diff --git "a/data.json" "b/data.json" --- "a/data.json" +++ "b/data.json" @@ -1211,1403 +1211,1403 @@ } ] }, - "mmluPro": { - "name": "MMLU-Pro", - "dataset": "TIGER-Lab/MMLU-Pro", + "sweVerified": { + "name": "SWE-bench Verified", + "dataset": "SWE-bench/SWE-bench_Verified", "lower_is_better": false, "models": [ { - "model_id": "FINAL-Bench/Darwin-180B-RSI", - "short_name": "Darwin-180B-RSI", - "provider": "FINAL-Bench", - "score": 88.12, - "date": "2026-09-28" + "model_id": "ornith-ai/Ornith-1.5-397B", + "short_name": "Ornith-1.5-397B", + "provider": "ornith-ai", + "score": 86.0, + "date": "2026-08-18" }, { - "model_id": "MiniMaxAI/MiniMax-M2.1", - "short_name": "MiniMax-M2.1", - "provider": "MiniMaxAI", - "score": 88.0, - "date": "2025-12-20" + "model_id": "mindlab-research/Macaron-V1-Venti", + "short_name": "Macaron-V1-Venti", + "provider": "mindlab-research", + "score": 85.6, + "date": "2026-07-20" }, { - "model_id": "internlm/Intern-S2-Preview", - "short_name": "Intern-S2-Preview", - "provider": "internlm", - "score": 88.0, - "date": "2026-05-15" + "model_id": "mindlab-research/Macaron-V1-Coding-Venti", + "short_name": "Macaron-V1-Coding-Venti", + "provider": "mindlab-research", + "score": 85.6, + "date": "2026-07-20" }, { - "model_id": "Qwen/Qwen3.5-397B-A17B", - "short_name": "Qwen3.5-397B-A17B", - "provider": "Qwen", - "score": 87.8, - "date": "2026-02-16" + "model_id": "ornith-ai/Ornith-1.0-397B", + "short_name": "Ornith-1.0-397B", + "provider": "ornith-ai", + "score": 82.4, + "date": "2026-06-23" }, { "model_id": "deepseek-ai/DeepSeek-V4-Pro", "short_name": "DeepSeek-V4-Pro", "provider": "deepseek-ai", - "score": 87.5, + "score": 80.6, "date": "2026-04-22" }, { - "model_id": "moonshotai/Kimi-K2.5", - "short_name": "Kimi-K2.5", - "provider": "moonshotai", - "score": 87.1, - "date": "2026-01-01" - }, - { - "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "provider": "nvidia", - "score": 86.8, - "date": "2026-06-03" + "model_id": "MiniMaxAI/MiniMax-M3", + "short_name": "MiniMax-M3", + "provider": "MiniMaxAI", + "score": 80.5, + "date": "2026-06-02" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", - "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", - "provider": "nvidia", - "score": 86.8, - "date": "2026-06-03" + "model_id": "moonshotai/Kimi-K2.6", + "short_name": "Kimi-K2.6", + "provider": "moonshotai", + "score": 80.2, + "date": "2026-04-14" }, { - "model_id": "Qwen/Qwen3.5-122B-A10B", - "short_name": "Qwen3.5-122B-A10B", - "provider": "Qwen", - "score": 86.7, - "date": "2026-02-24" + "model_id": "thinkingmachines/Inkling-Small", + "short_name": "Inkling-Small", + "provider": "thinkingmachines", + "score": 80.2, + "date": "2026-07-27" }, { "model_id": "deepseek-ai/DeepSeek-V4-Flash", "short_name": "DeepSeek-V4-Flash", "provider": "deepseek-ai", - "score": 86.4, + "score": 79.0, "date": "2026-04-22" }, { - "model_id": "Qwen/Qwen3.6-27B", - "short_name": "Qwen3.6-27B", - "provider": "Qwen", - "score": 86.2, - "date": "2026-04-21" + "model_id": "ornith-ai/Ornith-1.5-35B-A3B", + "short_name": "Ornith-1.5-35B-A3B", + "provider": "ornith-ai", + "score": 79.0, + "date": "2026-08-18" }, { - "model_id": "upstage/Solar-Open2-250B", - "short_name": "Solar-Open2-250B", - "provider": "upstage", - "score": 86.2, - "date": "2026-07-22" + "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", + "short_name": "MiMo-V2.5-Pro", + "provider": "XiaomiMiMo", + "score": 78.9, + "date": "2026-04-27" }, { - "model_id": "Qwen/Qwen3.5-27B", - "short_name": "Qwen3.5-27B", - "provider": "Qwen", - "score": 86.1, - "date": "2026-02-24" + "model_id": "dots-studio/dots3-note-prev", + "short_name": "dots3-note-prev", + "provider": "dots-studio", + "score": 78.4, + "date": "2026-08-09" + }, + { + "model_id": "tencent/Hy3", + "short_name": "Hy3", + "provider": "tencent", + "score": 78.0, + "date": "2026-07-02" }, { "model_id": "zai-org/GLM-5", "short_name": "GLM-5", "provider": "zai-org", - "score": 86.0, + "score": 77.8, "date": "2026-02-11" }, { - "model_id": "Qwen/Qwen3.6-35B-A3B", - "short_name": "Qwen3.6-35B-A3B", - "provider": "Qwen", - "score": 85.2, - "date": "2026-04-15" + "model_id": "mistralai/Mistral-Medium-3.5-128B", + "short_name": "Mistral-Medium-3.5-128B", + "provider": "mistralai", + "score": 77.6, + "date": "2026-03-31" }, { - "model_id": "deepseek-ai/DeepSeek-R1-0528", - "short_name": "DeepSeek-R1-0528", - "provider": "deepseek-ai", - "score": 85.0, - "date": "2025-05-28" + "model_id": "thinkingmachines/Inkling", + "short_name": "Inkling", + "provider": "thinkingmachines", + "score": 77.6, + "date": "2026-07-14" }, { - "model_id": "zai-org/GLM-4.5", - "short_name": "GLM-4.5", - "provider": "zai-org", - "score": 84.6, - "date": "2025-07-20" + "model_id": "Qwen/Qwen3.6-27B", + "short_name": "Qwen3.6-27B", + "provider": "Qwen", + "score": 77.2, + "date": "2026-04-21" }, { - "model_id": "stepfun-ai/Step-3.5-Flash", - "short_name": "Step-3.5-Flash", - "provider": "stepfun-ai", - "score": 84.4, - "date": "2026-02-01" + "model_id": "Qwen/Qwen3.5-397B-A17B", + "short_name": "Qwen3.5-397B-A17B", + "provider": "Qwen", + "score": 76.4, + "date": "2026-02-16" }, { - "model_id": "deepseek-ai/DeepSeek-R1", - "short_name": "DeepSeek-R1", - "provider": "deepseek-ai", - "score": 84.0, - "date": "2025-01-20" + "model_id": "meta-models/Muse-Glimmer-30B", + "short_name": "Muse-Glimmer-30B", + "provider": "meta-models", + "score": 76.0, + "date": "2026-08-09" }, { - "model_id": "LGAI-EXAONE/K-EXAONE-236B-A23B", - "short_name": "K-EXAONE-236B-A23B", - "provider": "LGAI-EXAONE", - "score": 83.8, - "date": "2025-12-26" + "model_id": "MiniMaxAI/MiniMax-M2.5", + "short_name": "MiniMax-M2.5", + "provider": "MiniMaxAI", + "score": 75.8, + "date": "2026-02-12" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "provider": "nvidia", - "score": 83.73, - "date": "2026-03-10" + "model_id": "ornith-ai/Ornith-1.0-35B", + "short_name": "Ornith-1.0-35B", + "provider": "ornith-ai", + "score": 75.6, + "date": "2026-06-21" }, { - "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "provider": "RedHatAI", - "score": 83.73, - "date": "2026-03-26" + "model_id": "mindlab-research/Macaron-V1-Tall", + "short_name": "Macaron-V1-Tall", + "provider": "mindlab-research", + "score": 75.4, + "date": "2026-07-22" }, { - "model_id": "internlm/Intern-S1", - "short_name": "Intern-S1", - "provider": "internlm", - "score": 83.5, - "date": "2025-07-24" + "model_id": "Multilingual-Multimodal-NLP/IndustrialCoder", + "short_name": "IndustrialCoder", + "provider": "Multilingual-Multimodal-NLP", + "score": 74.8, + "date": "2026-03-13" }, { - "model_id": "LGAI-EXAONE/EXAONE-4.5-33B", - "short_name": "EXAONE-4.5-33B", - "provider": "LGAI-EXAONE", - "score": 83.3, - "date": "2026-04-04" + "model_id": "poolside/Laguna-M.1", + "short_name": "Laguna-M.1", + "provider": "poolside", + "score": 74.6, + "date": "2026-06-15" }, { - "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", - "short_name": "Qwen3-235B-A22B-Instruct-2507", - "provider": "Qwen", - "score": 83.0, - "date": "2025-07-21" + "model_id": "stepfun-ai/Step-3.5-Flash", + "short_name": "Step-3.5-Flash", + "provider": "stepfun-ai", + "score": 74.4, + "date": "2026-02-01" }, { - "model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct", - "short_name": "Seed-OSS-36B-Instruct", - "provider": "ByteDance-Seed", - "score": 82.7, - "date": "2025-08-20" + "model_id": "tencent/Hy3-preview", + "short_name": "Hy3-preview", + "provider": "tencent", + "score": 74.4, + "date": "2026-04-13" }, { - "model_id": "meituan-longcat/LongCat-Flash-Chat", - "short_name": "LongCat-Flash-Chat", - "provider": "meituan-longcat", - "score": 82.7, - "date": "2025-08-29" + "model_id": "MiniMaxAI/MiniMax-M2.1", + "short_name": "MiniMax-M2.1", + "provider": "MiniMaxAI", + "score": 74.0, + "date": "2025-12-20" }, { - "model_id": "MiniMaxAI/MiniMax-M2", - "short_name": "MiniMax-M2", - "provider": "MiniMaxAI", - "score": 82.0, - "date": "2025-10-22" + "model_id": "inclusionAI/Ring-2.6-1T", + "short_name": "Ring-2.6-1T", + "provider": "inclusionAI", + "score": 74.0, + "date": "2026-05-14" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", - "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", - "provider": "nvidia", - "score": 81.94, - "date": "2026-08-01" + "model_id": "zai-org/GLM-4.7", + "short_name": "GLM-4.7", + "provider": "zai-org", + "score": 73.8, + "date": "2025-12-22" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", - "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", - "provider": "nvidia", - "score": 81.62, - "date": "2026-08-04" + "model_id": "Qwen/Qwen3.6-35B-A3B", + "short_name": "Qwen3.6-35B-A3B", + "provider": "Qwen", + "score": 73.4, + "date": "2026-04-15" }, { - "model_id": "skt/A.X-K1", - "short_name": "A.X-K1", - "provider": "skt", - "score": 81.5, - "date": "2025-12-29" + "model_id": "Qwen/Qwen3.5-27B", + "short_name": "Qwen3.5-27B", + "provider": "Qwen", + "score": 72.4, + "date": "2026-02-24" }, { - "model_id": "zai-org/GLM-4.5-Air", - "short_name": "GLM-4.5-Air", - "provider": "zai-org", - "score": 81.4, - "date": "2025-07-20" + "model_id": "inclusionAI/Ling-2.6-1T", + "short_name": "Ling-2.6-1T", + "provider": "inclusionAI", + "score": 72.2, + "date": "2026-04-29" }, { - "model_id": "deepseek-ai/DeepSeek-V3-0324", - "short_name": "DeepSeek-V3-0324", - "provider": "deepseek-ai", - "score": 81.2, - "date": "2025-03-24" + "model_id": "Qwen/Qwen3.5-122B-A10B", + "short_name": "Qwen3.5-122B-A10B", + "provider": "Qwen", + "score": 72.0, + "date": "2026-02-24" }, { - "model_id": "MiniMaxAI/MiniMax-M1-40k", - "short_name": "MiniMax-M1-40k", - "provider": "MiniMaxAI", - "score": 81.1, - "date": "2025-06-05" + "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "provider": "nvidia", + "score": 71.9, + "date": "2026-06-03" }, { - "model_id": "jdopensource/JoyAI-LLM-Flash", - "short_name": "JoyAI-LLM-Flash", - "provider": "jdopensource", - "score": 81.02, - "date": "2026-02-14" + "model_id": "moonshotai/Kimi-K2-Thinking", + "short_name": "Kimi-K2-Thinking", + "provider": "moonshotai", + "score": 71.3, + "date": "2025-11-04" }, { - "model_id": "moonshotai/Kimi-K2-Instruct", - "short_name": "Kimi-K2-Instruct", + "model_id": "poolside/Laguna-XS-2.1", + "short_name": "Laguna-XS-2.1", + "provider": "poolside", + "score": 70.9, + "date": "2026-06-20" + }, + { + "model_id": "moonshotai/Kimi-K2.5", + "short_name": "Kimi-K2.5", "provider": "moonshotai", - "score": 81.0, - "date": "2025-07-11" + "score": 70.8, + "date": "2026-01-01" }, { - "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", - "short_name": "Qwen3-30B-A3B-Thinking-2507", + "model_id": "Qwen/Qwen3-Coder-Next", + "short_name": "Qwen3-Coder-Next", "provider": "Qwen", - "score": 80.9, - "date": "2025-07-29" + "score": 70.6, + "date": "2026-01-30" }, { - "model_id": "openai/gpt-oss-120b", - "short_name": "gpt-oss-120b", - "provider": "openai", - "score": 80.8, - "date": "2025-08-04" + "model_id": "ornith-ai/Ornith-1.5-9B", + "short_name": "Ornith-1.5-9B", + "provider": "ornith-ai", + "score": 70.6, + "date": "2026-08-18" }, { - "model_id": "MiniMaxAI/MiniMax-M2.5", - "short_name": "MiniMax-M2.5", - "provider": "MiniMaxAI", - "score": 80.1, - "date": "2026-02-12" + "model_id": "upstage/Solar-Open2-250B", + "short_name": "Solar-Open2-250B", + "provider": "upstage", + "score": 70.4, + "date": "2026-07-22" }, { - "model_id": "baidu/ERNIE-4.5-300B-A47B-PT", - "short_name": "ERNIE-4.5-300B-A47B-PT", - "provider": "baidu", - "score": 78.4, - "date": "2025-06-28" + "model_id": "poolside/Laguna-XS.2", + "short_name": "Laguna-XS.2", + "provider": "poolside", + "score": 69.9, + "date": "2026-04-23" }, { - "model_id": "meituan-longcat/LongCat-Flash-Lite", - "short_name": "LongCat-Flash-Lite", - "provider": "meituan-longcat", - "score": 78.29, - "date": "2026-01-27" + "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", + "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", + "provider": "nvidia", + "score": 69.7, + "date": "2026-06-03" }, { - "model_id": "MiniMaxAI/MiniMax-Text-01", - "short_name": "MiniMax-Text-01", + "model_id": "MiniMaxAI/MiniMax-M2", + "short_name": "MiniMax-M2", "provider": "MiniMaxAI", - "score": 75.7, - "date": "2025-01-12" + "score": 69.4, + "date": "2025-10-22" }, { - "model_id": "openai/gpt-oss-20b", - "short_name": "gpt-oss-20b", - "provider": "openai", - "score": 73.6, - "date": "2025-08-04" + "model_id": "ornith-ai/Ornith-1.0-9B", + "short_name": "Ornith-1.0-9B", + "provider": "ornith-ai", + "score": 69.4, + "date": "2026-06-21" }, { - "model_id": "Qwen/Qwen2.5-72B", - "short_name": "Qwen2.5-72B", - "provider": "Qwen", - "score": 71.59, - "date": "2024-09-15" + "model_id": "MuVeraAI/Laguna-XS.2", + "short_name": "Laguna-XS.2", + "provider": "MuVeraAI", + "score": 68.2, + "date": "2026-04-28" }, { - "model_id": "microsoft/phi-4", - "short_name": "phi-4", - "provider": "microsoft", - "score": 