Spaces:
Running
Running
| { | |
| "benchmarks": { | |
| "deep_swe": { | |
| "name": "DeepSWE", | |
| "dataset": "datacurve/deep-swe", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "moonshotai/Kimi-K3", | |
| "short_name": "Kimi-K3", | |
| "provider": "moonshotai", | |
| "score": 67.5, | |
| "date": "2026-06-13" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash-0731", | |
| "short_name": "DeepSeek-V4-Flash-0731", | |
| "provider": "deepseek-ai", | |
| "score": 54.4, | |
| "date": "2026-07-31" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 46.2, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-S-2.1", | |
| "short_name": "Laguna-S-2.1", | |
| "provider": "poolside", | |
| "score": 40.4, | |
| "date": "2026-07-13" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3", | |
| "short_name": "Hy3", | |
| "provider": "tencent", | |
| "score": 28.0, | |
| "date": "2026-07-02" | |
| } | |
| ] | |
| }, | |
| "sweVerified": { | |
| "name": "SWE-bench Verified", | |
| "dataset": "SWE-bench/SWE-bench_Verified", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-397B", | |
| "short_name": "Ornith-1.0-397B", | |
| "provider": "deepreinforce-ai", | |
| "score": 82.4, | |
| "date": "2026-06-23" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 80.6, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 80.5, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 80.2, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "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": 79.0, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 78.9, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "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": 77.8, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "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": "thinkingmachines/Inkling", | |
| "short_name": "Inkling", | |
| "provider": "thinkingmachines", | |
| "score": 77.6, | |
| "date": "2026-07-14" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 77.2, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 76.4, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 75.8, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-35B", | |
| "short_name": "Ornith-1.0-35B", | |
| "provider": "deepreinforce-ai", | |
| "score": 75.6, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "Multilingual-Multimodal-NLP/IndustrialCoder", | |
| "short_name": "IndustrialCoder", | |
| "provider": "Multilingual-Multimodal-NLP", | |
| "score": 74.8, | |
| "date": "2026-03-13" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-M.1", | |
| "short_name": "Laguna-M.1", | |
| "provider": "poolside", | |
| "score": 74.6, | |
| "date": "2026-06-15" | |
| }, | |
| { | |
| "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": "tencent/Hy3-preview", | |
| "short_name": "Hy3-preview", | |
| "provider": "tencent", | |
| "score": 74.4, | |
| "date": "2026-04-13" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 74.0, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ring-2.6-1T", | |
| "short_name": "Ring-2.6-1T", | |
| "provider": "inclusionAI", | |
| "score": 74.0, | |
| "date": "2026-05-14" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 73.8, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 73.4, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 72.4, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ling-2.6-1T", | |
| "short_name": "Ling-2.6-1T", | |
| "provider": "inclusionAI", | |
| "score": 72.2, | |
| "date": "2026-04-29" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 72.0, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "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": "moonshotai/Kimi-K2-Thinking", | |
| "short_name": "Kimi-K2-Thinking", | |
| "provider": "moonshotai", | |
| "score": 71.3, | |
| "date": "2025-11-04" | |
| }, | |
| { | |
| "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": 70.8, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-Next", | |
| "short_name": "Qwen3-Coder-Next", | |
| "provider": "Qwen", | |
| "score": 70.6, | |
| "date": "2026-01-30" | |
| }, | |
| { | |
| "model_id": "upstage/Solar-Open2-250B", | |
| "short_name": "Solar-Open2-250B", | |
| "provider": "upstage", | |
| "score": 70.4, | |
| "date": "2026-07-22" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "poolside", | |
| "score": 69.9, | |
| "date": "2026-04-23" | |
| }, | |
| { | |
| "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": "MiniMaxAI/MiniMax-M2", | |
| "short_name": "MiniMax-M2", | |
| "provider": "MiniMaxAI", | |
| "score": 69.4, | |
| "date": "2025-10-22" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-9B", | |
| "short_name": "Ornith-1.0-9B", | |
| "provider": "deepreinforce-ai", | |
| "score": 69.4, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "MuVeraAI/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "MuVeraAI", | |
| "score": 68.2, | |
| "date": "2026-04-28" | |
| }, | |
| { | |
| "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": "internlm/Intern-S2-Preview", | |
| "short_name": "Intern-S2-Preview", | |
| "provider": "internlm", | |
| "score": 64.0, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "openpangu/openPangu-2.0-Flash", | |
| "short_name": "openPangu-2.0-Flash", | |
| "provider": "openpangu", | |
| "score": 63.1, | |
| "date": "2026-06-30" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 62.4, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ling-2.6-flash", | |
| "short_name": "Ling-2.6-flash", | |
| "provider": "inclusionAI", | |
| "score": 61.2, | |
| "date": "2026-04-28" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 60.7, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "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": "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": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 60.47, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 60.47, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 60.47, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "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": "facebook/cwm", | |
| "short_name": "cwm", | |
| "provider": "facebook", | |
| "score": 53.9, | |
| "date": "2025-08-25" | |
| } | |
| ] | |
| }, | |
| "open_asr_leaderboard": { | |
| "name": "open-asr-leaderboard", | |
| "dataset": "hf-audio/open-asr-leaderboard", | |
| "lower_is_better": true, | |
| "models": [ | |
| { | |
| "model_id": "Audio8/ARK-ASR-3B", | |
| "short_name": "ARK-ASR-3B", | |
| "provider": "Audio8", | |
| "score": 4.76, | |
| "date": "2026-06-22" | |
| }, | |
| { | |
| "model_id": "OpenMOSS-Team/MOSS-Transcribe-preview-2B", | |
| "short_name": "MOSS-Transcribe-preview-2B", | |
| "provider": "OpenMOSS-Team", | |
| "score": 4.87, | |
| "date": "2026-06-26" | |
| }, | |
| { | |
| "model_id": "OpenMOSS-Team/MOSS-Transcribe-Diarize", | |
| "short_name": "MOSS-Transcribe-Diarize", | |
| "provider": "OpenMOSS-Team", | |
| "score": 5.17, | |
| "date": "2026-05-19" | |
| }, | |
| { | |
| "model_id": "CohereLabs/cohere-transcribe-03-2026", | |
| "short_name": "cohere-transcribe-03-2026", | |
| "provider": "CohereLabs", | |
| "score": 5.42, | |
| "date": "2026-03-24" | |
| }, | |
| { | |
| "model_id": "Audio8/ARK-ASR-0.6B", | |
| "short_name": "ARK-ASR-0.6B", | |
| "provider": "Audio8", | |
| "score": 5.53, | |
| "date": "2026-05-25" | |
| }, | |
| { | |
| "model_id": "soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M", | |
| "short_name": "Zipformer-cr-ctc-transducer-XL-290M", | |
| "provider": "soundsgoodai", | |
| "score": 5.56, | |
| "date": "2026-07-09" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-ASR-1.7B", | |
| "short_name": "Qwen3-ASR-1.7B", | |
| "provider": "Qwen", | |
| "score": 5.76, | |
| "date": "2026-01-28" | |
| }, | |
| { | |
| "model_id": "microsoft/Phi-4-multimodal-instruct", | |
| "short_name": "Phi-4-multimodal-instruct", | |
| "provider": "microsoft", | |
| "score": 6.02, | |
| "date": "2025-02-24" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-tdt-0.6b-v2", | |
| "short_name": "parakeet-tdt-0.6b-v2", | |
| "provider": "nvidia", | |
| "score": 6.05, | |
| "date": "2025-04-15" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-tdt-0.6b-v3", | |
| "short_name": "parakeet-tdt-0.6b-v3", | |
| "provider": "nvidia", | |
| "score": 6.32, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "nvidia/canary-1b-flash", | |
| "short_name": "canary-1b-flash", | |
| "provider": "nvidia", | |
| "score": 6.35, | |
| "date": "2025-03-07" | |
| }, | |
| { | |
| "model_id": "kyutai/stt-2.6b-en", | |
| "short_name": "stt-2.6b-en", | |
| "provider": "kyutai", | |
| "score": 6.4, | |
| "date": "2025-06-06" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-ASR-0.6B", | |
| "short_name": "Qwen3-ASR-0.6B", | |
| "provider": "Qwen", | |
| "score": 6.42, | |
| "date": "2026-01-28" | |
| }, | |
| { | |
| "model_id": "nvidia/canary-1b", | |
| "short_name": "canary-1b", | |
| "provider": "nvidia", | |
| "score": 6.5, | |
| "date": "2024-02-07" | |
| }, | |
| { | |
| "model_id": "UsefulSensors/moonshine-streaming-medium", | |
| "short_name": "moonshine-streaming-medium", | |
| "provider": "UsefulSensors", | |
| "score": 6.66, | |
| "date": "2026-01-06" | |
| }, | |
| { | |
| "model_id": "soundsgoodai/Zipformer-transducer-XL-290M", | |
| "short_name": "Zipformer-transducer-XL-290M", | |
| "provider": "soundsgoodai", | |
| "score": 6.71, | |
| "date": "2026-05-12" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-tdt-1.1b", | |
| "short_name": "parakeet-tdt-1.1b", | |
| "provider": "nvidia", | |
