling", "source": { "url": "https://huggingface.co/thinkingmachines/Inkling", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 952377623626 }, { "rank": 28, "value": 87, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 560524578816 }, { "rank": 29, "value": 86.9, "verified": false, "modelId": "FINAL-Bench/Darwin-27B-Opus", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-27B-Opus", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 30, "value": 86.6, "verified": false, "modelId": "Qwen/Qwen3.5-122B-A10B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-122B-A10B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 125086497008 }, { "rank": 31, "value": 86.4, "verified": false, "modelId": "ornith-ai/Ornith-1.5-9B", "source": { "url": "https://huggingface.co/ornith-ai/Ornith-1.5-9B", "name": "Ornith-1.5-9B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 9653104368 }, { "rank": 32, "value": 86.36, "verified": false, "modelId": "FINAL-Bench/Ourbox-35B-JGOS", "source": { "url": "https://huggingface.co/FINAL-Bench/Ourbox-35B-JGOS", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 34660610688 }, { "rank": 33, "value": 86.3, "verified": false, "modelId": "upstage/Solar-Open2-250B", "source": { "url": "https://huggingface.co/upstage/Solar-Open2-250B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 250287810304 }, { "rank": 34, "value": 86.2, "verified": false, "modelId": "zai-org/GLM-5.1", "source": { "url": "https://huggingface.co/zai-org/GLM-5.1", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 753864139008 }, { "rank": 35, "value": 86.2, "verified": false, "modelId": "INCModel3/GLM-5.1-MXFP4-Mixed-CT-AutoRound", "source": { "url": "https://huggingface.co/zai-org/GLM-5.1", "name": "Model Card", "isExternal": true }, "lowerIsBetter": false, "parameters": 753864139008 }, { "rank": 36, "value": 86, "verified": false, "modelId": "zai-org/GLM-5", "source": { "url": "https://huggingface.co/zai-org/GLM-5", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 753864139008 }, { "rank": 37, "value": 86, "verified": false, "modelId": "Qwen/Qwen3.6-35B-A3B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.6-35B-A3B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 35951822704 }, { "rank": 38, "value": 85.9, "verified": false, "modelId": "FINAL-Bench/Darwin-31B-Opus", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-31B-Opus", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 31273088876 }, { "rank": 39, "value": 85.7, "verified": false, "modelId": "zai-org/GLM-4.7", "source": { "url": "https://huggingface.co/zai-org/GLM-4.7", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 358337791296 }, { "rank": 40, "value": 85.6, "verified": false, "modelId": "skt/A.X-K2", "source": { "url": "https://huggingface.co/skt/A.X-K2/blob/fb412dcd22e9c5ac43b2967d6c5e8a7d0e667b0f/README.md#L134-L152", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 691690231040 }, { "rank": 41, "value": 85.5, "verified": false, "modelId": "Qwen/Qwen3.5-27B", "source": { "url": "https://huggingface.co/Qwen/Qwen3.5-27B", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 42, "value": 85.3535353535, "verified": false, "modelId": "zai-org/GLM-5-FP8", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/8a/87/8a87d622-4abb-48a7-8ac3-594e31a85525.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 753910024032 }, { "rank": 43, "value": 85.2, "verified": false, "modelId": "MiniMaxAI/MiniMax-M2.5", "source": { "url": "https://huggingface.co/MiniMaxAI/MiniMax-M2.5", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 228703644928 }, { "rank": 44, "value": 85, "verified": false, "modelId": "FINAL-Bench/Darwin-4B-David", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-4B-David", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 7996156490 }, { "rank": 45, "value": 84.8484848485, "verified": false, "modelId": "Qwen/Qwen3.5-122B-A10B", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/58/60/5860f5bd-926e-4ece-bc87-a1af551a6280.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 125086497008 }, { "rank": 46, "value": 84.5, "verified": false, "modelId": "moonshotai/Kimi-K2-Thinking", "source": { "url": "https://huggingface.co/moonshotai/Kimi-K2-Thinking", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 1026408240256 }, { "rank": 47, "value": 84.34, "verified": false, "modelId": "FINAL-Bench/Darwin-9B-NEG", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-9B-NEG", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 9653104368 }, { "rank": 48, "value": 84.34, "verified": false, "modelId": "JGOS-Model/JGOS-31B-Citizen", "source": { "url": "https://huggingface.co/JGOS-Model/JGOS-31B-Citizen", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 31273086512 }, { "rank": 49, "value": 84.34, "verified": false, "modelId": "FlagRelease/Darwin-9B-NEG-FINAL-hygon-FlagOS", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-9B-NEG", "name": "Model Card", "isExternal": true }, "lowerIsBetter": false, "parameters": 9653104368 }, { "rank": 50, "value": 84.34, "verified": false, "modelId": "FlagRelease/Darwin-9B-NEG-ansulev-hygon-FlagOS", "source": { "url": "https://huggingface.co/FINAL-Bench/Darwin-9B-NEG", "name": "Model Card", "isExternal": true }, "lowerIsBetter": false, "parameters": 9653104368 }, { "rank": 51, "value": 