70.4, - "date": "2024-12-11" + "model_id": "CohereLabs/North-Mini-Code-1.0", + "short_name": "North-Mini-Code-1.0", + "provider": "CohereLabs", + "score": 67.6, + "date": "2026-06-05" }, { - "model_id": "Qwen/Qwen3-4B-Instruct-2507", - "short_name": "Qwen3-4B-Instruct-2507", - "provider": "Qwen", - "score": 69.6, - "date": "2025-08-05" + "model_id": "internlm/Intern-S2-Preview", + "short_name": "Intern-S2-Preview", + "provider": "internlm", + "score": 64.0, + "date": "2026-05-15" }, { - "model_id": "baidu/ERNIE-4.5-300B-A47B-Base-PT", - "short_name": "ERNIE-4.5-300B-A47B-Base-PT", - "provider": "baidu", - "score": 69.5, - "date": "2025-06-28" + "model_id": "openpangu/openPangu-2.0-Flash", + "short_name": "openPangu-2.0-Flash", + "provider": "openpangu", + "score": 63.1, + "date": "2026-06-30" }, { - "model_id": "Qwen/Qwen2.5-32B", - "short_name": "Qwen2.5-32B", - "provider": "Qwen", - "score": 69.23, - "date": "2024-09-15" + "model_id": "openai/gpt-oss-120b", + "short_name": "gpt-oss-120b", + "provider": "openai", + "score": 62.4, + "date": "2025-08-04" }, { - "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", - "short_name": "MiMo-V2.5-Pro", - "provider": "XiaomiMiMo", - "score": 68.5, - "date": "2026-04-27" + "model_id": "inclusionAI/Ling-2.6-flash", + "short_name": "Ling-2.6-flash", + "provider": "inclusionAI", + "score": 61.2, + "date": "2026-04-28" }, { - "model_id": "Qwen/Qwen3-235B-A22B", - "short_name": "Qwen3-235B-A22B", - "provider": "Qwen", - "score": 68.18, - "date": "2025-04-27" + "model_id": "openai/gpt-oss-20b", + "short_name": "gpt-oss-20b", + "provider": "openai", + "score": 60.7, + "date": "2025-08-04" }, { - "model_id": "mistralai/Mistral-Large-Instruct-2411", - "short_name": "Mistral-Large-Instruct-2411", - "provider": "mistralai", - "score": 67.94, - "date": "2024-11-14" + "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "provider": "nvidia", + "score": 60.47, + "date": "2026-03-10" }, { - "model_id": "tencent/Hunyuan-A13B-Instruct", - "short_name": "Hunyuan-A13B-Instruct", - "provider": "tencent", - "score": 67.3, - "date": "2025-06-25" + "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "provider": "RedHatAI", + "score": 60.47, + "date": "2026-03-26" }, { - "model_id": "mistralai/Mistral-Large-Instruct-2407", - "short_name": "Mistral-Large-Instruct-2407", - "provider": "mistralai", - "score": 65.91, - "date": "2024-07-24" + "model_id": "zai-org/GLM-4.7-Flash", + "short_name": "GLM-4.7-Flash", + "provider": "zai-org", + "score": 59.2, + "date": "2026-01-19" }, { - "model_id": "deepseek-ai/DeepSeek-V2.5", - "short_name": "DeepSeek-V2.5", - "provider": "deepseek-ai", - "score": 65.83, - "date": "2024-09-05" + "model_id": "facebook/cwm", + "short_name": "cwm", + "provider": "facebook", + "score": 53.9, + "date": "2025-08-25" }, { - "model_id": "ByteDance-Seed/Seed-OSS-36B-Base", - "short_name": "Seed-OSS-36B-Base", - "provider": "ByteDance-Seed", - "score": 65.1, - "date": "2025-08-20" + "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", + "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", + "provider": "nvidia", + "score": 52.8, + "date": "2026-08-04" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", - "short_name": "NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", + "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "provider": "nvidia", - "score": 65.1, - "date": "2025-12-03" + "score": 51.56, + "date": "2026-08-01" + } + ] + }, + "mmluPro": { + "name": "MMLU-Pro", + "dataset": "TIGER-Lab/MMLU-Pro", + "lower_is_better": false, + "models": [ + { + "model_id": "FINAL-Bench/Darwin-180B-RSI", + "short_name": "Darwin-180B-RSI", + "provider": "FINAL-Bench", + "score": 88.12, + "date": "2026-09-28" }, { - "model_id": "deepseek-ai/DeepSeek-V3", - "short_name": "DeepSeek-V3", - "provider": "deepseek-ai", - "score": 64.4, - "date": "2024-12-25" + "model_id": "MiniMaxAI/MiniMax-M2.1", + "short_name": "MiniMax-M2.1", + "provider": "MiniMaxAI", + "score": 88.0, + "date": "2025-12-20" }, { - "model_id": "ibm-granite/granite-4.1-30b", - "short_name": "granite-4.1-30b", - "provider": "ibm-granite", - "score": 64.09, - "date": "2026-04-06" + "model_id": "internlm/Intern-S2-Preview", + "short_name": "Intern-S2-Preview", + "provider": "internlm", + "score": 88.0, + "date": "2026-05-15" }, { - "model_id": "Qwen/Qwen2.5-14B", - "short_name": "Qwen2.5-14B", + "model_id": "Qwen/Qwen3.5-397B-A17B", + "short_name": "Qwen3.5-397B-A17B", "provider": "Qwen", - "score": 63.69, - "date": "2024-09-15" + "score": 87.8, + "date": "2026-02-16" }, { - "model_id": "Qwen/Qwen3-30B-A3B-Base", - "short_name": "Qwen3-30B-A3B-Base", - "provider": "Qwen", - "score": 61.7, - "date": "2025-04-28" + "model_id": "deepseek-ai/DeepSeek-V4-Pro", + "short_name": "DeepSeek-V4-Pro", + "provider": "deepseek-ai", + "score": 87.5, + "date": "2026-04-22" }, { - "model_id": "meta-llama/Llama-3.1-405B", - "short_name": "Llama-3.1-405B", - "provider": "meta-llama", - "score": 61.6, - "date": "2024-07-16" + "model_id": "moonshotai/Kimi-K2.5", + "short_name": "Kimi-K2.5", + "provider": "moonshotai", + "score": 87.1, + "date": "2026-01-01" }, { - "model_id": "nvidia/Nemotron-H-56B-Base-8K", - "short_name": "Nemotron-H-56B-Base-8K", + "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", + "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "provider": "nvidia", - "score": 60.5, - "date": "2025-04-08" + "score": 86.8, + "date": "2026-06-03" }, { - "model_id": "ByteDance-Seed/Seed-OSS-36B-Base-woSyn", - "short_name": "Seed-OSS-36B-Base-woSyn", - "provider": "ByteDance-Seed", - "score": 60.4, - "date": "2025-08-20" + "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", + "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", + "provider": "nvidia", + "score": 86.8, + "date": "2026-06-03" }, { - "model_id": "tencent/Tencent-Hunyuan-Large", - "short_name": "Tencent-Hunyuan-Large", - "provider": "tencent", - "score": 60.2, - "date": "2024-10-22" + "model_id": "Qwen/Qwen3.5-122B-A10B", + "short_name": "Qwen3.5-122B-A10B", + "provider": "Qwen", + "score": 86.7, + "date": "2026-02-24" }, { - "model_id": "JetBrains/Mellum2-12B-A2.5B-Base-Pretrain", - "short_name": "Mellum2-12B-A2.5B-Base-Pretrain", - "provider": "JetBrains", - "score": 59.31, - "date": "2026-04-07" + "model_id": "deepseek-ai/DeepSeek-V4-Flash", + "short_name": "DeepSeek-V4-Flash", + "provider": "deepseek-ai", + "score": 86.4, + "date": "2026-04-22" }, { - "model_id": "JetBrains/Mellum2-12B-A2.5B-Base", - "short_name": "Mellum2-12B-A2.5B-Base", - "provider": "JetBrains", - "score": 59.31, - "date": "2026-05-26" + "model_id": "Qwen/Qwen3.6-27B", + "short_name": "Qwen3.6-27B", + "provider": "Qwen", + "score": 86.2, + "date": "2026-04-21" }, { - "model_id": "LGAI-EXAONE/EXAONE-3.5-32B-Instruct", - "short_name": "EXAONE-3.5-32B-Instruct", - "provider": "LGAI-EXAONE", - "score": 58.91, - "date": "2024-12-01" + "model_id": "upstage/Solar-Open2-250B", + "short_name": "Solar-Open2-250B", + "provider": "upstage", + "score": 86.2, + "date": "2026-07-22" }, { - "model_id": "XiaomiMiMo/MiMo-7B-RL", - "short_name": "MiMo-7B-RL", - "provider": "XiaomiMiMo", - "score": 58.6, - "date": "2025-04-29" + "model_id": "Qwen/Qwen3.5-27B", + "short_name": "Qwen3.5-27B", + "provider": "Qwen", + "score": 86.1, + "date": "2026-02-24" }, { - "model_id": "internlm/internlm3-8b-instruct", - "short_name": "internlm3-8b-instruct", - "provider": "internlm", - "score": 57.6, - "date": "2025-01-13" + "model_id": "zai-org/GLM-5", + "short_name": "GLM-5", + "provider": "zai-org", + "score": 86.0, + "date": "2026-02-11" }, { - "model_id": "baidu/ERNIE-4.5-21B-A3B-Base-PT", - "short_name": "ERNIE-4.5-21B-A3B-Base-PT", - "provider": "baidu", - "score": 56.7, - "date": "2025-06-28" + "model_id": "Qwen/Qwen3.6-35B-A3B", + "short_name": "Qwen3.6-35B-A3B", + "provider": "Qwen", + "score": 85.2, + "date": "2026-04-15" }, { - "model_id": "ibm-granite/granite-4.1-8b", - "short_name": "granite-4.1-8b", - "provider": "ibm-granite", - "score": 55.99, - "date": "2026-04-06" + "model_id": "deepseek-ai/DeepSeek-R1-0528", + "short_name": "DeepSeek-R1-0528", + "provider": "deepseek-ai", + "score": 85.0, + "date": "2025-05-28" }, { - "model_id": "microsoft/Phi-3-medium-4k-instruct", - "short_name": "Phi-3-medium-4k-instruct", - "provider": "microsoft", - "score": 55.7, - "date": "2024-05-07" + "model_id": "zai-org/GLM-4.5", + "short_name": "GLM-4.5", + "provider": "zai-org", + "score": 84.6, + "date": "2025-07-20" }, { - "model_id": "deepseek-ai/DeepSeek-V2-Chat", - "short_name": "DeepSeek-V2-Chat", - "provider": "deepseek-ai", - "score": 54.81, - "date": "2024-04-28" + "model_id": "stepfun-ai/Step-3.5-Flash", + "short_name": "Step-3.5-Flash", + "provider": "stepfun-ai", + "score": 84.4, + "date": "2026-02-01" }, { - "model_id": "mistralai/Mistral-Small-24B-Base-2501", - "short_name": "Mistral-Small-24B-Base-2501", - "provider": "mistralai", - "score": 54.4, - "date": "2025-01-23" + "model_id": "deepseek-ai/DeepSeek-R1", + "short_name": "DeepSeek-R1", + "provider": "deepseek-ai", + "score": 84.0, + "date": "2025-01-20" }, { - "model_id": "microsoft/Phi-4-mini-instruct", - "short_name": "Phi-4-mini-instruct", - "provider": "microsoft", - "score": 52.8, - "date": "2025-02-19" + "model_id": "LGAI-EXAONE/K-EXAONE-236B-A23B", + "short_name": "K-EXAONE-236B-A23B", + "provider": "LGAI-EXAONE", + "score": 83.8, + "date": "2025-12-26" }, { - "model_id": "meta-llama/Meta-Llama-3-70B", - "short_name": "Meta-Llama-3-70B", - "provider": "meta-llama", - "score": 52.78, - "date": "2024-04-17" + "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "provider": "nvidia", + "score": 83.73, + "date": "2026-03-10" }, { - "model_id": "meta-llama/Llama-3.1-70B", - "short_name": "Llama-3.1-70B", - "provider": "meta-llama", - "score": 52.47, - "date": "2024-07-14" + "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", + "provider": "RedHatAI", + "score": 83.73, + "date": "2026-03-26" }, { - "model_id": "01-ai/Yi-1.5-34B-Chat", - "short_name": "Yi-1.5-34B-Chat", - "provider": "01-ai", - "score": 52.29, - "date": "2024-05-10" + "model_id": "internlm/Intern-S1", + "short_name": "Intern-S1", + "provider": "internlm", + "score": 83.5, + "date": "2025-07-24" }, { - "model_id": "microsoft/Phi-3-medium-128k-instruct", - "short_name": "Phi-3-medium-128k-instruct", - "provider": "microsoft", - "score": 51.91, - "date": "2024-05-07" + "model_id": "LGAI-EXAONE/EXAONE-4.5-33B", + "short_name": "EXAONE-4.5-33B", + "provider": "LGAI-EXAONE", + "score": 83.3, + "date": "2026-04-04" }, { - "model_id": "TIGER-Lab/MAmmoTH2-8x7B-Plus", - "short_name": "MAmmoTH2-8x7B-Plus", - "provider": "TIGER-Lab", - "score": 50.4, - "date": "2024-05-06" + "model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507", + "short_name": "Qwen3-235B-A22B-Instruct-2507", + "provider": "Qwen", + "score": 83.0, + "date": "2025-07-21" }, { - "model_id": "Qwen/Qwen1.5-110B", - "short_name": "Qwen1.5-110B", - "provider": "Qwen", - "score": 49.93, - "date": "2024-04-25" + "model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct", + "short_name": "Seed-OSS-36B-Instruct", + "provider": "ByteDance-Seed", + "score": 82.7, + "date": "2025-08-20" }, { - "model_id": "ibm-granite/granite-4.1-3b", - "short_name": "granite-4.1-3b", - "provider": "ibm-granite", - "score": 49.83, - "date": "2026-04-06" + "model_id": "meituan-longcat/LongCat-Flash-Chat", + "short_name": "LongCat-Flash-Chat", + "provider": "meituan-longcat", + "score": 82.7, + "date": "2025-08-29" }, { - "model_id": "ai21labs/AI21-Jamba-Large-1.5", - "short_name": "AI21-Jamba-Large-1.5", - "provider": "ai21labs", - "score": 49.46, - "date": "2024-08-19" + "model_id": "MiniMaxAI/MiniMax-M2", + "short_name": "MiniMax-M2", + "provider": "MiniMaxAI", + "score": 82.0, + "date": "2025-10-22" }, { - "model_id": "mistralai/Mistral-Small-Instruct-2409", - "short_name": "Mistral-Small-Instruct-2409", - "provider": "mistralai", - "score": 48.4, - "date": "2024-09-17" + "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", + "provider": "nvidia", + "score": 81.94, + "date": "2026-08-01" }, { - "model_id": "zai-org/glm-4-9b", - "short_name": "glm-4-9b", - "provider": "zai-org", - "score": 47.92, - "date": "2024-06-04" + "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", + "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", + "provider": "nvidia", + "score": 81.62, + "date": "2026-08-04" }, { - "model_id": "microsoft/Phi-3.5-mini-instruct", - "short_name": "Phi-3.5-mini-instruct", - "provider": "microsoft", - "score": 47.87, - "date": "2024-08-16" + "model_id": "skt/A.X-K1", + "short_name": "A.X-K1", + "provider": "skt", + "score": 81.5, + "date": "2025-12-29" }, { - "model_id": "LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct", - "short_name": "EXAONE-3.5-7.8B-Instruct", - "provider": "LGAI-EXAONE", - "score": 