| "score": 7.01, | |
| "date": "2024-01-25" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-ASR-Nano-2512", | |
| "short_name": "GLM-ASR-Nano-2512", | |
| "provider": "zai-org", | |
| "score": 7.03, | |
| "date": "2025-12-09" | |
| }, | |
| { | |
| "model_id": "Audio8/Audio8-ASR-0.1B", | |
| "short_name": "Audio8-ASR-0.1B", | |
| "provider": "Audio8", | |
| "score": 7.03, | |
| "date": "2026-07-10" | |
| }, | |
| { | |
| "model_id": "mistralai/Voxtral-Mini-3B-2507", | |
| "short_name": "Voxtral-Mini-3B-2507", | |
| "provider": "mistralai", | |
| "score": 7.05, | |
| "date": "2025-07-01" | |
| }, | |
| { | |
| "model_id": "nvidia/canary-180m-flash", | |
| "short_name": "canary-180m-flash", | |
| "provider": "nvidia", | |
| "score": 7.12, | |
| "date": "2025-03-11" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-rnnt-1.1b", | |
| "short_name": "parakeet-rnnt-1.1b", | |
| "provider": "nvidia", | |
| "score": 7.12, | |
| "date": "2023-12-27" | |
| }, | |
| { | |
| "model_id": "nvidia/canary-1b-v2", | |
| "short_name": "canary-1b-v2", | |
| "provider": "nvidia", | |
| "score": 7.15, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "distil-whisper/distil-large-v3.5", | |
| "short_name": "distil-large-v3.5", | |
| "provider": "distil-whisper", | |
| "score": 7.21, | |
| "date": "2024-12-05" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-ctc-1.1b", | |
| "short_name": "parakeet-ctc-1.1b", | |
| "provider": "nvidia", | |
| "score": 7.4, | |
| "date": "2023-12-28" | |
| }, | |
| { | |
| "model_id": "espnet/owsm_ctc_v4_1B", | |
| "short_name": "owsm_ctc_v4_1B", | |
| "provider": "espnet", | |
| "score": 7.42, | |
| "date": "2025-01-16" | |
| }, | |
| { | |
| "model_id": "openai/whisper-large-v3", | |
| "short_name": "whisper-large-v3", | |
| "provider": "openai", | |
| "score": 7.44, | |
| "date": "2023-11-07" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-tdt_ctc-110m", | |
| "short_name": "parakeet-tdt_ctc-110m", | |
| "provider": "nvidia", | |
| "score": 7.49, | |
| "date": "2024-09-17" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-rnnt-0.6b", | |
| "short_name": "parakeet-rnnt-0.6b", | |
| "provider": "nvidia", | |
| "score": 7.5, | |
| "date": "2023-12-28" | |
| }, | |
| { | |
| "model_id": "nvidia/parakeet-ctc-0.6b", | |
| "short_name": "parakeet-ctc-0.6b", | |
| "provider": "nvidia", | |
| "score": 7.69, | |
| "date": "2023-12-28" | |
| }, | |
| { | |
| "model_id": "microsoft/VibeVoice-ASR-HF", | |
| "short_name": "VibeVoice-ASR-HF", | |
| "provider": "microsoft", | |
| "score": 7.77, | |
| "date": "2026-03-02" | |
| }, | |
| { | |
| "model_id": "openai/whisper-large-v2", | |
| "short_name": "whisper-large-v2", | |
| "provider": "openai", | |
| "score": 7.83, | |
| "date": "2022-12-05" | |
| }, | |
| { | |
| "model_id": "UsefulSensors/moonshine-streaming-small", | |
| "short_name": "moonshine-streaming-small", | |
| "provider": "UsefulSensors", | |
| "score": 7.84, | |
| "date": "2026-01-06" | |
| }, | |
| { | |
| "model_id": "openai/whisper-large", | |
| "short_name": "whisper-large", | |
| "provider": "openai", | |
| "score": 7.94, | |
| "date": "2022-09-26" | |
| }, | |
| { | |
| "model_id": "openai/whisper-medium.en", | |
| "short_name": "whisper-medium.en", | |
| "provider": "openai", | |
| "score": 8.09, | |
| "date": "2022-09-26" | |
| }, | |
| { | |
| "model_id": "espnet/owsm_ctc_v3.1_1B", | |
| "short_name": "owsm_ctc_v3.1_1B", | |
| "provider": "espnet", | |
| "score": 8.12, | |
| "date": "2024-02-23" | |
| }, | |
| { | |
| "model_id": "nvidia/stt_en_conformer_ctc_large", | |
| "short_name": "stt_en_conformer_ctc_large", | |
| "provider": "nvidia", | |
| "score": 8.32, | |
| "date": "2022-04-09" | |
| }, | |
| { | |
| "model_id": "speechbrain/asr-conformer-loquacious", | |
| "short_name": "asr-conformer-loquacious", | |
| "provider": "speechbrain", | |
| "score": 8.48, | |
| "date": "2025-02-06" | |
| }, | |
| { | |
| "model_id": "openai/whisper-small.en", | |
| "short_name": "whisper-small.en", | |
| "provider": "openai", | |
| "score": 8.59, | |
| "date": "2022-09-26" | |
| }, | |
| { | |
| "model_id": "abr-ai/niagara-38m-batch.en", | |
| "short_name": "niagara-38m-batch.en", | |
| "provider": "abr-ai", | |
| "score": 8.91, | |
| "date": "2026-02-19" | |
| }, | |
| { | |
| "model_id": "nvidia/stt_en_fastconformer_ctc_large", | |
| "short_name": "stt_en_fastconformer_ctc_large", | |
| "provider": "nvidia", | |
| "score": 8.96, | |
| "date": "2023-06-08" | |
| }, | |
| { | |
| "model_id": "nvidia/stt_en_fastconformer_transducer_large", | |
| "short_name": "stt_en_fastconformer_transducer_large", | |
| "provider": "nvidia", | |
| "score": 9.06, | |
| "date": "2023-06-08" | |
| }, | |
| { | |
| "model_id": "UsefulSensors/moonshine-base", | |
| "short_name": "moonshine-base", | |
| "provider": "UsefulSensors", | |
| "score": 9.99, | |
| "date": "2024-11-02" | |
| }, | |
| { | |
| "model_id": "openai/whisper-base.en", | |
| "short_name": "whisper-base.en", | |
| "provider": "openai", | |
| "score": 10.32, | |
| "date": "2022-09-26" | |
| }, | |
| { | |
| "model_id": "abr-ai/niagara-19m-batch.en", | |
| "short_name": "niagara-19m-batch.en", | |
| "provider": "abr-ai", | |
| "score": 10.47, | |
| "date": "2025-11-13" | |
| }, | |
| { | |
| "model_id": "nvidia/stt_en_conformer_ctc_small", | |
| "short_name": "stt_en_conformer_ctc_small", | |
| "provider": "nvidia", | |
| "score": 11.16, | |
| "date": "2023-06-12" | |
| }, | |
| { | |
| "model_id": "UsefulSensors/moonshine-streaming-tiny", | |
| "short_name": "moonshine-streaming-tiny", | |
| "provider": "UsefulSensors", | |
| "score": 12.0, | |
| "date": "2026-01-06" | |
| }, | |
| { | |
| "model_id": "UsefulSensors/moonshine-tiny", | |
| "short_name": "moonshine-tiny", | |
| "provider": "UsefulSensors", | |
| "score": 12.65, | |
| "date": "2024-10-30" | |
| }, | |
| { | |
| "model_id": "openai/whisper-tiny.en", | |
| "short_name": "whisper-tiny.en", | |
| "provider": "openai", | |
| "score": 12.81, | |
| "date": "2022-09-26" | |
| }, | |
| { | |
| "model_id": "speechbrain/asr-wav2vec2-librispeech", | |
| "short_name": "asr-wav2vec2-librispeech", | |
| "provider": "speechbrain", | |
| "score": 14.35, | |
| "date": "2022-06-05" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-large-960h-lv60-self", | |
| "short_name": "wav2vec2-large-960h-lv60-self", | |
| "provider": "facebook", | |
| "score": 21.27, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/mms-1b-all", | |
| "short_name": "mms-1b-all", | |
| "provider": "facebook", | |
| "score": 22.54, | |
| "date": "2023-05-27" | |
| }, | |
| { | |
| "model_id": "facebook/hubert-xlarge-ls960-ft", | |
| "short_name": "hubert-xlarge-ls960-ft", | |
| "provider": "facebook", | |
| "score": 22.55, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/hubert-large-ls960-ft", | |
| "short_name": "hubert-large-ls960-ft", | |
| "provider": "facebook", | |
| "score": 22.69, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-large-robust-ft-libri-960h", | |
| "short_name": "wav2vec2-large-robust-ft-libri-960h", | |
| "provider": "facebook", | |
| "score": 22.93, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/data2vec-audio-large-960h", | |
| "short_name": "data2vec-audio-large-960h", | |
| "provider": "facebook", | |
| "score": 23.21, | |
| "date": "2022-04-02" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-conformer-rope-large-960h-ft", | |
| "short_name": "wav2vec2-conformer-rope-large-960h-ft", | |
| "provider": "facebook", | |
| "score": 23.28, | |
| "date": "2022-04-18" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-conformer-rel-pos-large-960h-ft", | |
| "short_name": "wav2vec2-conformer-rel-pos-large-960h-ft", | |
| "provider": "facebook", | |
| "score": 23.29, | |
| "date": "2022-04-18" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-large-960h", | |
| "short_name": "wav2vec2-large-960h", | |
| "provider": "facebook", | |
| "score": 26.77, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/data2vec-audio-base-960h", | |
| "short_name": "data2vec-audio-base-960h", | |
| "provider": "facebook", | |
| "score": 28.3, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/wav2vec2-base-960h", | |
| "short_name": "wav2vec2-base-960h", | |
| "provider": "facebook", | |
| "score": 29.4, | |
| "date": "2022-03-02" | |
| }, | |
| { | |
| "model_id": "facebook/mms-1b-fl102", | |
| "short_name": "mms-1b-fl102", | |
| "provider": "facebook", | |
| "score": 39.8, | |
| "date": "2023-05-27" | |
| } | |
| ] | |
| }, | |
| "gsm8k": { | |
| "name": "Grade School Math 8K", | |
| "dataset": "openai/gsm8k", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 99.6, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "meta-llama/Llama-3.1-405B", | |
| "short_name": "Llama-3.1-405B", | |
| "provider": "meta-llama", | |
| "score": 96.8, | |
| "date": "2024-07-16" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-30b", | |
| "short_name": "granite-4.1-30b", | |
| "provider": "ibm-granite", | |
| "score": 94.16, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "meta-llama/Llama-3.2-90B-Vision-Instruct", | |
| "short_name": "Llama-3.2-90B-Vision-Instruct", | |
| "provider": "meta-llama", | |
| "score": 93.1, | |
| "date": "2024-09-19" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 92.6, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-8b", | |
| "short_name": "granite-4.1-8b", | |
| "provider": "ibm-granite", | |
| "score": 92.49, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "microsoft/Phi-3-medium-4k-instruct", | |