83.7, "verified": false, "modelId": "openpangu/openPangu-2.0-Flash", "source": { "url": "https://huggingface.co/openpangu/openPangu-2.0-Flash", "name": "openPangu-2.0-Flash model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 100136311993 }, { "rank": 52, "value": 83.5, "verified": false, "modelId": "stepfun-ai/Step-3.5-Flash", "source": { "url": "https://arxiv.org/abs/2602.10604", "name": "Step 3.5 Flash Paper", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 199384301376 }, { "rank": 53, "value": 83.5, "verified": false, "modelId": "meta-models/Muse-Glimmer-30B", "source": { "url": "https://huggingface.co/meta-models/Muse-Glimmer-30B", "name": "Muse Glimmer-30B model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 29776626688 }, { "rank": 54, "value": 83.3333333333, "verified": false, "modelId": "XiaomiMiMo/MiMo-V2-Flash", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/36/22/3622b785-41c0-4a96-b867-5bde46851587.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 309785318400 }, { "rank": 55, "value": 83.3333333333, "verified": false, "modelId": "zai-org/GLM-5.1-FP8", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/52/23/522348c0-d242-4517-b97c-4e55c4261882.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 753910024032 }, { "rank": 56, "value": 82.7, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 57, "value": 82.7, "verified": false, "modelId": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 58, "value": 81.8181818182, "verified": false, "modelId": "Qwen/Qwen3.5-27B", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5b/a4/5ba4cf19-18b3-4d08-bad0-ef29422cb18a.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 27781427952 }, { "rank": 59, "value": 81.3131313131, "verified": false, "modelId": "zai-org/GLM-4.6-FP8", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/7e/18/7e18ad63-4a0a-4d9d-a4ec-40b683b42981.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 358458543424 }, { "rank": 60, "value": 80.9, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 61, "value": 80.8080808081, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/5d/3e/5d3e8832-c770-4796-957b-dfaefbd3bb2a.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 62, "value": 80.8080808081, "verified": false, "modelId": "MiniMaxAI/MiniMax-M2.1", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/08/7b/087b0dc6-3c87-4f40-8458-16f19de92200.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 228689764864 }, { "rank": 63, "value": 80.5, "verified": false, "modelId": "meituan-longcat/LongCat-Flash-Thinking-2601", "source": { "url": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 561862880256 }, { "rank": 64, "value": 80.5, "verified": false, "modelId": "LGAI-EXAONE/EXAONE-4.5-33B", "source": { "url": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.5-33B", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 34350097664 }, { "rank": 65, "value": 80.1, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 66, "value": 79.8, "verified": false, "modelId": "openpangu/openPangu-2.0-Flash", "source": { "url": "https://huggingface.co/openpangu/openPangu-2.0-Flash", "name": "openPangu-2.0-Flash model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 100136311993 }, { "rank": 67, "value": 79.23, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 68, "value": 79.23, "verified": false, "modelId": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "name": "Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 69, "value": 79.1, "verified": false, "modelId": "LGAI-EXAONE/K-EXAONE-236B-A23B", "source": { "url": "https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 237099669632 }, { "rank": 70, "value": 78.7878787879, "verified": false, "modelId": "deepseek-ai/DeepSeek-R1-0528", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/a1/dd/a1dd2ea2-f092-423e-bc53-04c2fba5948d.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 684531386000 }, { "rank": 71, "value": 77.2727272727, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/bd/1f/bd1fe04f-7d58-4045-be60-7150500d537f.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 123611012096 }, { "rank": 72, "value": 76.1, "verified": false, "modelId": "nvidia/Nemotron-Cascade-2-30B-A3B", "source": { "url": "https://huggingface.co/nvidia/Nemotron-Cascade-2-30B-A3B", "name": "Model Card", "isExternal": false, "author": { "_id": "6141a88b3a0ec78603c9e784", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg", "fullname": "merve", "name": "merve", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 10911, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 31577937344 }, { "rank": 73, "value": 75.57, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 17820210764 }, { "rank": 74, "value": 75.44, "verified": false, "modelId": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "source": { "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 31577937344 }, { "rank": 75, "value": 75.2, "verified": false, "modelId": "zai-org/GLM-4.7-Flash", "source": { "url": "https://huggingface.co/zai-org/GLM-4.7-Flash", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 31221488576 }, { "rank": 76, "value": 74.43, "verified": false, "modelId": "jdopensource/JoyAI-LLM-Flash", "source": { "url": "https://huggingface.co/jdopensource/JoyAI-LLM-Flash", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 49286094592 }, { "rank": 77, "value": 74.2, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 78, "value": 74, "verified": false, "modelId": "skt/A.X-K1", "source": { "url": "https://huggingface.co/skt/A.X-K1", "name": "A.X K1 model card", "isExternal": false }, "lowerIsBetter": false, "parameters": 518983059456 }, { "rank": 79, "value": 73.5, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 80, "value": 73.1, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 81, "value": 72.2222222222, "verified": false, "modelId": "Qwen/Qwen3-30B-A3B-Thinking-2507", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/4b/02/4b02c12c-3f7b-45c8-b746-c590860a7a36.