46.24, - "date": "2024-12-01" + "model_id": "zai-org/GLM-4.5-Air", + "short_name": "GLM-4.5-Air", + "provider": "zai-org", + "score": 81.4, + "date": "2025-07-20" }, { - "model_id": "01-ai/Yi-1.5-9B-Chat", - "short_name": "Yi-1.5-9B-Chat", - "provider": "01-ai", - "score": 45.95, - "date": "2024-05-10" + "model_id": "deepseek-ai/DeepSeek-V3-0324", + "short_name": "DeepSeek-V3-0324", + "provider": "deepseek-ai", + "score": 81.2, + "date": "2025-03-24" }, { - "model_id": "microsoft/Phi-3-mini-4k-instruct", - "short_name": "Phi-3-mini-4k-instruct", - "provider": "microsoft", - "score": 45.66, - "date": "2024-04-22" + "model_id": "MiniMaxAI/MiniMax-M1-40k", + "short_name": "MiniMax-M1-40k", + "provider": "MiniMaxAI", + "score": 81.1, + "date": "2025-06-05" }, { - "model_id": "CohereLabs/aya-expanse-32b", - "short_name": "aya-expanse-32b", - "provider": "CohereLabs", - "score": 45.41, - "date": "2024-10-23" + "model_id": "jdopensource/JoyAI-LLM-Flash", + "short_name": "JoyAI-LLM-Flash", + "provider": "jdopensource", + "score": 81.02, + "date": "2026-02-14" }, { - "model_id": "google/gemma-2-9b", - "short_name": "gemma-2-9b", - "provider": "google", - "score": 45.1, - "date": "2024-06-24" + "model_id": "moonshotai/Kimi-K2-Instruct", + "short_name": "Kimi-K2-Instruct", + "provider": "moonshotai", + "score": 81.0, + "date": "2025-07-11" }, { - "model_id": "Qwen/Qwen2.5-7B", - "short_name": "Qwen2.5-7B", + "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", + "short_name": "Qwen3-30B-A3B-Thinking-2507", "provider": "Qwen", - "score": 45.0, - "date": "2024-09-15" + "score": 80.9, + "date": "2025-07-29" }, { - "model_id": "microsoft/Phi-3-mini-128k-instruct", - "short_name": "Phi-3-mini-128k-instruct", - "provider": "microsoft", - "score": 43.86, - "date": "2024-04-22" + "model_id": "openai/gpt-oss-120b", + "short_name": "gpt-oss-120b", + "provider": "openai", + "score": 80.8, + "date": "2025-08-04" }, { - "model_id": "Qwen/Qwen2.5-3B", - "short_name": "Qwen2.5-3B", - "provider": "Qwen", - "score": 43.73, - "date": "2024-09-15" + "model_id": "MiniMaxAI/MiniMax-M2.5", + "short_name": "MiniMax-M2.5", + "provider": "MiniMaxAI", + "score": 80.1, + "date": "2026-02-12" }, { - "model_id": "TIGER-Lab/MAmmoTH2-8B-Plus", - "short_name": "MAmmoTH2-8B-Plus", - "provider": "TIGER-Lab", - "score": 43.35, - "date": "2024-05-06" + "model_id": "baidu/ERNIE-4.5-300B-A47B-PT", + "short_name": "ERNIE-4.5-300B-A47B-PT", + "provider": "baidu", + "score": 78.4, + "date": "2025-06-28" }, { - "model_id": "01-ai/Yi-34B", - "short_name": "Yi-34B", - "provider": "01-ai", - "score": 43.03, - "date": "2023-11-01" + "model_id": "meituan-longcat/LongCat-Flash-Lite", + "short_name": "LongCat-Flash-Lite", + "provider": "meituan-longcat", + "score": 78.29, + "date": "2026-01-27" }, { - "model_id": "mistralai/Mathstral-7B-v0.1", - "short_name": "Mathstral-7B-v0.1", - "provider": "mistralai", - "score": 42.0, - "date": "2024-07-16" + "model_id": "MiniMaxAI/MiniMax-Text-01", + "short_name": "MiniMax-Text-01", + "provider": "MiniMaxAI", + "score": 75.7, + "date": "2025-01-12" }, { - "model_id": "XiaomiMiMo/MiMo-7B-Base", - "short_name": "MiMo-7B-Base", - "provider": "XiaomiMiMo", - "score": 41.9, - "date": "2025-04-29" + "model_id": "openai/gpt-oss-20b", + "short_name": "gpt-oss-20b", + "provider": "openai", + "score": 73.6, + "date": "2025-08-04" }, { - "model_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", - "short_name": "DeepSeek-Coder-V2-Lite-Instruct", - "provider": "deepseek-ai", - "score": 41.57, - "date": "2024-06-14" + "model_id": "Qwen/Qwen2.5-72B", + "short_name": "Qwen2.5-72B", + "provider": "Qwen", + "score": 71.59, + "date": "2024-09-15" }, { - "model_id": "mistralai/Mixtral-8x7B-v0.1", - "short_name": "Mixtral-8x7B-v0.1", - "provider": "mistralai", - "score": 41.03, - "date": "2023-12-01" + "model_id": "microsoft/phi-4", + "short_name": "phi-4", + "provider": "microsoft", + "score": 70.4, + "date": "2024-12-11" }, { - "model_id": "meta-llama/Meta-Llama-3-8B-Instruct", - "short_name": "Meta-Llama-3-8B-Instruct", - "provider": "meta-llama", - "score": 40.98, - "date": "2024-04-17" + "model_id": "Qwen/Qwen3-4B-Instruct-2507", + "short_name": "Qwen3-4B-Instruct-2507", + "provider": "Qwen", + "score": 69.6, + "date": "2025-08-05" }, { - "model_id": "TIGER-Lab/MAmmoTH2-7B-Plus", - "short_name": "MAmmoTH2-7B-Plus", - "provider": "TIGER-Lab", - "score": 40.85, - "date": "2024-05-06" + "model_id": "baidu/ERNIE-4.5-300B-A47B-Base-PT", + "short_name": "ERNIE-4.5-300B-A47B-Base-PT", + "provider": "baidu", + "score": 69.5, + "date": "2025-06-28" }, { - "model_id": "Qwen/Qwen2-7B", - "short_name": "Qwen2-7B", + "model_id": "Qwen/Qwen2.5-32B", + "short_name": "Qwen2.5-32B", "provider": "Qwen", - "score": 40.73, - "date": "2024-06-04" + "score": 69.23, + "date": "2024-09-15" }, { - "model_id": "mistralai/Mistral-Nemo-Base-2407", - "short_name": "Mistral-Nemo-Base-2407", - "provider": "mistralai", - "score": 39.77, - "date": "2024-07-18" - }, - { - "model_id": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct", - "short_name": "EXAONE-3.5-2.4B-Instruct", - "provider": "LGAI-EXAONE", - "score": 39.1, - "date": "2024-12-01" - }, - { - "model_id": "01-ai/Yi-1.5-6B-Chat", - "short_name": "Yi-1.5-6B-Chat", - "provider": "01-ai", - "score": 38.23, - "date": "2024-05-11" + "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", + "short_name": "MiMo-V2.5-Pro", + "provider": "XiaomiMiMo", + "score": 68.5, + "date": "2026-04-27" }, { - "model_id": "Qwen/Qwen1.5-14B-Chat", - "short_name": "Qwen1.5-14B-Chat", + "model_id": "Qwen/Qwen3-235B-A22B", + "short_name": "Qwen3-235B-A22B", "provider": "Qwen", - "score": 38.02, - "date": "2024-01-30" + "score": 68.18, + "date": "2025-04-27" }, { - "model_id": "mistralai/Ministral-8B-Instruct-2410", - "short_name": "Ministral-8B-Instruct-2410", + "model_id": "mistralai/Mistral-Large-Instruct-2411", + "short_name": "Mistral-Large-Instruct-2411", "provider": "mistralai", - "score": 37.93, - "date": "2024-10-15" - }, - { - "model_id": "CohereLabs/c4ai-command-r-v01", - "short_name": "c4ai-command-r-v01", - "provider": "CohereLabs", - "score": 37.9, - "date": "2024-03-11" - }, - { - "model_id": "internlm/internlm2-math-plus-20b", - "short_name": "internlm2-math-plus-20b", - "provider": "internlm", - "score": 37.1, - "date": "2024-05-24" - }, - { - "model_id": "GSAI-ML/LLaDA-8B-Instruct", - "short_name": "LLaDA-8B-Instruct", - "provider": "GSAI-ML", - "score": 37.0, - "date": "2025-02-19" - }, - { - "model_id": "abacusai/Llama-3-Smaug-8B", - "short_name": "Llama-3-Smaug-8B", - "provider": "abacusai", - "score": 36.93, - "date": "2024-04-19" + "score": 67.94, + "date": "2024-11-14" }, { - "model_id": "meta-llama/Llama-3.1-8B", - "short_name": "Llama-3.1-8B", - "provider": "meta-llama", - "score": 36.6, - "date": "2024-07-14" + "model_id": "tencent/Hunyuan-A13B-Instruct", + "short_name": "Hunyuan-A13B-Instruct", + "provider": "tencent", + "score": 67.3, + "date": "2025-06-25" }, { - "model_id": "meta-llama/Meta-Llama-3-8B", - "short_name": "Meta-Llama-3-8B", - "provider": "meta-llama", - "score": 35.36, - "date": "2024-04-17" + "model_id": "mistralai/Mistral-Large-Instruct-2407", + "short_name": "Mistral-Large-Instruct-2407", + "provider": "mistralai", + "score": 65.91, + "date": "2024-07-24" }, { - "model_id": "deepseek-ai/deepseek-math-7b-instruct", - "short_name": "deepseek-math-7b-instruct", + "model_id": "deepseek-ai/DeepSeek-V2.5", + "short_name": "DeepSeek-V2.5", "provider": "deepseek-ai", - "score": 35.3, - "date": "2024-02-05" + "score": 65.83, + "date": "2024-09-05" }, { - "model_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Base", - "short_name": "DeepSeek-Coder-V2-Lite-Base", - "provider": "deepseek-ai", - "score": 34.37, - "date": "2024-06-14" + "model_id": "ByteDance-Seed/Seed-OSS-36B-Base", + "short_name": "Seed-OSS-36B-Base", + "provider": "ByteDance-Seed", + "score": 65.1, + "date": "2025-08-20" }, { - "model_id": "CohereLabs/aya-expanse-8b", - "short_name": "aya-expanse-8b", - "provider": "CohereLabs", - "score": 33.74, - "date": "2024-10-23" + "model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", + "short_name": "NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", + "provider": "nvidia", + "score": 65.1, + "date": "2025-12-03" }, { - "model_id": "internlm/internlm2-math-plus-7b", - "short_name": "internlm2-math-plus-7b", - "provider": "internlm", - "score": 33.5, - "date": "2024-05-24" + "model_id": "deepseek-ai/DeepSeek-V3", + "short_name": "DeepSeek-V3", + "provider": "deepseek-ai", + "score": 64.4, + "date": "2024-12-25" }, { - "model_id": "ibm-granite/granite-3.1-8b-base", - "short_name": "granite-3.1-8b-base", + "model_id": "ibm-granite/granite-4.1-30b", + "short_name": "granite-4.1-30b", "provider": "ibm-granite", - "score": 33.08, - "date": "2024-12-06" + "score": 64.09, + "date": "2026-04-06" }, { - "model_id": "Qwen/Qwen2.5-1.5B", - "short_name": "Qwen2.5-1.5B", + "model_id": "Qwen/Qwen2.5-14B", + "short_name": "Qwen2.5-14B", "provider": "Qwen", - "score": 32.1, + "score": 63.69, "date": "2024-09-15" }, { - "model_id": "ibm-granite/granite-3.0-8b-base", - "short_name": "granite-3.0-8b-base", - "provider": "ibm-granite", - "score": 31.03, - "date": "2024-10-02" + "model_id": "Qwen/Qwen3-30B-A3B-Base", + "short_name": "Qwen3-30B-A3B-Base", + "provider": "Qwen", + "score": 61.7, + "date": "2025-04-28" }, { - "model_id": "mistralai/Mistral-7B-Instruct-v0.2", - "short_name": "Mistral-7B-Instruct-v0.2", - "provider": "mistralai", - "score": 30.84, - "date": "2023-12-11" + "model_id": "meta-llama/Llama-3.1-405B", + "short_name": "Llama-3.1-405B", + "provider": "meta-llama", + "score": 61.6, + "date": "2024-07-16" }, { - "model_id": "mistral-community/Mistral-7B-v0.2", - "short_name": "Mistral-7B-v0.2", - "provider": "mistral-community", - "score": 30.43, - "date": "2024-03-23" + "model_id": "nvidia/Nemotron-H-56B-Base-8K", + "short_name": "Nemotron-H-56B-Base-8K", + "provider": "nvidia", + "score": 60.5, + "date": "2025-04-08" }, { - "model_id": "Qwen/Qwen1.5-7B-Chat", - "short_name": "Qwen1.5-7B-Chat", - "provider": "Qwen", - "score": 29.06, - "date": "2024-01-30" + "model_id": "ByteDance-Seed/Seed-OSS-36B-Base-woSyn", + "short_name": "Seed-OSS-36B-Base-woSyn", + "provider": "ByteDance-Seed", + "score": 60.4, + "date": "2025-08-20" }, { - "model_id": "01-ai/Yi-6B-Chat", - "short_name": "Yi-6B-Chat", - "provider": "01-ai", - "score": 28.84, - "date": "2023-11-22" + "model_id": "tencent/Tencent-Hunyuan-Large", + "short_name": "Tencent-Hunyuan-Large", + "provider": "tencent", + "score": 60.2, + "date": "2024-10-22" }, { - "model_id": "01-ai/Yi-6B", - "short_name": "Yi-6B", - "provider": "01-ai", - "score": 26.51, - "date": "2023-11-01" + "model_id": "JetBrains/Mellum2-12B-A2.5B-Base-Pretrain", + "short_name": "Mellum2-12B-A2.5B-Base-Pretrain", + "provider": "JetBrains", + "score": 59.31, + "date": "2026-04-07" }, { - "model_id": "ibm-granite/granite-3.1-2b-base", - "short_name": "granite-3.1-2b-base", - "provider": "ibm-granite", - "score": 23.89, - "date": "2024-12-06" + "model_id": "JetBrains/Mellum2-12B-A2.5B-Base", + "short_name": "Mellum2-12B-A2.5B-Base", + "provider": "JetBrains", + "score": 59.31, + "date": "2026-05-26" }, { - "model_id": "EleutherAI/llemma_7b", - "short_name": "llemma_7b", - "provider": "EleutherAI", - "score": 23.45, - "date": "2023-09-12" + "model_id": "LGAI-EXAONE/EXAONE-3.5-32B-Instruct", + "short_name": "EXAONE-3.5-32B-Instruct", + "provider": "LGAI-EXAONE", + "score": 58.91, + "date": "2024-12-01" }, { - "model_id": "Qwen/Qwen2-1.5B-Instruct", - "short_name": "Qwen2-1.5B-Instruct", - "provider": "Qwen", - "score": 22.62, - "date": "2024-06-03" + "model_id": "XiaomiMiMo/MiMo-7B-RL", + "short_name": "MiMo-7B-RL", + "provider": "XiaomiMiMo", + "score": 58.6, + "date": "2025-04-29" }, { - "model_id": "Qwen/Qwen2-1.5B", - "short_name": "Qwen2-1.5B", - "provider": "Qwen", - "score": 22.56, - "date": "2024-05-31" + "model_id": "internlm/internlm3-8b-instruct", + "short_name": "internlm3-8b-instruct", + "provider": "internlm", + "score": 57.6, + "date": "2025-01-13" }, { - "model_id": "meta-llama/Llama-3.2-3B", - "short_name": "Llama-3.2-3B", - "provider": "meta-llama", - "score": 22.17, - "date": "2024-09-18" + "model_id": "baidu/ERNIE-4.5-21B-A3B-Base-PT", + "short_name": "ERNIE-4.5-21B-A3B-Base-PT", + "provider": "baidu", + "score": 56.7, + "date": "2025-06-28" }, { - "model_id": "ibm-granite/granite-3.0-2b-base", - "short_name": "granite-3.0-2b-base", + "model_id": "ibm-granite/granite-4.1-8b", + "short_name": "granite-4.1-8b", "provider": "ibm-granite", - "score": 21.72, - "date": "2024-10-02" + "score": 55.99, + "date": "2026-04-06" }, { - "model_id": "ibm-granite/granite-3.1-3b-a800m-base", - "short_name": "granite-3.1-3b-a800m-base", - "provider": "ibm-granite", - "score": 