| "short_name": "Phi-3-medium-4k-instruct", | |
| "provider": "microsoft", | |
| "score": 91.0, | |
| "date": "2024-05-07" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2-72B", | |
| "short_name": "Qwen2-72B", | |
| "provider": "Qwen", | |
| "score": 89.5, | |
| "date": "2024-05-22" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V3", | |
| "short_name": "DeepSeek-V3", | |
| "provider": "deepseek-ai", | |
| "score": 89.3, | |
| "date": "2024-12-25" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-3b", | |
| "short_name": "granite-4.1-3b", | |
| "provider": "ibm-granite", | |
| "score": 86.88, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "microsoft/Phi-3.5-mini-instruct", | |
| "short_name": "Phi-3.5-mini-instruct", | |
| "provider": "microsoft", | |
| "score": 86.2, | |
| "date": "2024-08-16" | |
| }, | |
| { | |
| "model_id": "internlm/internlm2_5-7b-chat", | |
| "short_name": "internlm2_5-7b-chat", | |
| "provider": "internlm", | |
| "score": 86.0, | |
| "date": "2024-06-27" | |
| }, | |
| { | |
| "model_id": "microsoft/Phi-3-mini-4k-instruct", | |
| "short_name": "Phi-3-mini-4k-instruct", | |
| "provider": "microsoft", | |
| "score": 85.7, | |
| "date": "2024-04-22" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Base-Pretrain", | |
| "short_name": "Mellum2-12B-A2.5B-Base-Pretrain", | |
| "provider": "JetBrains", | |
| "score": 81.73, | |
| "date": "2026-04-07" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Base", | |
| "short_name": "Mellum2-12B-A2.5B-Base", | |
| "provider": "JetBrains", | |
| "score": 81.73, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2-7B", | |
| "short_name": "Qwen2-7B", | |
| "provider": "Qwen", | |
| "score": 79.9, | |
| "date": "2024-06-04" | |
| }, | |
| { | |
| "model_id": "internlm/internlm2-chat-20b", | |
| "short_name": "internlm2-chat-20b", | |
| "provider": "internlm", | |
| "score": 79.6, | |
| "date": "2024-01-10" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V2", | |
| "short_name": "DeepSeek-V2", | |
| "provider": "deepseek-ai", | |
| "score": 79.2, | |
| "date": "2024-04-22" | |
| } | |
| ] | |
| }, | |
| "hle": { | |
| "name": "HLE", | |
| "dataset": "cais/hle", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "moonshotai/Kimi-K3", | |
| "short_name": "Kimi-K3", | |
| "provider": "moonshotai", | |
| "score": 56.0, | |
| "date": "2026-06-13" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 54.7, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 54.0, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3", | |
| "short_name": "Hy3", | |
| "provider": "tencent", | |
| "score": 53.2, | |
| "date": "2026-07-02" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 52.3, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 50.4, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 50.2, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 48.5, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 48.3, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.7-Flash", | |
| "short_name": "Step-3.7-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 48.1, | |
| "date": "2026-05-23" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 48.0, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "InternScience/Agents-A1", | |
| "short_name": "Agents-A1", | |
| "provider": "InternScience", | |
| "score": 47.6, | |
| "date": "2026-06-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 47.5, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling", | |
| "short_name": "Inkling", | |
| "provider": "thinkingmachines", | |
| "score": 46.0, | |
| "date": "2026-07-14" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Thinking", | |
| "short_name": "Kimi-K2-Thinking", | |
| "provider": "moonshotai", | |
| "score": 44.9, | |
| "date": "2025-11-04" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 42.8, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 37.7, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", | |
| "provider": "nvidia", | |
| "score": 37.4, | |
| "date": "2026-06-03" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", | |
| "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", | |
| "provider": "nvidia", | |
| "score": 37.4, | |
| "date": "2026-06-03" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 34.8, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "PolarSeeker/OpenSeeker-v2-30B-SFT", | |
| "short_name": "OpenSeeker-v2-30B-SFT", | |
| "provider": "PolarSeeker", | |
| "score": 34.6, | |
| "date": "2026-05-05" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling-Small", | |
| "short_name": "Inkling-Small", | |
| "provider": "thinkingmachines", | |
| "score": 31.6, | |
| "date": "2026-07-27" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3-preview", | |
| "short_name": "Hy3-preview", | |
| "provider": "tencent", | |
| "score": 30.0, | |
| "date": "2026-04-13" | |
| }, | |
| { | |
| "model_id": "upstage/Solar-Open2-250B", | |
| "short_name": "Solar-Open2-250B", | |
| "provider": "upstage", | |
| "score": 28.8, | |
| "date": "2026-07-22" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K2", | |
| "short_name": "A.X-K2", | |
| "provider": "skt", | |
| "score": 27.8, | |
| "date": "2026-07-28" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 24.0, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 23.1, | |
| "date": "2026-02-01" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 22.82, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "RedHatAI", | |
| "score": 22.82, | |
| "date": "2026-03-26" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 22.82, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 22.82, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 22.82, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 22.2, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2-Flash", | |
| "short_name": "MiMo-V2-Flash", | |
| "provider": "XiaomiMiMo", | |
| "score": 22.1, | |
| "date": "2025-12-16" | |
| }, | |
| { | |
| "model_id": "internlm/Intern-S2-Preview", | |
| "short_name": "Intern-S2-Preview", | |
| "provider": "internlm", | |
| "score": 21.94, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 21.4, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 19.4, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 19.0, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 17.3, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7-Flash", | |
| "short_name": "GLM-4.7-Flash", | |
| "provider": "zai-org", | |
| "score": 14.4, | |
| "date": "2026-01-19" | |
| }, | |
| { | |
| "model_id": "LGAI-EXAONE/K-EXAONE-236B-A23B", | |
| "short_name": "K-EXAONE-236B-A23B", | |
| "provider": "LGAI-EXAONE", | |
| "score": 13.6, | |
| "date": "2025-12-26" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2", | |
| "short_name": "MiniMax-M2", | |
| "provider": "MiniMaxAI", | |
| "score": 12.5, | |
| "date": "2025-10-22" | |
| }, | |
| { | |
| "model_id": "HelpingAI/Dhanishtha-2.0-0126", | |
| "short_name": "Dhanishtha-2.0-0126", | |
| "provider": "HelpingAI", | |
| "score": 9.92, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K1", | |
| "short_name": "A.X-K1", | |
| "provider": "skt", | |
| "score": 8.6, | |
| "date": "2025-12-29" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.5", | |
| "short_name": "GLM-4.5", | |
| "provider": "zai-org", | |
| "score": 8.32, | |
| "date": "2025-07-20" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.5-Air", | |
| "short_name": "GLM-4.5-Air", | |
| "provider": "zai-org", | |
| "score": 8.12, | |
| "date": "2025-07-20" | |
| } | |
| ] | |
| }, | |
| "swePro": { | |
| "name": "SWE-bench Pro", | |
| "dataset": "ScaleAI/SWE-bench_Pro", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-397B", | |
| "short_name": "Ornith-1.0-397B", | |
| "provider": "deepreinforce-ai", | |
| "score": 62.2, | |
| "date": "2026-06-23" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 62.1, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-S-2.1", | |
| "short_name": "Laguna-S-2.1", | |
| "provider": "poolside", | |
| "score": 59.4, | |
| "date": "2026-07-13" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 59.0, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 58.6, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 58.4, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3", | |
| "short_name": "Hy3", | |
| "provider": "tencent", | |
| "score": 57.9, | |
| "date": "2026-07-02" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 57.2, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.7-Flash", | |
| "short_name": "Step-3.7-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 56.3, | |
| "date": "2026-05-23" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.7", | |
| "short_name": "MiniMax-M2.7", | |
| "provider": "MiniMaxAI", | |
| "score": 56.2, | |
| "date": "2026-04-09" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5", | |
| "short_name": "MiMo-V2.5", | |
| "provider": "XiaomiMiMo", | |
| "score": 56.1, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling-Small", | |
| "short_name": "Inkling-Small", | |
| "provider": "thinkingmachines", | |
| "score": 55.9, | |
| "date": "2026-07-27" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 55.4, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 55.4, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling", | |
| "short_name": "Inkling", | |
| "provider": "thinkingmachines", | |
| "score": 54.3, | |
| "date": "2026-07-14" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 53.5, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 50.7, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-35B", | |