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 30532122624 }, { "rank": 82, "value": 71.7171717172, "verified": false, "modelId": "zai-org/GLM-4.5-Air", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/9c/77/9c7740fd-9cad-445c-9681-eb576e2a110e.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 110468824832 }, { "rank": 83, "value": 71.5, "verified": false, "modelId": "deepseek-ai/DeepSeek-R1", "source": { "url": "https://huggingface.co/deepseek-ai/DeepSeek-R1", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 684489845504 }, { "rank": 84, "value": 71.5, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 85, "value": 71.2, "verified": false, "modelId": "mistralai/Mistral-Small-4-119B-2603", "source": { "url": "https://huggingface.co/mistralai/Mistral-Small-4-119B-2603", "name": "Model Card", "isExternal": false, "author": { "_id": "5f1158120c833276f61f1a84", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1608042047613-5f1158120c833276f61f1a84.jpeg", "fullname": "Niels Rogge", "name": "nielsr", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 1307, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 119401317952 }, { "rank": 86, "value": 68.1, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 87, "value": 67.1, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 88, "value": 67.1, "verified": false, "modelId": "openai/gpt-oss-120b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 116829156672 }, { "rank": 89, "value": 66.7, "verified": false, "modelId": "XiaomiMiMo/MiMo-V2.5-Pro", "source": { "url": "https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro", "name": "Model Card", "isExternal": false }, "lowerIsBetter": false, "parameters": 1023244718976 }, { "rank": 90, "value": 66, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 91, "value": 65.8, "verified": false, "modelId": "Qwen/Qwen3-4B-Thinking-2507", "source": { "url": "https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 4022468096 }, { "rank": 92, "value": 62, "verified": false, "modelId": "Qwen/Qwen3-4B-Instruct-2507", "source": { "url": "https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507", "name": "Model Card", "isExternal": false, "author": { "_id": "62d648291fa3e4e7ae3fa6e8", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/62d648291fa3e4e7ae3fa6e8/oatOwf8Xqe5eDbCSuYqCd.png", "fullname": "ben burtenshaw", "name": "burtenshaw", "type": "user", "isPro": false, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 4947, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 4022468096 }, { "rank": 93, "value": 58.5858585859, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/6f/c3/6fc3630c-36f0-4ba9-9f34-3c9f73dec76a.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 94, "value": 58.2070707071, "verified": false, "modelId": "deepseek-ai/DeepSeek-V3", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/0a/db/0adbcd9f-38e6-414a-88b1-7bd928d4c72e.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 684531386000 }, { "rank": 95, "value": 58, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 96, "value": 57.6, "verified": false, "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking", "lowerIsBetter": false, "parameters": 12149923072 }, { "rank": 97, "value": 56.8, "verified": false, "modelId": "openai/gpt-oss-20b", "source": { "url": "https://arxiv.org/abs/2508.10925", "name": "GPT-OSS Model Card", "isExternal": true, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 20914757184 }, { "rank": 98, "value": 50.5050505051, "verified": false, "modelId": "CohereLabs/c4ai-command-a-03-2025", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/b2/77/b27740dc-a017-4738-8dd0-c18973b61d9e.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 111057580032 }, { "rank": 99, "value": 46.0858585859, "verified": false, "modelId": "meta-llama/Llama-3.2-90B-Vision-Instruct", "source": { "url": "https://huggingface.co/datasets/evaleval/EEE_datastore/blob/192329fb7d6b15b7b0936a1a58ae862aa7e8ba24/flat/objects/94/0f/940ff5c0-b932-4c37-9eb5-27cbd4997484.json", "name": "EvalEval", "isExternal": true }, "lowerIsBetter": false, "parameters": 88593355323 }, { "rank": 100, "value": 45.76, "verified": false, "modelId": "ibm-granite/granite-4.1-30b", "source": { "url": "https://huggingface.co/ibm-granite/granite-4.1-30b", "name": "Model Card", "isExternal": false, "author": { "_id": "63e0eea7af523c37e5a77966", "avatarUrl": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678663263366-63e0eea7af523c37e5a77966.jpeg", "fullname": "Nathan Habib", "name": "SaylorTwift", "type": "user", "isPro": true, "isHf": true, "isHfAdmin": false, "isMod": false, "followerCount": 479, "isUserFollowing": false } }, "lowerIsBetter": false, "parameters": 28865728512 } ] } ] }