20.39, - "date": "2024-12-06" + "model_id": "microsoft/Phi-3-medium-4k-instruct", + "short_name": "Phi-3-medium-4k-instruct", + "provider": "microsoft", + "score": 55.7, + "date": "2024-05-07" }, { - "model_id": "HuggingFaceTB/SmolLM2-1.7B", - "short_name": "SmolLM2-1.7B", - "provider": "HuggingFaceTB", - "score": 18.31, - "date": "2024-10-30" + "model_id": "deepseek-ai/DeepSeek-V2-Chat", + "short_name": "DeepSeek-V2-Chat", + "provider": "deepseek-ai", + "score": 54.81, + "date": "2024-04-28" }, { - "model_id": "Qwen/Qwen2-0.5B", - "short_name": "Qwen2-0.5B", - "provider": "Qwen", - "score": 14.97, - "date": "2024-05-31" + "model_id": "mistralai/Mistral-Small-24B-Base-2501", + "short_name": "Mistral-Small-24B-Base-2501", + "provider": "mistralai", + "score": 54.4, + "date": "2025-01-23" }, { - "model_id": "Qwen/Qwen2.5-0.5B", - "short_name": "Qwen2.5-0.5B", - "provider": "Qwen", - "score": 14.92, - "date": "2024-09-15" + "model_id": "microsoft/Phi-4-mini-instruct", + "short_name": "Phi-4-mini-instruct", + "provider": "microsoft", + "score": 52.8, + "date": "2025-02-19" }, { - "model_id": "ibm-granite/granite-3.1-1b-a400m-base", - "short_name": "granite-3.1-1b-a400m-base", - "provider": "ibm-granite", - "score": 12.34, - "date": "2024-12-06" + "model_id": "meta-llama/Meta-Llama-3-70B", + "short_name": "Meta-Llama-3-70B", + "provider": "meta-llama", + "score": 52.78, + "date": "2024-04-17" }, { - "model_id": "meta-llama/Llama-3.2-1B", - "short_name": "Llama-3.2-1B", + "model_id": "meta-llama/Llama-3.1-70B", + "short_name": "Llama-3.1-70B", "provider": "meta-llama", - "score": 11.95, - "date": "2024-09-18" + "score": 52.47, + "date": "2024-07-14" }, { - "model_id": "HuggingFaceTB/SmolLM2-360M", - "short_name": "SmolLM2-360M", - "provider": "HuggingFaceTB", - "score": 11.38, - "date": "2024-10-31" + "model_id": "01-ai/Yi-1.5-34B-Chat", + "short_name": "Yi-1.5-34B-Chat", + "provider": "01-ai", + "score": 52.29, + "date": "2024-05-10" }, { - "model_id": "HuggingFaceTB/SmolLM2-135M", - "short_name": "SmolLM2-135M", - "provider": "HuggingFaceTB", - "score": 10.85, - "date": "2024-10-31" + "model_id": "microsoft/Phi-3-medium-128k-instruct", + "short_name": "Phi-3-medium-128k-instruct", + "provider": "microsoft", + "score": 51.91, + "date": "2024-05-07" }, { - "model_id": "Qwen/Qwen2.5-VL-72B-Instruct", - "short_name": "Qwen2.5-VL-72B-Instruct", + "model_id": "TIGER-Lab/MAmmoTH2-8x7B-Plus", + "short_name": "MAmmoTH2-8x7B-Plus", + "provider": "TIGER-Lab", + "score": 50.4, + "date": "2024-05-06" + }, + { + "model_id": "Qwen/Qwen1.5-110B", + "short_name": "Qwen1.5-110B", "provider": "Qwen", - "score": 0.65, - "date": "2025-01-27" - } - ] - }, - "sweVerified": { - "name": "SWE-bench Verified", - "dataset": "SWE-bench/SWE-bench_Verified", - "lower_is_better": false, - "models": [ + "score": 49.93, + "date": "2024-04-25" + }, { - "model_id": "ornith-ai/Ornith-1.5-397B", - "short_name": "Ornith-1.5-397B", - "provider": "ornith-ai", - "score": 86.0, - "date": "2026-08-18" + "model_id": "ibm-granite/granite-4.1-3b", + "short_name": "granite-4.1-3b", + "provider": "ibm-granite", + "score": 49.83, + "date": "2026-04-06" }, { - "model_id": "mindlab-research/Macaron-V1-Venti", - "short_name": "Macaron-V1-Venti", - "provider": "mindlab-research", - "score": 85.6, - "date": "2026-07-20" + "model_id": "ai21labs/AI21-Jamba-Large-1.5", + "short_name": "AI21-Jamba-Large-1.5", + "provider": "ai21labs", + "score": 49.46, + "date": "2024-08-19" }, { - "model_id": "mindlab-research/Macaron-V1-Coding-Venti", - "short_name": "Macaron-V1-Coding-Venti", - "provider": "mindlab-research", - "score": 85.6, - "date": "2026-07-20" + "model_id": "mistralai/Mistral-Small-Instruct-2409", + "short_name": "Mistral-Small-Instruct-2409", + "provider": "mistralai", + "score": 48.4, + "date": "2024-09-17" }, { - "model_id": "ornith-ai/Ornith-1.0-397B", - "short_name": "Ornith-1.0-397B", - "provider": "ornith-ai", - "score": 82.4, - "date": "2026-06-23" + "model_id": "zai-org/glm-4-9b", + "short_name": "glm-4-9b", + "provider": "zai-org", + "score": 47.92, + "date": "2024-06-04" }, { - "model_id": "deepseek-ai/DeepSeek-V4-Pro", - "short_name": "DeepSeek-V4-Pro", - "provider": "deepseek-ai", - "score": 80.6, - "date": "2026-04-22" + "model_id": "microsoft/Phi-3.5-mini-instruct", + "short_name": "Phi-3.5-mini-instruct", + "provider": "microsoft", + "score": 47.87, + "date": "2024-08-16" }, { - "model_id": "MiniMaxAI/MiniMax-M3", - "short_name": "MiniMax-M3", - "provider": "MiniMaxAI", - "score": 80.5, - "date": "2026-06-02" + "model_id": "LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct", + "short_name": "EXAONE-3.5-7.8B-Instruct", + "provider": "LGAI-EXAONE", + "score": 46.24, + "date": "2024-12-01" }, { - "model_id": "moonshotai/Kimi-K2.6", - "short_name": "Kimi-K2.6", - "provider": "moonshotai", - "score": 80.2, - "date": "2026-04-14" + "model_id": "01-ai/Yi-1.5-9B-Chat", + "short_name": "Yi-1.5-9B-Chat", + "provider": "01-ai", + "score": 45.95, + "date": "2024-05-10" }, { - "model_id": "thinkingmachines/Inkling-Small", - "short_name": "Inkling-Small", - "provider": "thinkingmachines", - "score": 80.2, - "date": "2026-07-27" + "model_id": "microsoft/Phi-3-mini-4k-instruct", + "short_name": "Phi-3-mini-4k-instruct", + "provider": "microsoft", + "score": 45.66, + "date": "2024-04-22" }, { - "model_id": "deepseek-ai/DeepSeek-V4-Flash", - "short_name": "DeepSeek-V4-Flash", - "provider": "deepseek-ai", - "score": 79.0, - "date": "2026-04-22" + "model_id": "CohereLabs/aya-expanse-32b", + "short_name": "aya-expanse-32b", + "provider": "CohereLabs", + "score": 45.41, + "date": "2024-10-23" }, { - "model_id": "ornith-ai/Ornith-1.5-35B-A3B", - "short_name": "Ornith-1.5-35B-A3B", - "provider": "ornith-ai", - "score": 79.0, - "date": "2026-08-18" + "model_id": "google/gemma-2-9b", + "short_name": "gemma-2-9b", + "provider": "google", + "score": 45.1, + "date": "2024-06-24" }, { - "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", - "short_name": "MiMo-V2.5-Pro", - "provider": "XiaomiMiMo", - "score": 78.9, - "date": "2026-04-27" + "model_id": "Qwen/Qwen2.5-7B", + "short_name": "Qwen2.5-7B", + "provider": "Qwen", + "score": 45.0, + "date": "2024-09-15" }, { - "model_id": "dots-studio/dots3-note-prev", - "short_name": "dots3-note-prev", - "provider": "dots-studio", - "score": 78.4, - "date": "2026-08-09" + "model_id": "microsoft/Phi-3-mini-128k-instruct", + "short_name": "Phi-3-mini-128k-instruct", + "provider": "microsoft", + "score": 43.86, + "date": "2024-04-22" }, { - "model_id": "tencent/Hy3", - "short_name": "Hy3", - "provider": "tencent", - "score": 78.0, - "date": "2026-07-02" + "model_id": "Qwen/Qwen2.5-3B", + "short_name": "Qwen2.5-3B", + "provider": "Qwen", + "score": 43.73, + "date": "2024-09-15" }, { - "model_id": "zai-org/GLM-5", - "short_name": "GLM-5", - "provider": "zai-org", - "score": 77.8, - "date": "2026-02-11" + "model_id": "TIGER-Lab/MAmmoTH2-8B-Plus", + "short_name": "MAmmoTH2-8B-Plus", + "provider": "TIGER-Lab", + "score": 43.35, + "date": "2024-05-06" }, { - "model_id": "mistralai/Mistral-Medium-3.5-128B", - "short_name": "Mistral-Medium-3.5-128B", + "model_id": "01-ai/Yi-34B", + "short_name": "Yi-34B", + "provider": "01-ai", + "score": 43.03, + "date": "2023-11-01" + }, + { + "model_id": "mistralai/Mathstral-7B-v0.1", + "short_name": "Mathstral-7B-v0.1", "provider": "mistralai", - "score": 77.6, - "date": "2026-03-31" + "score": 42.0, + "date": "2024-07-16" }, { - "model_id": "thinkingmachines/Inkling", - "short_name": "Inkling", - "provider": "thinkingmachines", - "score": 77.6, - "date": "2026-07-14" + "model_id": "XiaomiMiMo/MiMo-7B-Base", + "short_name": "MiMo-7B-Base", + "provider": "XiaomiMiMo", + "score": 41.9, + "date": "2025-04-29" }, { - "model_id": "Qwen/Qwen3.6-27B", - "short_name": "Qwen3.6-27B", - "provider": "Qwen", - "score": 77.2, - "date": "2026-04-21" + "model_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct", + "short_name": "DeepSeek-Coder-V2-Lite-Instruct", + "provider": "deepseek-ai", + "score": 41.57, + "date": "2024-06-14" }, { - "model_id": "Qwen/Qwen3.5-397B-A17B", - "short_name": "Qwen3.5-397B-A17B", - "provider": "Qwen", - "score": 76.4, - "date": "2026-02-16" + "model_id": "mistralai/Mixtral-8x7B-v0.1", + "short_name": "Mixtral-8x7B-v0.1", + "provider": "mistralai", + "score": 41.03, + "date": "2023-12-01" }, { - "model_id": "meta-models/Muse-Glimmer-30B", - "short_name": "Muse-Glimmer-30B", - "provider": "meta-models", - "score": 76.0, - "date": "2026-08-09" + "model_id": "meta-llama/Meta-Llama-3-8B-Instruct", + "short_name": "Meta-Llama-3-8B-Instruct", + "provider": "meta-llama", + "score": 40.98, + "date": "2024-04-17" }, { - "model_id": "MiniMaxAI/MiniMax-M2.5", - "short_name": "MiniMax-M2.5", - "provider": "MiniMaxAI", - "score": 75.8, - "date": "2026-02-12" + "model_id": "TIGER-Lab/MAmmoTH2-7B-Plus", + "short_name": "MAmmoTH2-7B-Plus", + "provider": "TIGER-Lab", + "score": 40.85, + "date": "2024-05-06" }, { - "model_id": "ornith-ai/Ornith-1.0-35B", - "short_name": "Ornith-1.0-35B", - "provider": "ornith-ai", - "score": 75.6, - "date": "2026-06-21" + "model_id": "Qwen/Qwen2-7B", + "short_name": "Qwen2-7B", + "provider": "Qwen", + "score": 40.73, + "date": "2024-06-04" }, { - "model_id": "mindlab-research/Macaron-V1-Tall", - "short_name": "Macaron-V1-Tall", - "provider": "mindlab-research", - "score": 75.4, - "date": "2026-07-22" + "model_id": "mistralai/Mistral-Nemo-Base-2407", + "short_name": "Mistral-Nemo-Base-2407", + "provider": "mistralai", + "score": 39.77, + "date": "2024-07-18" }, { - "model_id": "Multilingual-Multimodal-NLP/IndustrialCoder", - "short_name": "IndustrialCoder", - "provider": "Multilingual-Multimodal-NLP", - "score": 74.8, - "date": "2026-03-13" + "model_id": "LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct", + "short_name": "EXAONE-3.5-2.4B-Instruct", + "provider": "LGAI-EXAONE", + "score": 39.1, + "date": "2024-12-01" }, { - "model_id": "poolside/Laguna-M.1", - "short_name": "Laguna-M.1", - "provider": "poolside", - "score": 74.6, - "date": "2026-06-15" + "model_id": "01-ai/Yi-1.5-6B-Chat", + "short_name": "Yi-1.5-6B-Chat", + "provider": "01-ai", + "score": 38.23, + "date": "2024-05-11" }, { - "model_id": "stepfun-ai/Step-3.5-Flash", - "short_name": "Step-3.5-Flash", - "provider": "stepfun-ai", - "score": 74.4, - "date": "2026-02-01" + "model_id": "Qwen/Qwen1.5-14B-Chat", + "short_name": "Qwen1.5-14B-Chat", + "provider": "Qwen", + "score": 38.02, + "date": "2024-01-30" }, { - "model_id": "tencent/Hy3-preview", - "short_name": "Hy3-preview", - "provider": "tencent", - "score": 74.4, - "date": "2026-04-13" + "model_id": "mistralai/Ministral-8B-Instruct-2410", + "short_name": "Ministral-8B-Instruct-2410", + "provider": "mistralai", + "score": 37.93, + "date": "2024-10-15" }, { - "model_id": "MiniMaxAI/MiniMax-M2.1", - "short_name": "MiniMax-M2.1", - "provider": "MiniMaxAI", - "score": 74.0, - "date": "2025-12-20" + "model_id": "CohereLabs/c4ai-command-r-v01", + "short_name": "c4ai-command-r-v01", + "provider": "CohereLabs", + "score": 37.9, + "date": "2024-03-11" }, { - "model_id": "inclusionAI/Ring-2.6-1T", - "short_name": "Ring-2.6-1T", - "provider": "inclusionAI", - "score": 74.0, - "date": "2026-05-14" + "model_id": "internlm/internlm2-math-plus-20b", + "short_name": "internlm2-math-plus-20b", + "provider": "internlm", + "score": 37.1, + "date": "2024-05-24" }, { - "model_id": "zai-org/GLM-4.7", - "short_name": "GLM-4.7", - "provider": "zai-org", - "score": 73.8, - "date": "2025-12-22" + "model_id": "GSAI-ML/LLaDA-8B-Instruct", + "short_name": "LLaDA-8B-Instruct", + "provider": "GSAI-ML", + "score": 37.0, + "date": "2025-02-19" }, { - "model_id": "Qwen/Qwen3.6-35B-A3B", - "short_name": "Qwen3.6-35B-A3B", - "provider": "Qwen", - "score": 73.4, - "date": "2026-04-15" + "model_id": "abacusai/Llama-3-Smaug-8B", + "short_name": "Llama-3-Smaug-8B", + "provider": "abacusai", + "score": 36.93, + "date": "2024-04-19" }, { - "model_id": "Qwen/Qwen3.5-27B", - "short_name": "Qwen3.5-27B", - "provider": "Qwen", - "score": 72.4, - "date": "2026-02-24" + "model_id": "meta-llama/Llama-3.1-8B", + "short_name": "Llama-3.1-8B", + "provider": "meta-llama", + "score": 36.6, + "date": "2024-07-14" }, { - "model_id": "inclusionAI/Ling-2.6-1T", - "short_name": "Ling-2.6-1T", - "provider": "inclusionAI", - "score": 72.2, - "date": "2026-04-29" + "model_id": "meta-llama/Meta-Llama-3-8B", + "short_name": "Meta-Llama-3-8B", + "provider": "meta-llama", + "score": 35.36, + "date": "2024-04-17" }, { - "model_id": "Qwen/Qwen3.5-122B-A10B", - "short_name": "Qwen3.5-122B-A10B", - "provider": "Qwen", - "score": 72.0, - "date": "2026-02-24" + "model_id": "deepseek-ai/deepseek-math-7b-instruct", + "short_name": "deepseek-math-7b-instruct", + "provider": "deepseek-ai", + "score": 