| "short_name": "Ornith-1.0-35B", | |
| "provider": "deepreinforce-ai", | |
| "score": 50.4, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 49.5, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-M.1", | |
| "short_name": "Laguna-M.1", | |
| "provider": "poolside", | |
| "score": 49.2, | |
| "date": "2026-06-15" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-XS-2.1", | |
| "short_name": "Laguna-XS-2.1", | |
| "provider": "poolside", | |
| "score": 47.6, | |
| "date": "2026-06-20" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "poolside", | |
| "score": 46.3, | |
| "date": "2026-04-23" | |
| }, | |
| { | |
| "model_id": "MuVeraAI/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "MuVeraAI", | |
| "score": 44.5, | |
| "date": "2026-04-28" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-Next", | |
| "short_name": "Qwen3-Coder-Next", | |
| "provider": "Qwen", | |
| "score": 44.3, | |
| "date": "2026-01-30" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-9B", | |
| "short_name": "Ornith-1.0-9B", | |
| "provider": "deepreinforce-ai", | |
| "score": 42.9, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "CohereLabs/North-Mini-Code-1.0", | |
| "short_name": "North-Mini-Code-1.0", | |
| "provider": "CohereLabs", | |
| "score": 40.2, | |
| "date": "2026-06-05" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", | |
| "short_name": "Qwen3-Coder-480B-A35B-Instruct", | |
| "provider": "Qwen", | |
| "score": 38.7, | |
| "date": "2025-07-22" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 36.81, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Instruct", | |
| "short_name": "Kimi-K2-Instruct", | |
| "provider": "moonshotai", | |
| "score": 27.67, | |
| "date": "2025-07-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-235B-A22B", | |
| "short_name": "Qwen3-235B-A22B", | |
| "provider": "Qwen", | |
| "score": 21.41, | |
| "date": "2025-04-27" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 16.2, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.6", | |
| "short_name": "GLM-4.6", | |
| "provider": "zai-org", | |
| "score": 9.67, | |
| "date": "2025-09-29" | |
| } | |
| ] | |
| }, | |
| "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": "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" | |
| } | |
| ] | |
| }, | |
| "ParseBench": { | |
| "name": "ParseBench", | |
| "dataset": "llamaindex/ParseBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "KDLAI/KDL-Frontier-Parser-nano", | |
| "short_name": "KDL-Frontier-Parser-nano", | |
| "provider": "KDLAI", | |
| "score": 76.36, | |
| "date": "2026-06-10" | |
| }, | |
| { | |
| "model_id": "infly/Infinity-Parser2-Pro", | |
| "short_name": "Infinity-Parser2-Pro", | |
| "provider": "infly", | |
| "score": 74.3, | |
| "date": "2026-04-08" | |
| }, | |
| { | |
| "model_id": "infly/Infinity-Parser2-Flash", | |
| "short_name": "Infinity-Parser2-Flash", | |
| "provider": "infly", | |
| "score": 73.25, | |
| "date": "2026-02-27" | |
| }, | |
| { | |
| "model_id": "opendatalab/MinerU2.5-Pro-2605-1.2B", | |
| "short_name": "MinerU2.5-Pro-2605-1.2B", | |
| "provider": "opendatalab", | |
| "score": 72.78, | |
| "date": "2026-05-20" | |
| }, | |
| { | |
| "model_id": "datalab-to/chandra-ocr-2", | |
| "short_name": "chandra-ocr-2", | |
| "provider": "datalab-to", | |
| "score": 70.1, | |
| "date": "2026-03-16" | |
| }, | |
| { | |
| "model_id": "datalab-to/surya-ocr-2", | |
| "short_name": "surya-ocr-2", | |
| "provider": "datalab-to", | |
| "score": 64.83, | |
| "date": "2026-05-14" | |
| }, | |
| { | |
| "model_id": "dots-studio/dots.mocr", | |
| "short_name": "dots.mocr", | |
| "provider": "dots-studio", | |
| "score": 55.8, | |
| "date": "2026-03-19" | |
| }, | |
| { | |
| "model_id": "tiiuae/Falcon-OCR", | |
| "short_name": "Falcon-OCR", | |
| "provider": "tiiuae", | |
| "score": 53.08, | |
| "date": "2026-02-22" | |
| }, | |
| { | |
| "model_id": "docling-project/docling-models", | |
| "short_name": "docling-models", | |
| "provider": "docling-project", | |
| "score": 50.6, | |
| "date": "2024-07-02" | |
| }, | |
| { | |
| "model_id": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", | |
| "short_name": "Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", | |
| "provider": "nvidia", | |
| "score": 48.51, | |
| "date": "2026-04-20" | |
| }, | |
| { | |
| "model_id": "lightonai/LightOnOCR-2-1B", | |
| "short_name": "LightOnOCR-2-1B", | |
| "provider": "lightonai", | |
| "score": 48.0, | |
| "date": "2026-01-16" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-VL-8B-Instruct", | |
| "short_name": "Qwen3-VL-8B-Instruct", | |
| "provider": "Qwen", | |
| "score": 46.8, | |
| "date": "2025-10-11" | |
| }, | |
| { | |
| "model_id": "baidu/Qianfan-OCR", | |
| "short_name": "Qianfan-OCR", | |
| "provider": "baidu", | |
| "score": 46.2, | |
| "date": "2026-03-18" | |
| }, | |
| { | |
| "model_id": "baidu/Unlimited-OCR", | |
| "short_name": "Unlimited-OCR", | |
| "provider": "baidu", | |
| "score": 46.17, | |
| "date": "2026-06-19" | |
| }, | |
| { | |
| "model_id": "opendatalab/MinerU2.5-2509-1.2B", | |
| "short_name": "MinerU2.5-2509-1.2B", | |
| "provider": "opendatalab", | |
| "score": 45.9, | |
| "date": "2025-09-17" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 44.1, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "opendatalab/MinerU-Diffusion-V1-0320-2.5B", | |
| "short_name": "MinerU-Diffusion-V1-0320-2.5B", | |
| "provider": "opendatalab", | |
| "score": 42.63, | |
| "date": "2026-03-23" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-OCR-2", | |
| "short_name": "DeepSeek-OCR-2", | |
| "provider": "deepseek-ai", | |
| "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": "zai-org/GLM-OCR", | |
| "short_name": "GLM-OCR", | |
| "provider": "zai-org", | |
| "score": 29.6, | |
| "date": "2026-01-30" | |
| } | |
| ] | |
| }, | |
| "mmluPro": { | |
| "name": "MMLU-Pro", | |
| "dataset": "TIGER-Lab/MMLU-Pro", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 88.0, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "internlm/Intern-S2-Preview", | |
| "short_name": "Intern-S2-Preview", | |
| "provider": "internlm", | |
| "score": 88.0, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 87.8, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 87.5, | |
| "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": "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": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 86.7, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 86.4, | |
| "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": "upstage/Solar-Open2-250B", | |
| "short_name": "Solar-Open2-250B", | |
| "provider": "upstage", | |
| "score": 86.2, | |
| "date": "2026-07-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 86.1, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 86.0, | |
| "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": "deepseek-ai/DeepSeek-R1-0528", | |
| "short_name": "DeepSeek-R1-0528", | |
| "provider": "deepseek-ai", | |
| "score": 85.0, | |
| "date": "2025-05-28" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.5", | |
| "short_name": "GLM-4.5", | |
| "provider": "zai-org", | |
| "score": 84.6, | |
| "date": "2025-07-20" | |
| }, | |
| { | |
| "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": "deepseek-ai/DeepSeek-R1", | |
| "short_name": "DeepSeek-R1", | |
| "provider": "deepseek-ai", | |
| "score": 84.0, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "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": "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": "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": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 83.73, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 83.73, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 83.73, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "internlm/Intern-S1", | |
| "short_name": "Intern-S1", | |
| "provider": "internlm", | |
| "score": 83.5, | |
| "date": "2025-07-24" | |
| }, | |
| { | |
| "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": "Qwen/Qwen3-235B-A22B-Instruct-2507", | |
| "short_name": "Qwen3-235B-A22B-Instruct-2507", | |
| "provider": "Qwen", | |
| "score": 83.0, | |
| "date": "2025-07-21" | |
| }, | |
| { | |
| "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": "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", | |
| "short_name": "MiniMax-M2", | |
| "provider": "MiniMaxAI", | |
| "score": 82.0, | |
| "date": "2025-10-22" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K1", | |
| "short_name": "A.X-K1", | |
| "provider": "skt", | |
| "score": 81.5, | |
| "date": "2025-12-29" | |
| }, | |
| { | |
| "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": "deepseek-ai/DeepSeek-V3-0324", | |
| "short_name": "DeepSeek-V3-0324", | |
| "provider": "deepseek-ai", | |
| "score": 81.2, | |
| "date": "2025-03-24" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M1-40k", | |
| "short_name": "MiniMax-M1-40k", | |
| "provider": "MiniMaxAI", | |
| "score": 81.1, | |
| "date": "2025-06-05" | |
| }, | |
| { | |
| "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-Instruct", | |
| "short_name": "Kimi-K2-Instruct", | |
| "provider": "moonshotai", | |
| "score": 81.0, | |
| "date": "2025-07-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", | |
| "short_name": "Qwen3-30B-A3B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 80.9, | |