35.3, + "date": "2024-02-05" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", - "provider": "nvidia", - "score": 71.9, - "date": "2026-06-03" + "model_id": "deepseek-ai/DeepSeek-Coder-V2-Lite-Base", + "short_name": "DeepSeek-Coder-V2-Lite-Base", + "provider": "deepseek-ai", + "score": 34.37, + "date": "2024-06-14" }, { - "model_id": "moonshotai/Kimi-K2-Thinking", - "short_name": "Kimi-K2-Thinking", - "provider": "moonshotai", - "score": 71.3, - "date": "2025-11-04" + "model_id": "CohereLabs/aya-expanse-8b", + "short_name": "aya-expanse-8b", + "provider": "CohereLabs", + "score": 33.74, + "date": "2024-10-23" }, { - "model_id": "poolside/Laguna-XS-2.1", - "short_name": "Laguna-XS-2.1", - "provider": "poolside", - "score": 70.9, - "date": "2026-06-20" + "model_id": "internlm/internlm2-math-plus-7b", + "short_name": "internlm2-math-plus-7b", + "provider": "internlm", + "score": 33.5, + "date": "2024-05-24" }, { - "model_id": "moonshotai/Kimi-K2.5", - "short_name": "Kimi-K2.5", - "provider": "moonshotai", - "score": 70.8, - "date": "2026-01-01" + "model_id": "ibm-granite/granite-3.1-8b-base", + "short_name": "granite-3.1-8b-base", + "provider": "ibm-granite", + "score": 33.08, + "date": "2024-12-06" }, { - "model_id": "Qwen/Qwen3-Coder-Next", - "short_name": "Qwen3-Coder-Next", + "model_id": "Qwen/Qwen2.5-1.5B", + "short_name": "Qwen2.5-1.5B", "provider": "Qwen", - "score": 70.6, - "date": "2026-01-30" + "score": 32.1, + "date": "2024-09-15" }, { - "model_id": "ornith-ai/Ornith-1.5-9B", - "short_name": "Ornith-1.5-9B", - "provider": "ornith-ai", - "score": 70.6, - "date": "2026-08-18" + "model_id": "ibm-granite/granite-3.0-8b-base", + "short_name": "granite-3.0-8b-base", + "provider": "ibm-granite", + "score": 31.03, + "date": "2024-10-02" }, { - "model_id": "upstage/Solar-Open2-250B", - "short_name": "Solar-Open2-250B", - "provider": "upstage", - "score": 70.4, - "date": "2026-07-22" + "model_id": "mistralai/Mistral-7B-Instruct-v0.2", + "short_name": "Mistral-7B-Instruct-v0.2", + "provider": "mistralai", + "score": 30.84, + "date": "2023-12-11" }, { - "model_id": "poolside/Laguna-XS.2", - "short_name": "Laguna-XS.2", - "provider": "poolside", - "score": 69.9, - "date": "2026-04-23" + "model_id": "mistral-community/Mistral-7B-v0.2", + "short_name": "Mistral-7B-v0.2", + "provider": "mistral-community", + "score": 30.43, + "date": "2024-03-23" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", - "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", - "provider": "nvidia", - "score": 69.7, - "date": "2026-06-03" + "model_id": "Qwen/Qwen1.5-7B-Chat", + "short_name": "Qwen1.5-7B-Chat", + "provider": "Qwen", + "score": 29.06, + "date": "2024-01-30" }, { - "model_id": "MiniMaxAI/MiniMax-M2", - "short_name": "MiniMax-M2", - "provider": "MiniMaxAI", - "score": 69.4, - "date": "2025-10-22" + "model_id": "01-ai/Yi-6B-Chat", + "short_name": "Yi-6B-Chat", + "provider": "01-ai", + "score": 28.84, + "date": "2023-11-22" }, { - "model_id": "ornith-ai/Ornith-1.0-9B", - "short_name": "Ornith-1.0-9B", - "provider": "ornith-ai", - "score": 69.4, - "date": "2026-06-21" + "model_id": "01-ai/Yi-6B", + "short_name": "Yi-6B", + "provider": "01-ai", + "score": 26.51, + "date": "2023-11-01" }, { - "model_id": "MuVeraAI/Laguna-XS.2", - "short_name": "Laguna-XS.2", - "provider": "MuVeraAI", - "score": 68.2, - "date": "2026-04-28" + "model_id": "ibm-granite/granite-3.1-2b-base", + "short_name": "granite-3.1-2b-base", + "provider": "ibm-granite", + "score": 23.89, + "date": "2024-12-06" }, { - "model_id": "CohereLabs/North-Mini-Code-1.0", - "short_name": "North-Mini-Code-1.0", - "provider": "CohereLabs", - "score": 67.6, - "date": "2026-06-05" + "model_id": "EleutherAI/llemma_7b", + "short_name": "llemma_7b", + "provider": "EleutherAI", + "score": 23.45, + "date": "2023-09-12" + }, + { + "model_id": "Qwen/Qwen2-1.5B-Instruct", + "short_name": "Qwen2-1.5B-Instruct", + "provider": "Qwen", + "score": 22.62, + "date": "2024-06-03" }, { - "model_id": "internlm/Intern-S2-Preview", - "short_name": "Intern-S2-Preview", - "provider": "internlm", - "score": 64.0, - "date": "2026-05-15" + "model_id": "Qwen/Qwen2-1.5B", + "short_name": "Qwen2-1.5B", + "provider": "Qwen", + "score": 22.56, + "date": "2024-05-31" }, { - "model_id": "openpangu/openPangu-2.0-Flash", - "short_name": "openPangu-2.0-Flash", - "provider": "openpangu", - "score": 63.1, - "date": "2026-06-30" + "model_id": "meta-llama/Llama-3.2-3B", + "short_name": "Llama-3.2-3B", + "provider": "meta-llama", + "score": 22.17, + "date": "2024-09-18" }, { - "model_id": "openai/gpt-oss-120b", - "short_name": "gpt-oss-120b", - "provider": "openai", - "score": 62.4, - "date": "2025-08-04" + "model_id": "ibm-granite/granite-3.0-2b-base", + "short_name": "granite-3.0-2b-base", + "provider": "ibm-granite", + "score": 21.72, + "date": "2024-10-02" }, { - "model_id": "inclusionAI/Ling-2.6-flash", - "short_name": "Ling-2.6-flash", - "provider": "inclusionAI", - "score": 61.2, - "date": "2026-04-28" + "model_id": "ibm-granite/granite-3.1-3b-a800m-base", + "short_name": "granite-3.1-3b-a800m-base", + "provider": "ibm-granite", + "score": 20.39, + "date": "2024-12-06" }, { - "model_id": "openai/gpt-oss-20b", - "short_name": "gpt-oss-20b", - "provider": "openai", - "score": 60.7, - "date": "2025-08-04" + "model_id": "HuggingFaceTB/SmolLM2-1.7B", + "short_name": "SmolLM2-1.7B", + "provider": "HuggingFaceTB", + "score": 18.31, + "date": "2024-10-30" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "provider": "nvidia", - "score": 60.47, - "date": "2026-03-10" + "model_id": "Qwen/Qwen2-0.5B", + "short_name": "Qwen2-0.5B", + "provider": "Qwen", + "score": 14.97, + "date": "2024-05-31" }, { - "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", - "provider": "RedHatAI", - "score": 60.47, - "date": "2026-03-26" + "model_id": "Qwen/Qwen2.5-0.5B", + "short_name": "Qwen2.5-0.5B", + "provider": "Qwen", + "score": 14.92, + "date": "2024-09-15" }, { - "model_id": "zai-org/GLM-4.7-Flash", - "short_name": "GLM-4.7-Flash", - "provider": "zai-org", - "score": 59.2, - "date": "2026-01-19" + "model_id": "ibm-granite/granite-3.1-1b-a400m-base", + "short_name": "granite-3.1-1b-a400m-base", + "provider": "ibm-granite", + "score": 12.34, + "date": "2024-12-06" }, { - "model_id": "facebook/cwm", - "short_name": "cwm", - "provider": "facebook", - "score": 53.9, - "date": "2025-08-25" + "model_id": "meta-llama/Llama-3.2-1B", + "short_name": "Llama-3.2-1B", + "provider": "meta-llama", + "score": 11.95, + "date": "2024-09-18" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", - "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", - "provider": "nvidia", - "score": 52.8, - "date": "2026-08-04" + "model_id": "HuggingFaceTB/SmolLM2-360M", + "short_name": "SmolLM2-360M", + "provider": "HuggingFaceTB", + "score": 11.38, + "date": "2024-10-31" }, { - "model_id": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", - "short_name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", - "provider": "nvidia", - "score": 51.56, - "date": "2026-08-01" + "model_id": "HuggingFaceTB/SmolLM2-135M", + "short_name": "SmolLM2-135M", + "provider": "HuggingFaceTB", + "score": 10.85, + "date": "2024-10-31" + }, + { + "model_id": "Qwen/Qwen2.5-VL-72B-Instruct", + "short_name": "Qwen2.5-VL-72B-Instruct", + "provider": "Qwen", + "score": 0.65, + "date": "2025-01-27" } ] }, @@ -3081,233 +3081,100 @@ ] }, "apex_agents": { - "name": "apex-agents", - "dataset": "mercor/apex-agents", - "lower_is_better": false, - "models": [ - { - "model_id": "moonshotai/Kimi-K3", - "short_name": "Kimi-K3", - "provider": "moonshotai", - "score": 41.0, - "date": "2026-06-13" - }, - { - "model_id": "tencent/Hy4-preview", - "short_name": "Hy4-preview", - "provider": "tencent", - "score": 37.1, - "date": "2026-08-27" - }, - { - "model_id": "dots-studio/dots3-note-prev", - "short_name": "dots3-note-prev", - "provider": "dots-studio", - "score": 30.8, - "date": "2026-08-09" - }, - { - "model_id": "MiniMaxAI/MiniMax-M3", - "short_name": "MiniMax-M3", - "provider": "MiniMaxAI", - "score": 27.7, - "date": "2026-06-02" - }, - { - "model_id": "tencent/Hy3", - "short_name": "Hy3", - "provider": "tencent", - "score": 25.6, - "date": "2026-07-02" - }, - { - "model_id": "zai-org/GLM-5", - "short_name": "GLM-5", - "provider": "zai-org", - "score": 17.2, - "date": "2026-02-11" - }, - { - "model_id": "upstage/Solar-Open2-250B", - "short_name": "Solar-Open2-250B", - "provider": "upstage", - "score": 16.6, - "date": "2026-07-22" - }, - { - "model_id": "moonshotai/Kimi-K2.5", - "short_name": "Kimi-K2.5", - "provider": "moonshotai", - "score": 14.4, - "date": "2026-01-01" - }, - { - "model_id": "Qwen/Qwen3.5-397B-A17B", - "short_name": "Qwen3.5-397B-A17B", - "provider": "Qwen", - "score": 13.6, - "date": "2026-02-16" - }, - { - "model_id": "MiniMaxAI/MiniMax-M2.5", - "short_name": "MiniMax-M2.5", - "provider": "MiniMaxAI", - "score": 6.2, - "date": "2026-02-12" - }, - { - "model_id": "moonshotai/Kimi-K2-Instruct", - "short_name": "Kimi-K2-Instruct", - "provider": "moonshotai", - "score": 4.1, - "date": "2025-07-11" - }, - { - "model_id": "zai-org/GLM-4.6", - "short_name": "GLM-4.6", - "provider": "zai-org", - "score": 4.0, - "date": "2025-09-29" - }, - { - "model_id": "zai-org/GLM-4.7", - "short_name": "GLM-4.7", - "provider": "zai-org", - "score": 3.1, - "date": "2025-12-22" - } - ] - }, - "olmOcr": { - "name": "olmOCR-bench", - "dataset": "allenai/olmOCR-bench", - "lower_is_better": false, - "models": [ - { - "model_id": "infly/Infinity-Parser2-Pro", - "short_name": "Infinity-Parser2-Pro", - "provider": "infly", - "score": 87.6, - "date": "2026-04-08" - }, - { - "model_id": "datalab-to/chandra-ocr-2", - "short_name": "chandra-ocr-2", - "provider": "datalab-to", - "score": 85.8, - "date": "2026-03-16" - }, - { - "model_id": "dots-studio/dots.mocr", - "short_name": "dots.mocr", - "provider": "dots-studio", - "score": 83.9, - "date": "2026-03-19" - }, - { - "model_id": "jinaai/jina-ocr-v1", - "short_name": "jina-ocr-v1", - "provider": "jinaai", - "score": 83.4, - "date": "2026-09-01" - }, - { - "model_id": "datalab-to/surya-ocr-2", - "short_name": "surya-ocr-2", - "provider": "datalab-to", - "score": 83.3, - "date": "2026-05-14" - }, + "name": "apex-agents", + "dataset": "mercor/apex-agents", + "lower_is_better": false, + "models": [ { - "model_id": "onnx-community/Surya-Ocr-2-Onnx", - "short_name": "Surya-Ocr-2-Onnx", - "provider": "onnx-community", - "score": 83.3, - "date": "2026-08-03" + "model_id": "moonshotai/Kimi-K3", + "short_name": "Kimi-K3", + "provider": "moonshotai", + "score": 41.0, + "date": "2026-06-13" }, { - "model_id": "lightonai/LightOnOCR-2-1B", - "short_name": "LightOnOCR-2-1B", - "provider": "lightonai", - "score": 83.2, - "date": "2026-01-16" + "model_id": "tencent/Hy4-preview", + "short_name": "Hy4-preview", + "provider": "tencent", + "score": 37.1, + "date": "2026-08-27" }, { - "model_id": "datalab-to/chandra", - "short_name": "chandra", - "provider": "datalab-to", - "score": 83.1, - "date": "2025-10-21" + "model_id": "dots-studio/dots3-note-prev", + "short_name": "dots3-note-prev", + "provider": "dots-studio", + "score": 30.8, + "date": "2026-08-09" }, { - "model_id": "infly/Infinity-Parser-7B", - "short_name": "Infinity-Parser-7B", - "provider": "infly", - "score": 82.5, - "date": "2025-10-17" + "model_id": "MiniMaxAI/MiniMax-M3", + "short_name": "MiniMax-M3", + "provider": "MiniMaxAI", + "score": 27.7, + "date": "2026-06-02" }, { - "model_id": "tiiuae/Falcon-OCR", - "short_name": "Falcon-OCR", - "provider": "tiiuae", - "score": 80.3, - "date": "2026-02-22" + "model_id": "tencent/Hy3", + "short_name": "Hy3", + "provider": "tencent", + "score": 25.6, + "date": "2026-07-02" }, { - "model_id": "baidu/Qianfan-OCR", - "short_name": "Qianfan-OCR", - "provider": "baidu", - "score": 79.8, - "date": "2026-03-18" + "model_id": "zai-org/GLM-5", + "short_name": "GLM-5", + "provider": "zai-org", + "score": 17.2, + "date": "2026-02-11" }, { - "model_id": "dots-studio/dots.ocr", - "short_name": "dots.ocr", - "provider": "dots-studio", - "score": 79.1, - "date": "2025-07-30" + "model_id": "upstage/Solar-Open2-250B", + "short_name": "Solar-Open2-250B", + "provider": "upstage", + "score": 16.6, + "date": "2026-07-22" }, { - "model_id": "deepseek-ai/DeepSeek-OCR-2", - "short_name": "DeepSeek-OCR-2", - "provider": "deepseek-ai", - "score": 76.3, - "date": "2026-01-27" + "model_id": "moonshotai/Kimi-K2.5", + "short_name": "Kimi-K2.5", + "provider": "moonshotai", + "score": 14.4, + "date": "2026-01-01" }, { - "model_id": "lightonai/LightOnOCR-1B-1025", - "short_name": "LightOnOCR-1B-1025", - "provider": "lightonai", - "score": 76.1, - "date": "2025-10-20" + "model_id": "Qwen/Qwen3.5-397B-A17B", + "short_name": "Qwen3.5-397B-A17B", + "provider": "Qwen", + "score": 13.6, + "date": "2026-02-16" }, { - "model_id": "deepseek-ai/DeepSeek-OCR", - "short_name": "DeepSeek-OCR", - "provider": "deepseek-ai", - "score": 75.7, - "date": "2025-10-17" + "model_id": "MiniMaxAI/MiniMax-M2.5", + "short_name": "MiniMax-M2.5", + "provider": "MiniMaxAI", + "score": 6.2, + "date": "2026-02-12" }, { - "model_id": "opendatalab/MinerU2.5-2509-1.2B", - "short_name": "MinerU2.5-2509-1.2B", - "provider": "opendatalab", - "score": 75.2, - "date": "2025-09-17" + "model_id": "moonshotai/Kimi-K2-Instruct", + "short_name": "Kimi-K2-Instruct", + "provider": "moonshotai", + "score": 4.1, + "date": "2025-07-11" }, { - "model_id": "zai-org/GLM-OCR", - "short_name": "GLM-OCR", + "model_id": "zai-org/GLM-4.6", + "short_name": "GLM-4.6", "provider": "zai-org", - "score": 75.2, - "date": "2026-01-30" + "score": 4.0, + "date": "2025-09-29" }, { - "model_id": "small-models-for-glam/kraken-ppocrv6-medium", - "short_name": "kraken-ppocrv6-medium", - "provider": "small-models-for-glam", - "score": 36.77, - "date": "2026-09-03" + "model_id": "zai-org/GLM-4.7", + "short_name": "GLM-4.7", + "provider": "zai-org", + "score": 3.1, + "date": "2025-12-22" } ] }, @@ -3495,36 +3362,204 @@ "model_id": "deepseek-ai/DeepSeek-OCR-2", "short_name": "DeepSeek-OCR-2", "provider": "deepseek-ai", - "score": 41.2, + "score": 41.2, + "date": "2026-01-27" + }, + { + "model_id": "ibm-granite/granite-vision-4.1-4b", + "short_name": "granite-vision-4.1-4b", + "provider": "ibm-granite", + "score": 39.45, + "date": "2026-04-16" + }, + { + "model_id": "tencent/WeVisDoc-2B", + "short_name": "WeVisDoc-2B", + "provider": "tencent", + "score": 38.93, + "date": "2026-09-16" + }, + { + "model_id": "tencent/WeVisDoc-4B", + "short_name": "WeVisDoc-4B", + "provider": "tencent", + "score": 36.15, + "date": "2026-09-16" + }, + { + "model_id": "zai-org/GLM-OCR", + "short_name": "GLM-OCR", + "provider": "zai-org", + "score": 29.6, + "date": "2026-01-30" + } + ] + }, + "olmOcr": { + "name": "olmOCR-bench", + "dataset": "allenai/olmOCR-bench", + "lower_is_better": false, + "models": [ + { + "model_id": "infly/Infinity-Parser2-Pro", + "short_name": "Infinity-Parser2-Pro", + "provider": "infly", + "score": 87.6, + "date": "2026-04-08" + }, + { + "model_id": "datalab-to/chandra-ocr-2", + "short_name": "chandra-ocr-2", + "provider": "datalab-to", + "score": 85.8, + "date": "2026-03-16" + }, + { + "model_id": "dots-studio/dots.mocr", + "short_name": "dots.mocr", + "provider": "dots-studio", + "score": 83.9, + "date": "2026-03-19" + }, + { + "model_id": "jinaai/jina-ocr-v1", + "short_name": "jina-ocr-v1", + "provider": "jinaai", + "score": 83.4, + "date": "2026-09-01" + }, + { + "model_id": "datalab-to/surya-ocr-2", + "short_name": "surya-ocr-2", + "provider": "datalab-to", + "score": 83.3, + "date": "2026-05-14" + }, + { + "model_id": "onnx-community/Surya-Ocr-2-Onnx", + "short_name": "Surya-Ocr-2-Onnx", + "provider": "onnx-community", + "score": 83.3, + "date": "2026-08-03" + }, + { + "model_id": "lightonai/LightOnOCR-2-1B", + "short_name": "LightOnOCR-2-1B", + "provider": "lightonai", + "score": 83.2, + "date": "2026-01-16" + }, + { + "model_id": "datalab-to/chandra", + "short_name": "chandra", + "provider": "datalab-to", + "score": 83.1, + "date": "2025-10-21" + }, + { + "model_id": "infly/Infinity-Parser-7B", + "short_name": "Infinity-Parser-7B", + "provider": "infly", + "score": 82.5, + "date": "2025-10-17" + }, + { + "model_id": "tiiuae/Falcon-OCR", + "short_name": "Falcon-OCR", + "provider": "tiiuae", + "score": 80.3, + "date": "2026-02-22" + }, + { + "model_id": "baidu/Qianfan-OCR", + "short_name": "Qianfan-OCR", + "provider": "baidu", + "score": 79.8, + "date": "2026-03-18" + }, + { + "model_id": "dots-studio/dots.ocr", + "short_name": "dots.ocr", + "provider": "dots-studio", + "score": 79.1, + "date": "2025-07-30" + }, + { + "model_id": "deepseek-ai/DeepSeek-OCR-2", + "short_name": "DeepSeek-OCR-2", + "provider": "deepseek-ai", + "score": 76.3, "date": "2026-01-27" }, { - "model_id": "ibm-granite/granite-vision-4.1-4b", - "short_name": "granite-vision-4.1-4b", - "provider": "ibm-granite", - "score": 39.45, - "date": "2026-04-16" + "model_id": "lightonai/LightOnOCR-1B-1025", + "short_name": "LightOnOCR-1B-1025", + "provider": "lightonai", + "score": 76.1, + "date": "2025-10-20" }, { - "model_id": "tencent/WeVisDoc-2B", - "short_name": "WeVisDoc-2B", - "provider": "tencent", - "score": 38.93, - "date": "2026-09-16" + "model_id": "deepseek-ai/DeepSeek-OCR", + "short_name": "DeepSeek-OCR", + "provider": "deepseek-ai", + "score": 75.7, + "date": "2025-10-17" }, { - "model_id": "tencent/WeVisDoc-4B", - "short_name": "WeVisDoc-4B", - "provider": "tencent", - "score": 36.15, - "date": "2026-09-16" + "model_id": "opendatalab/MinerU2.5-2509-1.2B", + "short_name": "MinerU2.5-2509-1.2B", + "provider": "opendatalab", + "score": 75.2, + "date": "2025-09-17" }, { "model_id": "zai-org/GLM-OCR", "short_name": "GLM-OCR", "provider": "zai-org", - "score": 29.6, + "score": 75.2, "date": "2026-01-30" + }, + { + "model_id": "small-models-for-glam/kraken-ppocrv6-medium", + "short_name": "kraken-ppocrv6-medium", + "provider": "small-models-for-glam", + "score": 36.77, + "date": "2026-09-03" + } + ] + }, + "agents_last_exam": { + "name": "Agents Last Exam \u2014 Task Card Metadata", + "dataset": "agents-last-exam/agents-last-exam", + "lower_is_better": false, + "models": [ + { + "model_id": "moonshotai/Kimi-K3", + "short_name": "Kimi-K3", + "provider": "moonshotai", + "score": 28.29, + "date": "2026-06-13" + }, + { + "model_id": "zai-org/GLM-5.2", + "short_name": "GLM-5.2", + "provider": "zai-org", + "score": 20.39, + "date": "2026-06-16" + }, + { + "model_id": "Qwen/Qwen3.8-27B", + "short_name": "Qwen3.8-27B", + "provider": "Qwen", + "score": 20.39, + "date": "2026-08-05" + }, + { + "model_id": "deepseek-ai/DeepSeek-V4-Pro", + "short_name": "DeepSeek-V4-Pro", + "provider": "deepseek-ai", + "score": 12.39, + "date": "2026-04-22" } ] }, @@ -4054,233 +4089,44 @@ { "model_id": "opendatalab/MinerU2.5-2509-1.2B", "short_name": "MinerU2.5-2509-1.2B", - "provider": "opendatalab", - "score": 85.61, - "date": "2025-09-17" - }, - { - "model_id": "opendatalab/MinerU2.0-2505-0.9B", - "short_name": "MinerU2.0-2505-0.9B", - "provider": "opendatalab", - "score": 76.95, - "date": "2025-06-05" - }, - { - "model_id": "deepseek-ai/DeepSeek-OCR", - "short_name": "DeepSeek-OCR", - "provider": "deepseek-ai", - "score": 73.99, - "date": "2025-10-17" - }, - { - "model_id": "deepseek-ai/DeepSeek-OCR-2", - "short_name": "DeepSeek-OCR-2", - "provider": "deepseek-ai", - "score": 73.01, - "date": "2026-01-27" - }, - { - "model_id": "ByteDance/Dolphin", - "short_name": "Dolphin", - "provider": "ByteDance", - "score": 61.78, - "date": "2025-05-19" - }, - { - "model_id": "ByteDance/Dolphin-1.5", - "short_name": "Dolphin-1.5", - "provider": "ByteDance", - "score": 61.48, - "date": "2025-10-17" - } - ] - }, - "WildClawBench": { - "name": "WildClawBench", - "dataset": "internlm/WildClawBench", - "lower_is_better": false, - "models": [ - { - "model_id": "dots-studio/dots3-note-prev", - "short_name": "dots3-note-prev", - "provider": "dots-studio", - "score": 61.7, - "date": "2026-08-09" - }, - { - "model_id": "Qwen/Qwen3.8-2.4T-A95B", - "short_name": "Qwen3.8-2.4T-A95B", - "provider": "Qwen", - "score": 56.2, - "date": "2026-08-08" - }, - { - "model_id": "moonshotai/Kimi-K3", - "short_name": "Kimi-K3", - "provider": "moonshotai", - "score": 54.5, - "date": "2026-06-13" - }, - { - "model_id": "zai-org/GLM-5.2", - "short_name": "GLM-5.2", - "provider": "zai-org", - "score": 54.2, - "date": "2026-06-16" - }, - { - "model_id": "tencent/Hy3", - "short_name": "Hy3", - "provider": "tencent", - "score": 53.6, - "date": "2026-07-02" - }, - { - "model_id": "nex-agi/Nex-N2-Pro", - "short_name": "Nex-N2-Pro", - "provider": "nex-agi", - "score": 53.5, - "date": "2026-06-03" - }, - { - "model_id": "zai-org/GLM-5.1", - "short_name": "GLM-5.1", - "provider": "zai-org", - "score": 48.2, - "date": "2026-04-03" - }, - { - "model_id": "Qwen/Qwen3.8-27B", - "short_name": "Qwen3.8-27B", - "provider": "Qwen", - "score": 48.02, - "date": "2026-08-05" - }, - { - "model_id": "meta-models/Muse-Glimmer-30B", - "short_name": "Muse-Glimmer-30B", - "provider": "meta-models", - "score": 47.6, - "date": "2026-08-09" - }, - { - "model_id": "moonshotai/Kimi-K2.7-Code", - "short_name": "Kimi-K2.7-Code", - "provider": "moonshotai", - "score": 46.9, - "date": "2026-06-11" - }, - { - "model_id": "internlm/Intern-S2-Preview-397B", - "short_name": "Intern-S2-Preview-397B", - "provider": "internlm", - "score": 44.7, - "date": "2026-07-16" - }, - { - "model_id": "deepseek-ai/DeepSeek-V4-Pro", - "short_name": "DeepSeek-V4-Pro", - "provider": "deepseek-ai", - "score": 43.7, - "date": "2026-04-22" - }, - { - "model_id": "Qwen/Qwen3.6-27B", - "short_name": "Qwen3.6-27B", - "provider": "Qwen", - "score": 43.2, - "date": "2026-04-21" - }, - { - "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", - "short_name": "MiMo-V2.5-Pro", - "provider": "XiaomiMiMo", - "score": 43.0, - "date": "2026-04-27" - }, - { - "model_id": "zai-org/GLM-5", - "short_name": "GLM-5", - "provider": "zai-org", - "score": 42.6, - "date": "2026-02-11" - }, - { - "model_id": "openpangu/openPangu-2.0-Flash", - "short_name": "openPangu-2.0-Flash", - "provider": "openpangu", - "score": 41.5, - "date": "2026-06-30" - }, - { - "model_id": "internlm/Intern-S2-Preview", - "short_name": "Intern-S2-Preview", - "provider": "internlm", - "score": 39.2, - "date": "2026-05-15" - }, - { - "model_id": "Qwen/Qwen3.5-397B-A17B", - "short_name": "Qwen3.5-397B-A17B", - "provider": "Qwen", - "score": 34.5, - "date": "2026-02-16" - }, - { - "model_id": "MiniMaxAI/MiniMax-M2.7", - "short_name": "MiniMax-M2.7", - "provider": "MiniMaxAI", - "score": 33.8, - "date": "2026-04-09" + "provider": "opendatalab", + "score": 85.61, + "date": "2025-09-17" }, { - "model_id": "moonshotai/Kimi-K2.5", - "short_name": "Kimi-K2.5", - "provider": "moonshotai", - "score": 30.8, - "date": "2026-01-01" + "model_id": "opendatalab/MinerU2.0-2505-0.9B", + "short_name": "MinerU2.0-2505-0.9B", + "provider": "opendatalab", + "score": 76.95, + "date": "2025-06-05" }, { - "model_id": "MiniMaxAI/MiniMax-M2.5", - "short_name": "MiniMax-M2.5", - "provider": "MiniMaxAI", - "score": 27.1, - "date": "2026-02-12" + "model_id": "deepseek-ai/DeepSeek-OCR", + "short_name": "DeepSeek-OCR", + "provider": "deepseek-ai", + "score": 73.99, + "date": "2025-10-17" }, { - "model_id": "stepfun-ai/Step-3.5-Flash", - "short_name": "Step-3.5-Flash", - "provider": "stepfun-ai", - "score": 26.7, - "date": "2026-02-01" - } - ] - }, - "chi_bench": { - "name": "\u03c7-Bench", - "dataset": "actava/chi-bench", - "lower_is_better": false, - "models": [ - { - "model_id": "zai-org/GLM-5.1", - "short_name": "GLM-5.1", - "provider": "zai-org", - "score": 18.7, - "date": "2026-04-03" + "model_id": "deepseek-ai/DeepSeek-OCR-2", + "short_name": "DeepSeek-OCR-2", + "provider": "deepseek-ai", + "score": 73.01, + "date": "2026-01-27" }, { - "model_id": "moonshotai/Kimi-K2.6", - "short_name": "Kimi-K2.6", - "provider": "moonshotai", - "score": 15.6, - "date": "2026-04-14" + "model_id": "ByteDance/Dolphin", + "short_name": "Dolphin", + "provider": "ByteDance", + "score": 61.78, + "date": "2025-05-19" }, { - "model_id": "deepseek-ai/DeepSeek-V4-Pro", - "short_name": "DeepSeek-V4-Pro", - "provider": "deepseek-ai", - "score": 14.2, - "date": "2026-04-22" + "model_id": "ByteDance/Dolphin-1.5", + "short_name": "Dolphin-1.5", + "provider": "ByteDance", + "score": 61.48, + "date": "2025-10-17" } ] }, @@ -4368,41 +4214,6 @@ } ] }, - "agents_last_exam": { - "name": "Agents Last Exam \u2014 Task Card Metadata", - "dataset": "agents-last-exam/agents-last-exam", - "lower_is_better": false, - "models": [ - { - "model_id": "moonshotai/Kimi-K3", - "short_name": "Kimi-K3", - "provider": "moonshotai", - "score": 28.29, - "date": "2026-06-13" - }, - { - "model_id": "zai-org/GLM-5.2", - "short_name": "GLM-5.2", - "provider": "zai-org", - "score": 20.39, - "date": "2026-06-16" - }, - { - "model_id": "Qwen/Qwen3.8-27B", - "short_name": "Qwen3.8-27B", - "provider": "Qwen", - "score": 20.39, - "date": "2026-08-05" - }, - { - "model_id": "deepseek-ai/DeepSeek-V4-Pro", - "short_name": "DeepSeek-V4-Pro", - "provider": "deepseek-ai", - "score": 12.39, - "date": "2026-04-22" - } - ] - }, "Long_Horizon_Terminal_Bench": { "name": "Long-Horizon Terminal-Bench (LHTB)", "dataset": "IntelligenceLab/Long-Horizon-Terminal-Bench", @@ -5980,57 +5791,218 @@ "model_id": "zai-org/GLM-5", "short_name": "GLM-5", "provider": "zai-org", - "score": 1208190.0, + "score": 1208190.0, + "date": "2026-02-11" + }, + { + "model_id": "deepseek-ai/DeepSeek-V4-Pro", + "short_name": "DeepSeek-V4-Pro", + "provider": "deepseek-ai", + "score": 