| "date": "2025-07-29" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 80.8, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 80.1, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "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": "meituan-longcat/LongCat-Flash-Lite", | |
| "short_name": "LongCat-Flash-Lite", | |
| "provider": "meituan-longcat", | |
| "score": 78.29, | |
| "date": "2026-01-27" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-Text-01", | |
| "short_name": "MiniMax-Text-01", | |
| "provider": "MiniMaxAI", | |
| "score": 75.7, | |
| "date": "2025-01-12" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 73.6, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-72B", | |
| "short_name": "Qwen2.5-72B", | |
| "provider": "Qwen", | |
| "score": 71.59, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "model_id": "microsoft/phi-4", | |
| "short_name": "phi-4", | |
| "provider": "microsoft", | |
| "score": 70.4, | |
| "date": "2024-12-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-4B-Instruct-2507", | |
| "short_name": "Qwen3-4B-Instruct-2507", | |
| "provider": "Qwen", | |
| "score": 69.6, | |
| "date": "2025-08-05" | |
| }, | |
| { | |
| "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/Qwen2.5-32B", | |
| "short_name": "Qwen2.5-32B", | |
| "provider": "Qwen", | |
| "score": 69.23, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "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/Qwen3-235B-A22B", | |
| "short_name": "Qwen3-235B-A22B", | |
| "provider": "Qwen", | |
| "score": 68.18, | |
| "date": "2025-04-27" | |
| }, | |
| { | |
| "model_id": "mistralai/Mistral-Large-Instruct-2411", | |
| "short_name": "Mistral-Large-Instruct-2411", | |
| "provider": "mistralai", | |
| "score": 67.94, | |
| "date": "2024-11-14" | |
| }, | |
| { | |
| "model_id": "tencent/Hunyuan-A13B-Instruct", | |
| "short_name": "Hunyuan-A13B-Instruct", | |
| "provider": "tencent", | |
| "score": 67.3, | |
| "date": "2025-06-25" | |
| }, | |
| { | |
| "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-V2.5", | |
| "short_name": "DeepSeek-V2.5", | |
| "provider": "deepseek-ai", | |
| "score": 65.83, | |
| "date": "2024-09-05" | |
| }, | |
| { | |
| "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-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": "deepseek-ai/DeepSeek-V3", | |
| "short_name": "DeepSeek-V3", | |
| "provider": "deepseek-ai", | |
| "score": 64.4, | |
| "date": "2024-12-25" | |
| }, | |
| { | |
| "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": "Qwen/Qwen2.5-14B", | |
| "short_name": "Qwen2.5-14B", | |
| "provider": "Qwen", | |
| "score": 63.69, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-30B-A3B-Base", | |
| "short_name": "Qwen3-30B-A3B-Base", | |
| "provider": "Qwen", | |
| "score": 61.7, | |
| "date": "2025-04-28" | |
| }, | |
| { | |
| "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": "nvidia/Nemotron-H-56B-Base-8K", | |
| "short_name": "Nemotron-H-56B-Base-8K", | |
| "provider": "nvidia", | |
| "score": 60.5, | |
| "date": "2025-04-08" | |
| }, | |
| { | |
| "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": "tencent/Tencent-Hunyuan-Large", | |
| "short_name": "Tencent-Hunyuan-Large", | |
| "provider": "tencent", | |
| "score": 60.2, | |
| "date": "2024-10-22" | |
| }, | |
| { | |
| "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": "JetBrains/Mellum2-12B-A2.5B-Base", | |
| "short_name": "Mellum2-12B-A2.5B-Base", | |
| "provider": "JetBrains", | |
| "score": 59.31, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "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": "XiaomiMiMo/MiMo-7B-RL", | |
| "short_name": "MiMo-7B-RL", | |
| "provider": "XiaomiMiMo", | |
| "score": 58.6, | |
| "date": "2025-04-29" | |
| }, | |
| { | |
| "model_id": "internlm/internlm3-8b-instruct", | |
| "short_name": "internlm3-8b-instruct", | |
| "provider": "internlm", | |
| "score": 57.6, | |
| "date": "2025-01-13" | |
| }, | |
| { | |
| "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-4.1-8b", | |
| "short_name": "granite-4.1-8b", | |
| "provider": "ibm-granite", | |
| "score": 55.99, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "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": "deepseek-ai/DeepSeek-V2-Chat", | |
| "short_name": "DeepSeek-V2-Chat", | |
| "provider": "deepseek-ai", | |
| "score": 54.81, | |
| "date": "2024-04-28" | |
| }, | |
| { | |
| "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": "microsoft/Phi-4-mini-instruct", | |
| "short_name": "Phi-4-mini-instruct", | |
| "provider": "microsoft", | |
| "score": 52.8, | |
| "date": "2025-02-19" | |
| }, | |
| { | |
| "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-3.1-70B", | |
| "short_name": "Llama-3.1-70B", | |
| "provider": "meta-llama", | |
| "score": 52.47, | |
| "date": "2024-07-14" | |
| }, | |
| { | |
| "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": "microsoft/Phi-3-medium-128k-instruct", | |
| "short_name": "Phi-3-medium-128k-instruct", | |
| "provider": "microsoft", | |
| "score": 51.91, | |
| "date": "2024-05-07" | |
| }, | |
| { | |
| "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": 49.93, | |
| "date": "2024-04-25" | |
| }, | |
| { | |
| "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": "ai21labs/AI21-Jamba-Large-1.5", | |
| "short_name": "AI21-Jamba-Large-1.5", | |
| "provider": "ai21labs", | |
| "score": 49.46, | |
| "date": "2024-08-19" | |
| }, | |
| { | |
| "model_id": "mistralai/Mistral-Small-Instruct-2409", | |
| "short_name": "Mistral-Small-Instruct-2409", | |
| "provider": "mistralai", | |
| "score": 48.4, | |
| "date": "2024-09-17" | |
| }, | |
| { | |
| "model_id": "zai-org/glm-4-9b", | |
| "short_name": "glm-4-9b", | |
| "provider": "zai-org", | |
| "score": 47.92, | |
| "date": "2024-06-04" | |
| }, | |
| { | |
| "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": "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": "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": "microsoft/Phi-3-mini-4k-instruct", | |
| "short_name": "Phi-3-mini-4k-instruct", | |
| "provider": "microsoft", | |
| "score": 45.66, | |
| "date": "2024-04-22" | |
| }, | |
| { | |
| "model_id": "CohereLabs/aya-expanse-32b", | |
| "short_name": "aya-expanse-32b", | |
| "provider": "CohereLabs", | |
| "score": 45.41, | |
| "date": "2024-10-23" | |
| }, | |
| { | |
| "model_id": "google/gemma-2-9b", | |
| "short_name": "gemma-2-9b", | |
| "provider": "google", | |
| "score": 45.1, | |
| "date": "2024-06-24" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-7B", | |
| "short_name": "Qwen2.5-7B", | |
| "provider": "Qwen", | |
| "score": 45.0, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "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": "Qwen/Qwen2.5-3B", | |
| "short_name": "Qwen2.5-3B", | |
| "provider": "Qwen", | |
| "score": 43.73, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "model_id": "TIGER-Lab/MAmmoTH2-8B-Plus", | |
| "short_name": "MAmmoTH2-8B-Plus", | |
| "provider": "TIGER-Lab", | |
| "score": 43.35, | |
| "date": "2024-05-06" | |
| }, | |
| { | |
| "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": 42.0, | |
| "date": "2024-07-16" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-7B-Base", | |
| "short_name": "MiMo-7B-Base", | |
| "provider": "XiaomiMiMo", | |
| "score": 41.9, | |
| "date": "2025-04-29" | |
| }, | |
| { | |
| "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": "mistralai/Mixtral-8x7B-v0.1", | |
| "short_name": "Mixtral-8x7B-v0.1", | |
| "provider": "mistralai", | |
| "score": 41.03, | |
| "date": "2023-12-01" | |
| }, | |
| { | |
| "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": "TIGER-Lab/MAmmoTH2-7B-Plus", | |
| "short_name": "MAmmoTH2-7B-Plus", | |
| "provider": "TIGER-Lab", | |
| "score": 40.85, | |
| "date": "2024-05-06" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2-7B", | |
| "short_name": "Qwen2-7B", | |
| "provider": "Qwen", | |
| "score": 40.73, | |
| "date": "2024-06-04" | |
| }, | |
| { | |
| "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": "Qwen/Qwen1.5-14B-Chat", | |
| "short_name": "Qwen1.5-14B-Chat", | |
| "provider": "Qwen", | |
| "score": 38.02, | |
| "date": "2024-01-30" | |
| }, | |
| { | |
| "model_id": "mistralai/Ministral-8B-Instruct-2410", | |
| "short_name": "Ministral-8B-Instruct-2410", | |
| "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" | |
| }, | |
| { | |
| "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": "meta-llama/Meta-Llama-3-8B", | |
| "short_name": "Meta-Llama-3-8B", | |
| "provider": "meta-llama", | |
| "score": 35.36, | |
| "date": "2024-04-17" | |
| }, | |
| { | |
| "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": "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": "CohereLabs/aya-expanse-8b", | |
| "short_name": "aya-expanse-8b", | |
| "provider": "CohereLabs", | |
| "score": 33.74, | |
| "date": "2024-10-23" | |
| }, | |
| { | |
| "model_id": "internlm/internlm2-math-plus-7b", | |
| "short_name": "internlm2-math-plus-7b", | |
| "provider": "internlm", | |
| "score": 33.5, | |
| "date": "2024-05-24" | |
| }, | |
| { | |
| "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/Qwen2.5-1.5B", | |
| "short_name": "Qwen2.5-1.5B", | |
| "provider": "Qwen", | |
| "score": 32.1, | |
| "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": "mistralai/Mistral-7B-Instruct-v0.2", | |
| "short_name": "Mistral-7B-Instruct-v0.2", | |
| "provider": "mistralai", | |
| "score": 30.84, | |
| "date": "2023-12-11" | |
| }, | |
| { | |
| "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": "Qwen/Qwen1.5-7B-Chat", | |