1066426.0, + "date": "2026-04-22" + }, + { + "model_id": "moonshotai/Kimi-K2.6", + "short_name": "Kimi-K2.6", + "provider": "moonshotai", + "score": 511137.0, + "date": "2026-04-14" + }, + { + "model_id": "moonshotai/Kimi-K2.5", + "short_name": "Kimi-K2.5", + "provider": "moonshotai", + "score": 408822.0, + "date": "2026-01-01" + }, + { + "model_id": "zai-org/GLM-4.7", + "short_name": "GLM-4.7", + "provider": "zai-org", + "score": 398410.0, + "date": "2025-12-22" + }, + { + "model_id": "MiniMaxAI/MiniMax-M2.5", + "short_name": "MiniMax-M2.5", + "provider": "MiniMaxAI", + "score": 230465.0, + "date": "2026-02-12" + }, + { + "model_id": "Qwen/Qwen3.5-397B-A17B", + "short_name": "Qwen3.5-397B-A17B", + "provider": "Qwen", + "score": 90787.0, + "date": "2026-02-16" + }, + { + "model_id": "Qwen/Qwen3.5-122B-A10B", + "short_name": "Qwen3.5-122B-A10B", + "provider": "Qwen", + "score": 0.0, + "date": "2026-02-24" + } + ] + }, + "WildClawBench": { + "name": "WildClawBench", + "dataset": "internlm/WildClawBench", + "lower_is_better": false, + "models": [ + { + "model_id": "dots-studio/dots3-note-prev", + "short_name": "dots3-note-prev", + "provider": "dots-studio", + "score": 61.7, + "date": "2026-08-09" + }, + { + "model_id": "Qwen/Qwen3.8-2.4T-A95B", + "short_name": "Qwen3.8-2.4T-A95B", + "provider": "Qwen", + "score": 56.2, + "date": "2026-08-08" + }, + { + "model_id": "moonshotai/Kimi-K3", + "short_name": "Kimi-K3", + "provider": "moonshotai", + "score": 54.5, + "date": "2026-06-13" + }, + { + "model_id": "zai-org/GLM-5.2", + "short_name": "GLM-5.2", + "provider": "zai-org", + "score": 54.2, + "date": "2026-06-16" + }, + { + "model_id": "tencent/Hy3", + "short_name": "Hy3", + "provider": "tencent", + "score": 53.6, + "date": "2026-07-02" + }, + { + "model_id": "nex-agi/Nex-N2-Pro", + "short_name": "Nex-N2-Pro", + "provider": "nex-agi", + "score": 53.5, + "date": "2026-06-03" + }, + { + "model_id": "zai-org/GLM-5.1", + "short_name": "GLM-5.1", + "provider": "zai-org", + "score": 48.2, + "date": "2026-04-03" + }, + { + "model_id": "Qwen/Qwen3.8-27B", + "short_name": "Qwen3.8-27B", + "provider": "Qwen", + "score": 48.02, + "date": "2026-08-05" + }, + { + "model_id": "meta-models/Muse-Glimmer-30B", + "short_name": "Muse-Glimmer-30B", + "provider": "meta-models", + "score": 47.6, + "date": "2026-08-09" + }, + { + "model_id": "moonshotai/Kimi-K2.7-Code", + "short_name": "Kimi-K2.7-Code", + "provider": "moonshotai", + "score": 46.9, + "date": "2026-06-11" + }, + { + "model_id": "internlm/Intern-S2-Preview-397B", + "short_name": "Intern-S2-Preview-397B", + "provider": "internlm", + "score": 44.7, + "date": "2026-07-16" + }, + { + "model_id": "deepseek-ai/DeepSeek-V4-Pro", + "short_name": "DeepSeek-V4-Pro", + "provider": "deepseek-ai", + "score": 43.7, + "date": "2026-04-22" + }, + { + "model_id": "Qwen/Qwen3.6-27B", + "short_name": "Qwen3.6-27B", + "provider": "Qwen", + "score": 43.2, + "date": "2026-04-21" + }, + { + "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", + "short_name": "MiMo-V2.5-Pro", + "provider": "XiaomiMiMo", + "score": 43.0, + "date": "2026-04-27" + }, + { + "model_id": "zai-org/GLM-5", + "short_name": "GLM-5", + "provider": "zai-org", + "score": 42.6, "date": "2026-02-11" }, { - "model_id": "deepseek-ai/DeepSeek-V4-Pro", - "short_name": "DeepSeek-V4-Pro", - "provider": "deepseek-ai", - "score": 1066426.0, - "date": "2026-04-22" + "model_id": "openpangu/openPangu-2.0-Flash", + "short_name": "openPangu-2.0-Flash", + "provider": "openpangu", + "score": 41.5, + "date": "2026-06-30" }, { - "model_id": "moonshotai/Kimi-K2.6", - "short_name": "Kimi-K2.6", - "provider": "moonshotai", - "score": 511137.0, - "date": "2026-04-14" + "model_id": "internlm/Intern-S2-Preview", + "short_name": "Intern-S2-Preview", + "provider": "internlm", + "score": 39.2, + "date": "2026-05-15" + }, + { + "model_id": "Qwen/Qwen3.5-397B-A17B", + "short_name": "Qwen3.5-397B-A17B", + "provider": "Qwen", + "score": 34.5, + "date": "2026-02-16" + }, + { + "model_id": "MiniMaxAI/MiniMax-M2.7", + "short_name": "MiniMax-M2.7", + "provider": "MiniMaxAI", + "score": 33.8, + "date": "2026-04-09" }, { "model_id": "moonshotai/Kimi-K2.5", "short_name": "Kimi-K2.5", "provider": "moonshotai", - "score": 408822.0, + "score": 30.8, "date": "2026-01-01" }, - { - "model_id": "zai-org/GLM-4.7", - "short_name": "GLM-4.7", - "provider": "zai-org", - "score": 398410.0, - "date": "2025-12-22" - }, { "model_id": "MiniMaxAI/MiniMax-M2.5", "short_name": "MiniMax-M2.5", "provider": "MiniMaxAI", - "score": 230465.0, + "score": 27.1, "date": "2026-02-12" }, { - "model_id": "Qwen/Qwen3.5-397B-A17B", - "short_name": "Qwen3.5-397B-A17B", - "provider": "Qwen", - "score": 90787.0, - "date": "2026-02-16" - }, - { - "model_id": "Qwen/Qwen3.5-122B-A10B", - "short_name": "Qwen3.5-122B-A10B", - "provider": "Qwen", - "score": 0.0, - "date": "2026-02-24" + "model_id": "stepfun-ai/Step-3.5-Flash", + "short_name": "Step-3.5-Flash", + "provider": "stepfun-ai", + "score": 26.7, + "date": "2026-02-01" } ] }, @@ -6384,6 +6356,34 @@ } ] }, + "chi_bench": { + "name": "\u03c7-Bench", + "dataset": "actava/chi-bench", + "lower_is_better": false, + "models": [ + { + "model_id": "zai-org/GLM-5.1", + "short_name": "GLM-5.1", + "provider": "zai-org", + "score": 18.7, + "date": "2026-04-03" + }, + { + "model_id": "moonshotai/Kimi-K2.6", + "short_name": "Kimi-K2.6", + "provider": "moonshotai", + "score": 15.6, + "date": "2026-04-14" + }, + { + "model_id": "deepseek-ai/DeepSeek-V4-Pro", + "short_name": "DeepSeek-V4-Pro", + "provider": "deepseek-ai", + "score": 14.2, + "date": "2026-04-22" + } + ] + }, "WBench": { "name": "WBench", "dataset": "meituan-longcat/WBench", @@ -6550,6 +6550,20 @@ "score": 55.5, "date": "2026-08-20" }, + { + "model_id": "crosbylegal/gemini-3.8-flash", + "short_name": "gemini-3.8-flash", + "provider": "crosbylegal", + "score": 55.2, + "date": "2026-10-02" + }, + { + "model_id": "crosbylegal/claude-opus-5-5", + "short_name": "claude-opus-5-5", + "provider": "crosbylegal", + "score": 53.5, + "date": "2026-10-02" + }, { "model_id": "crosbylegal/gemini-3.6-flash", "short_name": "gemini-3.6-flash", @@ -6904,100 +6918,100 @@ } }, "logos": { - "gnani": "https://cdn-avatars.huggingface.co/v1/production/uploads/63eb50dbd64e6436e22ba90a/TMj98qiLr9dUT4_oHFioD.jpeg", "tiiuae": "https://cdn-avatars.huggingface.co/v1/production/uploads/61a8d1aac664736898ffc84f/AT6cAB5ZNwCcqFMal71WD.jpeg", - "LGAI-EXAONE": "https://cdn-avatars.huggingface.co/v1/production/uploads/66a899a72f11aaf66001a8dc/UfdrP3GMo9pNT62BaMnhw.png", - "distil-whisper": "https://cdn-avatars.huggingface.co/v1/production/uploads/61f91cf54a8e5a275b2b3e7c/cUNzV7MAYi8lo9LsCYixp.png", - "xlangai": "https://cdn-avatars.huggingface.co/v1/production/uploads/628f6e5ab90dde28ef57d293/PHIYPvE_tCM94SgoUzd7l.jpeg", - "ATH-MaaS": "https://cdn-avatars.huggingface.co/v1/production/uploads/666a9d46a638e57bb7907929/CRc-9MCuH2q9hjTScyTPE.png", - "EleutherAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/1614054059123-603481bb60e3dd96631c9095.png", + "kyutai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6355a3c1805be5a8f30fea49/8xGdIOlfkopZfhbMitw_k.jpeg", + "robbyant": "https://cdn-avatars.huggingface.co/v1/production/uploads/67aeffda7330db26f93cd62f/ZTuImney4XzRmBHyUL47F.png", + "numind": "https://cdn-avatars.huggingface.co/v1/production/uploads/649be8cf867d442094248a40/p-vHYU5a6a6AlAqj0D1P7.png", + "CohereLabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png", + "facebook": "https://cdn-avatars.huggingface.co/v1/production/uploads/1592839207516-noauth.png", + "jdopensource": "https://cdn-avatars.huggingface.co/v1/production/uploads/68c0e2ab44ea28a974e3074b/g-4gTubd16qUtwmGZ0n4h.png", "RedHatAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/60466e4b4f40b01b66151416/cdABRow21BL0sl1vSVTPk.png", "bharatgenai": "https://cdn-avatars.huggingface.co/v1/production/uploads/67b462a1f4f414c2b3e2bc2f/EnVeNWEIeZ6yF6ueZ7E3Y.jpeg", - "PolarSeeker": "https://www.gravatar.com/avatar/55d9cc59db4e30206a307c186cc6d5bb?d=retro&size=100", - "espnet": "https://cdn-avatars.huggingface.co/v1/production/uploads/1625224006560-60d28bba010d938bba5c6ae9.png", - "HelpingAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/6612aedf09f16e7347dfa7e1/jHRLPBTlyykFwrd6-Mak_.png", - "openai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png", - "soundsgoodai": "https://www.gravatar.com/avatar/2e7e38eb40d5e4429d62544c73640cc6?d=retro&size=100", - "Edge0": "https://cdn-avatars.huggingface.co/v1/production/uploads/64361bcaf81a16e74367d2e2/D5QI700pnaujz5PeWE6MX.jpeg", - "JGOS-Model": "https://cdn-avatars.huggingface.co/v1/production/uploads/66e54edddba1e4fee4500a5a/mHGK5-lBrEy1xKZmRqtfc.png", - "speechbrain": "https://cdn-avatars.huggingface.co/v1/production/uploads/1663000279893-60243f18c1f3c79f98e4b382.png", - "Salesforce": "https://cdn-avatars.huggingface.co/v1/production/uploads/1602756670970-noauth.jpeg", - "openbmb": "https://cdn-avatars.huggingface.co/v1/production/uploads/1670387859384-633fe7784b362488336bbfad.png", - "Qwen": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg", - "CohereLabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png", + "Lightricks": "https://cdn-avatars.huggingface.co/v1/production/uploads/669524bcbcd81f395e8f60f6/0ynfqKEWMh_dn3h4ff1K5.png", + "crosbylegal": "https://cdn-avatars.huggingface.co/v1/production/uploads/6342f326aa45ed8ecf954c80/bjQGFQhNkm75Za3XOByzu.png", + "EleutherAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/1614054059123-603481bb60e3dd96631c9095.png", "Multilingual-Multimodal-NLP": "https://www.gravatar.com/avatar/cdabcf4c0ac6a92af4940fe0eb6924eb?d=retro&size=100", - "internlm": "https://cdn-avatars.huggingface.co/v1/production/uploads/6432683407bad11484a68457/Q3Y0dL79GcsnaBCGRMooZ.png", - "ACERobotics": "https://cdn-avatars.huggingface.co/v1/production/uploads/6a4a45de4ba0a921a91a548a/MSX_HJLXaBYKy2ZByYTnN.png", - "01-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6536187279f1de44b5e02d0f/-T8Xw0mX67_R73b7Re1y-.png", - "docling-project": "https://cdn-avatars.huggingface.co/v1/production/uploads/63c64dd877caf00391004e20/aWC70TyF2UhxyaUh1alpu.png", - "SPRINGLab": "https://cdn-avatars.huggingface.co/v1/production/uploads/65fd29f704a313d0597e01bb/BNz5HpwEo_DR9Et03MmEh.png", + "onnx-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/61b253b7ac5ecaae3d1efe0c/BpiYJ-m5mXPXfjkzEt6yZ.png", + "JetBrains": "https://cdn-avatars.huggingface.co/v1/production/uploads/6645d54b780d46f274dd4145/8RHS3MzGGBFWtH1-bynJ0.png", "openpangu": "https://cdn-avatars.huggingface.co/v1/production/uploads/66446e5f8c16ba43d3952eb8/_d3vpdB-0d6umBvgKND6m.png", - "opendatalab": "https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png", - "moonshine-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6509fc8d11afda55cae0b2e7/6tyQ-L7VxHMOSKIOff09A.png", - "numind": "https://cdn-avatars.huggingface.co/v1/production/uploads/649be8cf867d442094248a40/p-vHYU5a6a6AlAqj0D1P7.png", - "microsoft": "https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png", - "inclusionAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/662e1f9da266499277937d33/fyKuazRifqiaIO34xrhhm.jpeg", - "ibm-granite": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png", - "InternScience": "https://cdn-avatars.huggingface.co/v1/production/uploads/65f2a4198404ac0e4c0f175f/XIPU4aCPBogXSrj6NrfLk.png", - "mteb": "https://cdn-avatars.huggingface.co/v1/production/uploads/5ff5943752c26e9bc240bada/OrZxdlg8doDNO2TZ6Q58G.png", - "nex-agi": "https://cdn-avatars.huggingface.co/v1/production/uploads/65435cad429b80b14922ab8d/a_O9jT_daz_NXTfxtcw6S.png", - "Lightricks": "https://cdn-avatars.huggingface.co/v1/production/uploads/669524bcbcd81f395e8f60f6/0ynfqKEWMh_dn3h4ff1K5.png", + "mistral-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/HAdAzcs1CDB9OxgxT2W9K.png", + "PaddlePaddle": "https://cdn-avatars.huggingface.co/v1/production/uploads/1654942635336-5f3ff69679c1ba4c353d0c5a.png", + "zai-org": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png", + "abacusai": "https://cdn-avatars.huggingface.co/v1/production/uploads/63128dd099791aa61d180c72/dJ6uR23m09M-YEafBpmea.png", + "ByteDance-Seed": "https://cdn-avatars.huggingface.co/v1/production/uploads/6535c9e88bde2fae19b6fb25/flkDUqd_YEuFsjeNET3r-.png", "ornith-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68661bce022667cf9c7534fb/dwzGCqj9B7NGaJRO-NjjP.png", - "nvidia": "https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png", - "google": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/WtA3YYitedOr9n02eHfJe.png", - "facebook": "https://cdn-avatars.huggingface.co/v1/production/uploads/1592839207516-noauth.png", - "deepseek-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png", - "mindlab-research": "https://cdn-avatars.huggingface.co/v1/production/uploads/64303a4484f3ed1ce62a2c5a/0L3sMuvL2JGls3zUKOKYU.jpeg", "swiss-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/648211d39c44e3422ca7e4f3/gnfixzw9IqBziR6bzA6u8.png", - "jdopensource": "https://cdn-avatars.huggingface.co/v1/production/uploads/68c0e2ab44ea28a974e3074b/g-4gTubd16qUtwmGZ0n4h.png", - "XiaomiMiMo": "https://cdn-avatars.huggingface.co/v1/production/uploads/680cb7d1233834890a64acee/5w_4aLfF-7MAyaIPOV498.jpeg", - "HuggingFaceTB": "https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/e4VK7uW5sTeCYupD0s_ob.png", + "ByteDance": "https://cdn-avatars.huggingface.co/v1/production/uploads/6535c9e88bde2fae19b6fb25/0clr54wj5Ly-RkYU9OXPp.png", + "internlm": "https://cdn-avatars.huggingface.co/v1/production/uploads/6432683407bad11484a68457/Q3Y0dL79GcsnaBCGRMooZ.png", "tencent": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png", - "FINAL-Bench": "https://cdn-avatars.huggingface.co/v1/production/uploads/6905bc786cb49b1f11d32728/VZmuKH-liifeL2GCXlwka.jpeg", - "poolside": "https://cdn-avatars.huggingface.co/v1/production/uploads/699484cbe85a4b61cbc5ee0f/GpYWuz-CovEFgbPOW21dZ.png", - "JetBrains": "https://cdn-avatars.huggingface.co/v1/production/uploads/6645d54b780d46f274dd4145/8RHS3MzGGBFWtH1-bynJ0.png", - "mistralai": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png", - "KDLAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/63687f5246919b9619c181b2/YzQFwtOJHPswxma-nG-vy.png", - "meta-llama": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png", - "ai21labs": "https://cdn-avatars.huggingface.co/v1/production/uploads/67baf6e5489cb4dc98a4bff4/9Rkvk1VGhK1woxWvhqDyb.png", - "INCModel3": "https://www.gravatar.com/avatar/b95e8aeaa2dcab599634e2a79570d4aa?d=retro&size=100", "dots-studio": "https://cdn-avatars.huggingface.co/v1/production/uploads/683f0a13218449ec8f707047/K8V6vNs42cvpaTq_s6snK.png", - "PaddlePaddle": "https://cdn-avatars.huggingface.co/v1/production/uploads/1654942635336-5f3ff69679c1ba4c353d0c5a.png", - "moonshotai": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg", - "abacusai": "https://cdn-avatars.huggingface.co/v1/production/uploads/63128dd099791aa61d180c72/dJ6uR23m09M-YEafBpmea.png", - "lerobot": "https://cdn-avatars.huggingface.co/v1/production/uploads/631ce4b244503b72277fc89f/pcLUTLsvMQiR-ujlTgLYF.png", + "openai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png", + "moondream": "https://cdn-avatars.huggingface.co/v1/production/uploads/65df6605dba41b152100edf9/LEUWPRTize9N7dMShjcPC.png", "small-models-for-glam": "https://cdn-avatars.huggingface.co/v1/production/uploads/60107b385ac3e86b3ea4fc34/1nssJ2v1Ry-KlZcqhBdqD.jpeg", + "gnani": "https://cdn-avatars.huggingface.co/v1/production/uploads/63eb50dbd64e6436e22ba90a/TMj98qiLr9dUT4_oHFioD.jpeg", + "lerobot": "https://cdn-avatars.huggingface.co/v1/production/uploads/631ce4b244503b72277fc89f/pcLUTLsvMQiR-ujlTgLYF.png", + "ACERobotics": "https://cdn-avatars.huggingface.co/v1/production/uploads/6a4a45de4ba0a921a91a548a/MSX_HJLXaBYKy2ZByYTnN.png", + "TIGER-Lab": "https://cdn-avatars.huggingface.co/v1/production/uploads/6313a86154e6e5d9f0f94e04/Noi3Qq3RYz8Jdq6BaFteq.png", + "nex-agi": "https://cdn-avatars.huggingface.co/v1/production/uploads/65435cad429b80b14922ab8d/a_O9jT_daz_NXTfxtcw6S.png", + "inclusionAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/662e1f9da266499277937d33/fyKuazRifqiaIO34xrhhm.jpeg", + "mteb": "https://cdn-avatars.huggingface.co/v1/production/uploads/5ff5943752c26e9bc240bada/OrZxdlg8doDNO2TZ6Q58G.png", "baidu": "https://cdn-avatars.huggingface.co/v1/production/uploads/64f187a2cc1c03340ac30498/TYYUxK8xD1AxExFMWqbZD.png", + "meta-models": "https://cdn-avatars.huggingface.co/v1/production/uploads/64c115d1f661ace7c4022432/EbzfQisFJBEcKWDWLyV5O.png", + "docling-project": "https://cdn-avatars.huggingface.co/v1/production/uploads/63c64dd877caf00391004e20/aWC70TyF2UhxyaUh1alpu.png", + "01-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6536187279f1de44b5e02d0f/-T8Xw0mX67_R73b7Re1y-.png", + "nvidia": "https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png", + "distil-whisper": "https://cdn-avatars.huggingface.co/v1/production/uploads/61f91cf54a8e5a275b2b3e7c/cUNzV7MAYi8lo9LsCYixp.png", + "espnet": "https://cdn-avatars.huggingface.co/v1/production/uploads/1625224006560-60d28bba010d938bba5c6ae9.png", + "mistralai": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png", + "Qwen": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg", + "Surpem": "https://cdn-avatars.huggingface.co/v1/production/uploads/69625a973527f984b1d0cec1/0jGoHYar6rASTHnqLnEzr.png", + "ai21labs": "https://cdn-avatars.huggingface.co/v1/production/uploads/67baf6e5489cb4dc98a4bff4/9Rkvk1VGhK1woxWvhqDyb.png", + "shunyalabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/689dc0f0e770d8d76631f8a5/MwkDIbJ3xqS2Cb5MwexLR.jpeg", + "stepfun-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/644f7e6233ac8f46fa0b9e26/CmF2ocXhkr2UtHXgmwq7-.png", + "Salesforce": "https://cdn-avatars.huggingface.co/v1/production/uploads/1602756670970-noauth.jpeg", + "upstage": "https://cdn-avatars.huggingface.co/v1/production/uploads/649144feeb13c70f7671c603/bUxWC5jKltd-MyrrCNCv5.png", + "MuVeraAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/65ba8b772db90cb31145dbee/K8-0i5PExUW8ivebDyTo-.png", "GSAI-ML": "https://cdn-avatars.huggingface.co/v1/production/uploads/624f909eac5dd186b01ac3f5/6tfvx3XT5Sx6YDGl7KUAU.jpeg", - "robbyant": "https://cdn-avatars.huggingface.co/v1/production/uploads/67aeffda7330db26f93cd62f/ZTuImney4XzRmBHyUL47F.png", + "soundsgoodai": "https://www.gravatar.com/avatar/2e7e38eb40d5e4429d62544c73640cc6?d=retro&size=100", + "Edge0": "https://cdn-avatars.huggingface.co/v1/production/uploads/64361bcaf81a16e74367d2e2/D5QI700pnaujz5PeWE6MX.jpeg", "MiniMaxAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg", - "crosbylegal": "https://cdn-avatars.huggingface.co/v1/production/uploads/6342f326aa45ed8ecf954c80/bjQGFQhNkm75Za3XOByzu.png", - "lightonai": "https://cdn-avatars.huggingface.co/v1/production/uploads/1651597775471-62715572ab9243b5d40cbb1d.png", - "kyutai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6355a3c1805be5a8f30fea49/8xGdIOlfkopZfhbMitw_k.jpeg", - "ByteDance": "https://cdn-avatars.huggingface.co/v1/production/uploads/6535c9e88bde2fae19b6fb25/0clr54wj5Ly-RkYU9OXPp.png", - "meituan-longcat": "https://cdn-avatars.huggingface.co/v1/production/uploads/68a2a29ab9d4c5698e02c747/CDCAx7X7rXDt7xjI-DoxG.png", - "abr-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68e56cb442da034c65305b1b/DYHvx48l1-zt0G5VRj95j.png", + "moonshine-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6509fc8d11afda55cae0b2e7/6tyQ-L7VxHMOSKIOff09A.png", + "ibm-granite": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png", + "deepseek-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png", "XingChen-AGI": "https://cdn-avatars.huggingface.co/v1/production/uploads/64368160eef1f55654ab21dc/HGow19-5fgUcp_IEMZoXG.png", - "thinkingmachines": "https://cdn-avatars.huggingface.co/v1/production/uploads/680a76de1b8d08640089fab0/r60-JyW_pv4llgjEyDYj9.png", + "InternScience": "https://cdn-avatars.huggingface.co/v1/production/uploads/65f2a4198404ac0e4c0f175f/XIPU4aCPBogXSrj6NrfLk.png", + "FINAL-Bench": "https://cdn-avatars.huggingface.co/v1/production/uploads/6905bc786cb49b1f11d32728/VZmuKH-liifeL2GCXlwka.jpeg", + "PolarSeeker": "https://www.gravatar.com/avatar/55d9cc59db4e30206a307c186cc6d5bb?d=retro&size=100", + "meta-llama": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png", + "HuggingFaceTB": "https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/e4VK7uW5sTeCYupD0s_ob.png", "inspatio": "https://www.gravatar.com/avatar/0e9900671188e39a6c9589e882d99e9c?d=retro&size=100", - "Surpem": "https://cdn-avatars.huggingface.co/v1/production/uploads/69625a973527f984b1d0cec1/0jGoHYar6rASTHnqLnEzr.png", - "upstage": "https://cdn-avatars.huggingface.co/v1/production/uploads/649144feeb13c70f7671c603/bUxWC5jKltd-MyrrCNCv5.png", - "stepfun-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/644f7e6233ac8f46fa0b9e26/CmF2ocXhkr2UtHXgmwq7-.png", - "shunyalabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/689dc0f0e770d8d76631f8a5/MwkDIbJ3xqS2Cb5MwexLR.jpeg", - "mistral-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/HAdAzcs1CDB9OxgxT2W9K.png", - "moondream": "https://cdn-avatars.huggingface.co/v1/production/uploads/65df6605dba41b152100edf9/LEUWPRTize9N7dMShjcPC.png", - "skt": "https://cdn-avatars.huggingface.co/v1/production/uploads/6311a3f4d5a165db5d1d6862/XUPnKE9YqJcgORZoVOXMR.jpeg", - "KDEGroup": "https://cdn-avatars.huggingface.co/v1/production/uploads/688dc279b2d5ebe029e8aafe/GZis_Qxofgb67RkJsllJ6.png", - "OpenMOSS-Team": "https://cdn-avatars.huggingface.co/v1/production/uploads/61457b8deff2c9fdb4de4988/N5b9663zQ4uq5_OTNlnmw.png", + "speechbrain": "https://cdn-avatars.huggingface.co/v1/production/uploads/1663000279893-60243f18c1f3c79f98e4b382.png", + "google": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/WtA3YYitedOr9n02eHfJe.png", + "poolside": "https://cdn-avatars.huggingface.co/v1/production/uploads/699484cbe85a4b61cbc5ee0f/GpYWuz-CovEFgbPOW21dZ.png", "jinaai": "https://cdn-avatars.huggingface.co/v1/production/uploads/603763514de52ff951d89793/wD54VbAHHyHop3uYlJKl4.png", - "ByteDance-Seed": "https://cdn-avatars.huggingface.co/v1/production/uploads/6535c9e88bde2fae19b6fb25/flkDUqd_YEuFsjeNET3r-.png", - "onnx-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/61b253b7ac5ecaae3d1efe0c/BpiYJ-m5mXPXfjkzEt6yZ.png", - "MuVeraAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/65ba8b772db90cb31145dbee/K8-0i5PExUW8ivebDyTo-.png", + "JGOS-Model": "https://cdn-avatars.huggingface.co/v1/production/uploads/66e54edddba1e4fee4500a5a/mHGK5-lBrEy1xKZmRqtfc.png", + "KDLAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/63687f5246919b9619c181b2/YzQFwtOJHPswxma-nG-vy.png", + "microsoft": "https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png", + "ATH-MaaS": "https://cdn-avatars.huggingface.co/v1/production/uploads/666a9d46a638e57bb7907929/CRc-9MCuH2q9hjTScyTPE.png", + "openbmb": "https://cdn-avatars.huggingface.co/v1/production/uploads/1670387859384-633fe7784b362488336bbfad.png", + "OpenMOSS-Team": "https://cdn-avatars.huggingface.co/v1/production/uploads/61457b8deff2c9fdb4de4988/N5b9663zQ4uq5_OTNlnmw.png", + "abr-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68e56cb442da034c65305b1b/DYHvx48l1-zt0G5VRj95j.png", "infly": "https://cdn-avatars.huggingface.co/v1/production/uploads/63ed9862679c2cc40abb55d2/0n6g0jngiKkRjaEoAvPmM.png", - "zai-org": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png", - "meta-models": "https://cdn-avatars.huggingface.co/v1/production/uploads/64c115d1f661ace7c4022432/EbzfQisFJBEcKWDWLyV5O.png", - "TIGER-Lab": "https://cdn-avatars.huggingface.co/v1/production/uploads/6313a86154e6e5d9f0f94e04/Noi3Qq3RYz8Jdq6BaFteq.png", - "datalab-to": "https://cdn-avatars.huggingface.co/v1/production/uploads/67ab6afe315e622f597bf9e8/YOgg0gVYVXZC1PDIHFTWK.png" + "XiaomiMiMo": "https://cdn-avatars.huggingface.co/v1/production/uploads/680cb7d1233834890a64acee/5w_4aLfF-7MAyaIPOV498.jpeg", + "meituan-longcat": "https://cdn-avatars.huggingface.co/v1/production/uploads/68a2a29ab9d4c5698e02c747/CDCAx7X7rXDt7xjI-DoxG.png", + "xlangai": "https://cdn-avatars.huggingface.co/v1/production/uploads/628f6e5ab90dde28ef57d293/PHIYPvE_tCM94SgoUzd7l.jpeg", + "moonshotai": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg", + "LGAI-EXAONE": "https://cdn-avatars.huggingface.co/v1/production/uploads/66a899a72f11aaf66001a8dc/UfdrP3GMo9pNT62BaMnhw.png", + "SPRINGLab": "https://cdn-avatars.huggingface.co/v1/production/uploads/65fd29f704a313d0597e01bb/BNz5HpwEo_DR9Et03MmEh.png", + "mindlab-research": "https://cdn-avatars.huggingface.co/v1/production/uploads/64303a4484f3ed1ce62a2c5a/0L3sMuvL2JGls3zUKOKYU.jpeg", + "thinkingmachines": "https://cdn-avatars.huggingface.co/v1/production/uploads/680a76de1b8d08640089fab0/r60-JyW_pv4llgjEyDYj9.png", + "lightonai": "https://cdn-avatars.huggingface.co/v1/production/uploads/1651597775471-62715572ab9243b5d40cbb1d.png", + "INCModel3": "https://www.gravatar.com/avatar/b95e8aeaa2dcab599634e2a79570d4aa?d=retro&size=100", + "HelpingAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/6612aedf09f16e7347dfa7e1/jHRLPBTlyykFwrd6-Mak_.png", + "skt": "https://cdn-avatars.huggingface.co/v1/production/uploads/6311a3f4d5a165db5d1d6862/XUPnKE9YqJcgORZoVOXMR.jpeg", + "opendatalab": "https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png", + "datalab-to": "https://cdn-avatars.huggingface.co/v1/production/uploads/67ab6afe315e622f597bf9e8/YOgg0gVYVXZC1PDIHFTWK.png", + "KDEGroup": "https://cdn-avatars.huggingface.co/v1/production/uploads/688dc279b2d5ebe029e8aafe/GZis_Qxofgb67RkJsllJ6.png" }, "colors": { "01-ai": "#6366f1", @@ -7095,5 +7109,5 @@ "xlangai": "#dc2626", "zai-org": "#0284c7" }, - "generated_at": "2026-10-02T08:00:44.364198+00:00" + "generated_at": "2026-10-02T20:00:36.710240+00:00" } \ No newline at end of file