| "short_name": "Qwen1.5-7B-Chat", | |
| "provider": "Qwen", | |
| "score": 29.06, | |
| "date": "2024-01-30" | |
| }, | |
| { | |
| "model_id": "01-ai/Yi-6B-Chat", | |
| "short_name": "Yi-6B-Chat", | |
| "provider": "01-ai", | |
| "score": 28.84, | |
| "date": "2023-11-22" | |
| }, | |
| { | |
| "model_id": "01-ai/Yi-6B", | |
| "short_name": "Yi-6B", | |
| "provider": "01-ai", | |
| "score": 26.51, | |
| "date": "2023-11-01" | |
| }, | |
| { | |
| "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": "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": "Qwen/Qwen2-1.5B", | |
| "short_name": "Qwen2-1.5B", | |
| "provider": "Qwen", | |
| "score": 22.56, | |
| "date": "2024-05-31" | |
| }, | |
| { | |
| "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": "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": "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": "HuggingFaceTB/SmolLM2-1.7B", | |
| "short_name": "SmolLM2-1.7B", | |
| "provider": "HuggingFaceTB", | |
| "score": 18.31, | |
| "date": "2024-10-30" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2-0.5B", | |
| "short_name": "Qwen2-0.5B", | |
| "provider": "Qwen", | |
| "score": 14.97, | |
| "date": "2024-05-31" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-0.5B", | |
| "short_name": "Qwen2.5-0.5B", | |
| "provider": "Qwen", | |
| "score": 14.92, | |
| "date": "2024-09-15" | |
| }, | |
| { | |
| "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/Llama-3.2-1B", | |
| "short_name": "Llama-3.2-1B", | |
| "provider": "meta-llama", | |
| "score": 11.95, | |
| "date": "2024-09-18" | |
| }, | |
| { | |
| "model_id": "HuggingFaceTB/SmolLM2-360M", | |
| "short_name": "SmolLM2-360M", | |
| "provider": "HuggingFaceTB", | |
| "score": 11.38, | |
| "date": "2024-10-31" | |
| }, | |
| { | |
| "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" | |
| } | |
| ] | |
| }, | |
| "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": "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": "lightonai/LightOnOCR-1B-1025", | |
| "short_name": "LightOnOCR-1B-1025", | |
| "provider": "lightonai", | |
| "score": 76.1, | |
| "date": "2025-10-20" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-OCR", | |
| "short_name": "DeepSeek-OCR", | |
| "provider": "deepseek-ai", | |
| "score": 75.7, | |
| "date": "2025-10-17" | |
| }, | |
| { | |
| "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": 75.2, | |
| "date": "2026-01-30" | |
| }, | |
| { | |
| "model_id": "XCurOS/XCurOS-OCR", | |
| "short_name": "XCurOS-OCR", | |
| "provider": "XCurOS", | |
| "score": 75.2, | |
| "date": "2026-06-01" | |
| } | |
| ] | |
| }, | |
| "gpqa": { | |
| "name": "GPQA Diamond", | |
| "dataset": "Idavidrein/gpqa", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "moonshotai/Kimi-K3", | |
| "short_name": "Kimi-K3", | |
| "provider": "moonshotai", | |
| "score": 93.5, | |
| "date": "2026-06-13" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 91.2, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-398B-JGOS", | |
| "short_name": "Darwin-398B-JGOS", | |
| "provider": "FINAL-Bench", | |
| "score": 90.9, | |
| "date": "2026-06-14" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 90.5, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3", | |
| "short_name": "Hy3", | |
| "provider": "tencent", | |
| "score": 90.4, | |
| "date": "2026-07-02" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 90.1, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling-Small", | |
| "short_name": "Inkling-Small", | |
| "provider": "thinkingmachines", | |
| "score": 89.5, | |
| "date": "2026-07-27" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-28B-REASON", | |
| "short_name": "Darwin-28B-REASON", | |
| "provider": "FINAL-Bench", | |
| "score": 89.39, | |
| "date": "2026-05-17" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 88.4, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-36B-Opus", | |
| "short_name": "Darwin-36B-Opus", | |
| "provider": "FINAL-Bench", | |
| "score": 88.4, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-60B-DUO", | |
| "short_name": "Darwin-60B-DUO", | |
| "provider": "FINAL-Bench", | |
| "score": 88.38, | |
| "date": "2026-05-27" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ring-2.6-1T", | |
| "short_name": "Ring-2.6-1T", | |
| "provider": "inclusionAI", | |
| "score": 88.27, | |
| "date": "2026-05-14" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 88.1, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", | |
| "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4", | |
| "provider": "nvidia", | |
| "score": 87.9, | |
| "date": "2026-06-03" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7-FP8", | |
| "short_name": "GLM-4.7-FP8", | |
| "provider": "zai-org", | |
| "score": 87.88, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 87.8, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 87.6, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3-preview", | |
| "short_name": "Hy3-preview", | |
| "provider": "tencent", | |
| "score": 87.2, | |
| "date": "2026-04-13" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling", | |
| "short_name": "Inkling", | |
| "provider": "thinkingmachines", | |
| "score": 87.2, | |
| "date": "2026-07-14" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", | |
| "provider": "nvidia", | |
| "score": 87.0, | |
| "date": "2026-06-03" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-27B-Opus", | |
| "short_name": "Darwin-27B-Opus", | |
| "provider": "FINAL-Bench", | |
| "score": 86.9, | |
| "date": "2026-04-12" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 86.6, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Ourbox-35B-JGOS", | |
| "short_name": "Ourbox-35B-JGOS", | |
| "provider": "FINAL-Bench", | |
| "score": 86.36, | |
| "date": "2026-07-10" | |
| }, | |
| { | |
| "model_id": "upstage/Solar-Open2-250B", | |
| "short_name": "Solar-Open2-250B", | |
| "provider": "upstage", | |
| "score": 86.3, | |
| "date": "2026-07-22" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 86.2, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 86.0, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 86.0, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-31B-Opus", | |
| "short_name": "Darwin-31B-Opus", | |
| "provider": "FINAL-Bench", | |
| "score": 85.9, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 85.7, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K2", | |
| "short_name": "A.X-K2", | |
| "provider": "skt", | |
| "score": 85.6, | |
| "date": "2026-07-28" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 85.5, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5-FP8", | |
| "short_name": "GLM-5-FP8", | |
| "provider": "zai-org", | |
| "score": 85.35, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 85.2, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-4B-David", | |
| "short_name": "Darwin-4B-David", | |
| "provider": "FINAL-Bench", | |
| "score": 85.0, | |
| "date": "2026-04-10" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Thinking", | |
| "short_name": "Kimi-K2-Thinking", | |
| "provider": "moonshotai", | |
| "score": 84.5, | |
| "date": "2025-11-04" | |
| }, | |
| { | |
| "model_id": "FINAL-Bench/Darwin-9B-NEG", | |
| "short_name": "Darwin-9B-NEG", | |
| "provider": "FINAL-Bench", | |
| "score": 84.34, | |
| "date": "2026-04-24" | |
| }, | |
| { | |
| "model_id": "JGOS-Model/JGOS-31B-Citizen", | |
| "short_name": "JGOS-31B-Citizen", | |
| "provider": "JGOS-Model", | |
| "score": 84.34, | |
| "date": "2026-06-04" | |
| }, | |
| { | |
| "model_id": "openpangu/openPangu-2.0-Flash", | |
| "short_name": "openPangu-2.0-Flash", | |
| "provider": "openpangu", | |
| "score": 83.7, | |
| "date": "2026-06-30" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 83.5, | |
| "date": "2026-02-01" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2-Flash", | |
| "short_name": "MiMo-V2-Flash", | |
| "provider": "XiaomiMiMo", | |
| "score": 83.33, | |
| "date": "2025-12-16" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1-FP8", | |
| "short_name": "GLM-5.1-FP8", | |
| "provider": "zai-org", | |
| "score": 83.33, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 82.7, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "RedHatAI", | |
| "score": 82.7, | |
| "date": "2026-03-26" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 82.7, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 82.7, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 82.7, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.6-FP8", | |
| "short_name": "GLM-4.6-FP8", | |
| "provider": "zai-org", | |
| "score": 81.31, | |
| "date": "2025-09-29" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 80.9, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 80.81, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "meituan-longcat/LongCat-Flash-Thinking-2601", | |
| "short_name": "LongCat-Flash-Thinking-2601", | |
| "provider": "meituan-longcat", | |
| "score": 80.5, | |
| "date": "2026-01-14" | |
| }, | |
| { | |
| "model_id": "LGAI-EXAONE/EXAONE-4.5-33B", | |
| "short_name": "EXAONE-4.5-33B", | |
| "provider": "LGAI-EXAONE", | |
| "score": 80.5, | |
| "date": "2026-04-04" | |
| }, | |
| { | |
| "model_id": "LGAI-EXAONE/K-EXAONE-236B-A23B", | |
| "short_name": "K-EXAONE-236B-A23B", | |
| "provider": "LGAI-EXAONE", | |
| "score": 79.1, | |
| "date": "2025-12-26" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-R1-0528", | |
| "short_name": "DeepSeek-R1-0528", | |
| "provider": "deepseek-ai", | |
| "score": 78.79, | |
| "date": "2025-05-28" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-FP8", | |
| "provider": "nvidia", | |
| "score": 77.27, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "nvidia/Nemotron-Cascade-2-30B-A3B", | |
| "short_name": "Nemotron-Cascade-2-30B-A3B", | |
| "provider": "nvidia", | |
| "score": 76.1, | |
| "date": "2026-03-18" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7-Flash", | |
| "short_name": "GLM-4.7-Flash", | |
| "provider": "zai-org", | |
| "score": 75.2, | |
| "date": "2026-01-19" | |
| }, | |
| { | |
| "model_id": "jdopensource/JoyAI-LLM-Flash", | |
| "short_name": "JoyAI-LLM-Flash", | |
| "provider": "jdopensource", | |
| "score": 74.43, | |
| "date": "2026-02-14" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 74.2, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K1", | |
| "short_name": "A.X-K1", | |
| "provider": "skt", | |
| "score": 74.0, | |
| "date": "2025-12-29" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", | |
| "short_name": "Qwen3-30B-A3B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 72.22, | |
| "date": "2025-07-29" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.5-Air", | |
| "short_name": "GLM-4.5-Air", | |
| "provider": "zai-org", | |
| "score": 71.72, | |
| "date": "2025-07-20" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-R1", | |
| "short_name": "DeepSeek-R1", | |
| "provider": "deepseek-ai", | |
| "score": 71.5, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "model_id": "mistralai/Mistral-Small-4-119B-2603", | |
| "short_name": "Mistral-Small-4-119B-2603", | |
| "provider": "mistralai", | |
| "score": 71.2, | |
| "date": "2026-01-23" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 66.7, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-4B-Thinking-2507", | |
| "short_name": "Qwen3-4B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 65.8, | |
| "date": "2025-08-05" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-4B-Instruct-2507", | |
| "short_name": "Qwen3-4B-Instruct-2507", | |
| "provider": "Qwen", | |
| "score": 62.0, | |
| "date": "2025-08-05" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V3", | |
| "short_name": "DeepSeek-V3", | |
| "provider": "deepseek-ai", | |
| "score": 58.21, | |
| "date": "2024-12-25" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Thinking", | |
| "short_name": "Mellum2-12B-A2.5B-Thinking", | |
| "provider": "JetBrains", | |
| "score": 57.6, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "CohereLabs/c4ai-command-a-03-2025", | |
| "short_name": "c4ai-command-a-03-2025", | |
| "provider": "CohereLabs", | |
| "score": 50.51, | |
| "date": "2025-03-11" | |
| }, | |
| { | |
| "model_id": "meta-llama/Llama-3.2-90B-Vision-Instruct", | |
| "short_name": "Llama-3.2-90B-Vision-Instruct", | |
| "provider": "meta-llama", | |
| "score": 46.09, | |
| "date": "2024-09-19" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-30b", | |
| "short_name": "granite-4.1-30b", | |
| "provider": "ibm-granite", | |
| "score": 45.76, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-8b", | |
| "short_name": "granite-4.1-8b", | |
| "provider": "ibm-granite", | |
| "score": 41.96, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Instruct", | |
| "short_name": "Mellum2-12B-A2.5B-Instruct", | |
| "provider": "JetBrains", | |
| "score": 40.9, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", | |
| "short_name": "Mellum2-12B-A2.5B-Thinking-SFT", | |
| "provider": "JetBrains", | |
| "score": 39.9, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Instruct-SFT", | |
| "short_name": "Mellum2-12B-A2.5B-Instruct-SFT", | |
| "provider": "JetBrains", | |
| "score": 38.9, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "CohereLabs/c4ai-command-r-plus-08-2024", | |
| "short_name": "c4ai-command-r-plus-08-2024", | |
| "provider": "CohereLabs", | |
| "score": 34.34, | |
| "date": "2024-08-21" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-3b", | |
| "short_name": "granite-4.1-3b", | |
| "provider": "ibm-granite", | |
| "score": 31.7, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Base-Pretrain", | |
| "short_name": "Mellum2-12B-A2.5B-Base-Pretrain", | |
| "provider": "JetBrains", | |
| "score": 31.31, | |
| "date": "2026-04-07" | |
| }, | |
| { | |
| "model_id": "JetBrains/Mellum2-12B-A2.5B-Base", | |
| "short_name": "Mellum2-12B-A2.5B-Base", | |
| "provider": "JetBrains", | |
| "score": 31.31, | |
| "date": "2026-05-26" | |
| }, | |
| { | |
| "model_id": "CohereLabs/c4ai-command-r-08-2024", | |
| "short_name": "c4ai-command-r-08-2024", | |
| "provider": "CohereLabs", | |
| "score": 26.77, | |
| "date": "2024-08-19" | |
| }, | |
| { | |
| "model_id": "CohereLabs/c4ai-command-r7b-12-2024", | |
| "short_name": "c4ai-command-r7b-12-2024", | |
| "provider": "CohereLabs", | |
| "score": 26.77, | |
| "date": "2024-12-11" | |
| }, | |
| { | |
| "model_id": "Muse-research/Muse-2-350M", | |
| "short_name": "Muse-2-350M", | |
| "provider": "Muse-research", | |
| "score": 25.79, | |
| "date": "2026-06-06" | |
| }, | |
| { | |
| "model_id": "meta-llama/Llama-3.2-1B-Instruct", | |
| "short_name": "Llama-3.2-1B-Instruct", | |
| "provider": "meta-llama", | |
| "score": 18.69, | |
| "date": "2024-09-18" | |
| } | |
| ] | |
| }, | |
| "LEXam": { | |
| "name": "LEXam", | |
| "dataset": "LEXam-Benchmark/LEXam", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-R1", | |
| "short_name": "DeepSeek-R1", | |
| "provider": "deepseek-ai", | |
| "score": 52.41, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507", | |
| "short_name": "Qwen3-235B-A22B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 48.19, | |
| "date": "2025-07-25" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-120b", | |
| "short_name": "gpt-oss-120b", | |
| "provider": "openai", | |
| "score": 47.71, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V3", | |
| "short_name": "DeepSeek-V3", | |
| "provider": "deepseek-ai", | |
| "score": 46.57, | |
| "date": "2024-12-25" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-32B", | |
| "short_name": "Qwen3-32B", | |
| "provider": "Qwen", | |
| "score": 45.3, | |
| "date": "2025-04-27" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking", | |
| "short_name": "Qwen3-Next-80B-A3B-Thinking", | |
| "provider": "Qwen", | |
| "score": 43.31, | |
| "date": "2025-09-09" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 40.78, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "microsoft/phi-4", | |
| "short_name": "phi-4", | |
| "provider": "microsoft", | |
| "score": 40.66, | |
| "date": "2024-12-11" | |
| }, | |
| { | |
| "model_id": "mistralai/Ministral-8B-Instruct-2410", | |
| "short_name": "Ministral-8B-Instruct-2410", | |
| "provider": "mistralai", | |
| "score": 26.27, | |
| "date": "2024-10-15" | |
| } | |
| ] | |
| }, | |
| "aime2026": { | |
| "name": "AIME 2026", | |
| "dataset": "MathArena/aime_2026", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "thinkingmachines/Inkling", | |
| "short_name": "Inkling", | |
| "provider": "thinkingmachines", | |
| "score": 97.1, | |
| "date": "2026-07-14" | |
| }, | |
| { | |
| "model_id": "skt/A.X-K2", | |
| "short_name": "A.X-K2", | |
| "provider": "skt", | |
| "score": 97.1, | |
| "date": "2026-07-28" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 96.67, | |
| "date": "2026-02-01" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 96.4, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 95.83, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 95.83, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ring-2.6-1T", | |
| "short_name": "Ring-2.6-1T", | |
| "provider": "inclusionAI", | |
| "score": 95.83, | |
| "date": "2026-05-14" | |
| }, | |
| { | |
| "model_id": "upstage/Solar-Open2-250B", | |
| "short_name": "Solar-Open2-250B", | |
| "provider": "upstage", | |
| "score": 95.7, | |
| "date": "2026-07-22" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling-Small", | |
| "short_name": "Inkling-Small", | |
| "provider": "thinkingmachines", | |
| "score": 95.5, | |
| "date": "2026-07-27" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 95.3, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 94.1, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 93.33, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "openpangu/openPangu-2.0-Flash", | |
| "short_name": "openPangu-2.0-Flash", | |
| "provider": "openpangu", | |
| "score": 93.3, | |
| "date": "2026-06-30" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 92.7, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "LGAI-EXAONE/EXAONE-4.5-33B", | |
| "short_name": "EXAONE-4.5-33B", | |
| "provider": "LGAI-EXAONE", | |
| "score": 92.6, | |
| "date": "2026-04-04" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 90.83, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 90.0, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", | |
| "short_name": "Qwen3-30B-A3B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 87.5, | |
| "date": "2025-07-29" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-4B-Thinking-2507", | |
| "short_name": "Qwen3-4B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 82.5, | |
| "date": "2025-08-05" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ling-2.6-flash", | |
| "short_name": "Ling-2.6-flash", | |
| "provider": "inclusionAI", | |
| "score": 73.85, | |
| "date": "2026-04-28" | |
| } | |
| ] | |
| }, | |
| "hmmt2026": { | |
| "name": "HMMT Feb 2026", | |
| "dataset": "MathArena/hmmt_feb_2026", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 92.7, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "thinkingmachines/Inkling-Small", | |
| "short_name": "Inkling-Small", | |
| "provider": "thinkingmachines", | |
| "score": 90.2, | |
| "date": "2026-07-27" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 87.88, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "internlm/Intern-S2-Preview", | |
| "short_name": "Intern-S2-Preview", | |
| "provider": "internlm", | |
| "score": 87.31, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 87.12, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 86.36, | |
| "date": "2026-02-01" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 86.36, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 84.85, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 84.3, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 83.6, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 82.6, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 81.06, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507", | |
| "short_name": "Qwen3-30B-A3B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 78.79, | |
| "date": "2025-07-29" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-4B-Thinking-2507", | |
| "short_name": "Qwen3-4B-Thinking-2507", | |
| "provider": "Qwen", | |
| "score": 53.03, | |
| "date": "2025-08-05" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ling-2.6-flash", | |
| "short_name": "Ling-2.6-flash", | |
| "provider": "inclusionAI", | |
| "score": 49.29, | |
| "date": "2026-04-28" | |
| } | |
| ] | |
| }, | |
| "ResearchClawBench": { | |
| "name": "ResearchClawBench", | |
| "dataset": "InternScience/ResearchClawBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 20.71, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 18.19, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 18.0, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 17.12, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5", | |
| "short_name": "MiMo-V2.5", | |
| "provider": "XiaomiMiMo", | |
| "score": 16.91, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 14.23, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 13.96, | |
| "date": "2026-01-01" | |
| } | |
| ] | |
| }, | |
| "ifstruct_v1_0": { | |
| "name": "IFStruct v1.0", | |
| "dataset": "LiquidAI/ifstruct-v1.0", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "InternScience/Agents-A1", | |
| "short_name": "Agents-A1", | |
| "provider": "InternScience", | |
| "score": 93.25, | |
| "date": "2026-06-22" | |
| }, | |
| { | |
| "model_id": "openai/gpt-oss-20b", | |
| "short_name": "gpt-oss-20b", | |
| "provider": "openai", | |
| "score": 91.95, | |
| "date": "2025-08-04" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", | |
| "provider": "nvidia", | |
| "score": 86.8, | |
| "date": "2025-12-04" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.1-8b", | |
| "short_name": "granite-4.1-8b", | |
| "provider": "ibm-granite", | |
| "score": 68.45, | |
| "date": "2026-04-06" | |
| }, | |
| { | |
| "model_id": "ibm-granite/granite-4.0-h-tiny", | |
| "short_name": "granite-4.0-h-tiny", | |
| "provider": "ibm-granite", | |
| "score": 38.75, | |
| "date": "2025-09-16" | |
| } | |
| ] | |
| }, | |
| "arguana": { | |
| "name": "arguana", | |
| "dataset": "mteb/arguana", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "google/embeddinggemma-300m", | |
| "short_name": "embeddinggemma-300m", | |
| "provider": "google", | |
| "score": 71.53, | |
| "date": "2025-07-17" | |
| }, | |
| { | |
| "model_id": "mteb/baseline-bm25s", | |
| "short_name": "baseline-bm25s", | |
| "provider": "mteb", | |
| "score": 49.28, | |
| "date": "2026-02-19" | |
| }, | |
| { | |
| "model_id": "Surpem/Supertron-embedding-190M", | |
| "short_name": "Supertron-embedding-190M", | |
| "provider": "Surpem", | |
| "score": 42.02, | |
| "date": "2026-06-15" | |
| } | |
| ] | |
| }, | |
| "MMMU_Pro": { | |
| "name": "MMMU_Pro", | |
| "dataset": "MMMU/MMMU_Pro", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 79.4, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 78.5, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "internlm/Intern-S2-Preview", | |
| "short_name": "Intern-S2-Preview", | |
| "provider": "internlm", | |
| "score": 76.88, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 75.8, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 75.3, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 75.0, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "ATH-MaaS/Ovis2.6-80B-A3B", | |
| "short_name": "Ovis2.6-80B-A3B", | |
| "provider": "ATH-MaaS", | |
| "score": 66.3, | |
| "date": "2026-05-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-VL-7B-Instruct", | |
| "short_name": "Qwen2.5-VL-7B-Instruct", | |
| "provider": "Qwen", | |
| "score": 34.3, | |
| "date": "2025-01-26" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-VL-3B-Instruct", | |
| "short_name": "Qwen2.5-VL-3B-Instruct", | |
| "provider": "Qwen", | |
| "score": 32.7, | |
| "date": "2025-01-26" | |
| } | |
| ] | |
| }, | |
| "ScreenSpot_Pro": { | |
| "name": "SS-Pro", | |
| "dataset": "likaixin/ScreenSpot-Pro", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 70.4, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 70.3, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "inclusionAI/UI-Venus-1.5-30B-A3B", | |
| "short_name": "UI-Venus-1.5-30B-A3B", | |
| "provider": "inclusionAI", | |
| "score": 69.6, | |
| "date": "2026-02-09" | |
| }, | |
| { | |
| "model_id": "inclusionAI/UI-Venus-1.5-8B", | |
| "short_name": "UI-Venus-1.5-8B", | |
| "provider": "inclusionAI", | |
| "score": 68.4, | |
| "date": "2026-02-09" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 65.6, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "Salesforce/GTA1-32B", | |
| "short_name": "GTA1-32B", | |
| "provider": "Salesforce", | |
| "score": 63.6, | |
| "date": "2025-09-25" | |
| }, | |
| { | |
| "model_id": "inclusionAI/UI-Venus-Ground-72B", | |
| "short_name": "UI-Venus-Ground-72B", | |
| "provider": "inclusionAI", | |
| "score": 61.9, | |
| "date": "2025-08-16" | |
| }, | |
| { | |
| "model_id": "ByteDance-Seed/UI-TARS-1.5-7B", | |
| "short_name": "UI-TARS-1.5-7B", | |
| "provider": "ByteDance-Seed", | |
| "score": 61.6, | |
| "date": "2025-04-16" | |
| }, | |
| { | |
| "model_id": "inclusionAI/UI-Venus-1.5-2B", | |
| "short_name": "UI-Venus-1.5-2B", | |
| "provider": "inclusionAI", | |
| "score": 57.7, | |
| "date": "2026-02-09" | |
| }, | |
| { | |
| "model_id": "Salesforce/GTA1-7B", | |
| "short_name": "GTA1-7B", | |
| "provider": "Salesforce", | |
| "score": 55.5, | |
| "date": "2025-10-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-VL-72B-Instruct", | |
| "short_name": "Qwen2.5-VL-72B-Instruct", | |
| "provider": "Qwen", | |
| "score": 53.3, | |
| "date": "2025-01-27" | |
| }, | |
| { | |
| "model_id": "inclusionAI/UI-Venus-Ground-7B", | |
| "short_name": "UI-Venus-Ground-7B", | |
| "provider": "inclusionAI", | |
| "score": 50.8, | |
| "date": "2025-08-15" | |
| }, | |
| { | |
| "model_id": "KDEGroup/UI-AGILE-3B", | |
| "short_name": "UI-AGILE-3B", | |
| "provider": "KDEGroup", | |
| "score": 45.0, | |
| "date": "2025-08-07" | |
| }, | |
| { | |
| "model_id": "ByteDance-Seed/UI-TARS-72B-SFT", | |
| "short_name": "UI-TARS-72B-SFT", | |
| "provider": "ByteDance-Seed", | |
| "score": 38.1, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "model_id": "ByteDance-Seed/UI-TARS-7B-SFT", | |
| "short_name": "UI-TARS-7B-SFT", | |
| "provider": "ByteDance-Seed", | |
| "score": 35.7, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "model_id": "ByteDance-Seed/UI-TARS-2B-SFT", | |
| "short_name": "UI-TARS-2B-SFT", | |
| "provider": "ByteDance-Seed", | |
| "score": 27.7, | |
| "date": "2025-01-20" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-VL-7B-Instruct", | |
| "short_name": "Qwen2.5-VL-7B-Instruct", | |
| "provider": "Qwen", | |
| "score": 26.8, | |
| "date": "2025-01-26" | |
| }, | |
| { | |
| "model_id": "xlangai/Aguvis-7B-720P", | |
| "short_name": "Aguvis-7B-720P", | |
| "provider": "xlangai", | |
| "score": 22.9, | |
| "date": "2025-01-07" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen2.5-VL-3B-Instruct", | |
| "short_name": "Qwen2.5-VL-3B-Instruct", | |
| "provider": "Qwen", | |
| "score": 16.1, | |
| "date": "2025-01-26" | |
| }, | |
| { | |
| "model_id": "zai-org/CogAgent", | |
| "short_name": "CogAgent", | |
| "provider": "zai-org", | |
| "score": 7.7, | |
| "date": "2023-12-15" | |
| }, | |
| { | |
| "model_id": "openbmb/MiniCPM-V-2", | |
| "short_name": "MiniCPM-V-2", | |
| "provider": "openbmb", | |
| "score": 3.0, | |
| "date": "2024-04-09" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen-VL", | |
| "short_name": "Qwen-VL", | |
| "provider": "Qwen", | |
| "score": 0.1, | |
| "date": "2023-08-18" | |
| } | |
| ] | |
| }, | |
| "APEX_v1_extended": { | |
| "name": "APEX-v1-extended", | |
| "dataset": "mercor/APEX-v1-extended", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 51.7, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 49.0, | |
| "date": "2026-02-11" | |
| } | |
| ] | |
| }, | |
| "vlabench_primitive_ft_lerobot_video": { | |
| "name": "vlabench_primitive_ft_lerobot_video", | |
| "dataset": "VLABench/vlabench_primitive_ft_lerobot_video", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "lerobot/pi0_base", | |
| "short_name": "pi0_base", | |
| "provider": "lerobot", | |
| "score": 44.5, | |
| "date": "2025-09-09" | |
| }, | |
| { | |
| "model_id": "lerobot/pi05_base", | |
| "short_name": "pi05_base", | |
| "provider": "lerobot", | |
| "score": 42.0, | |
| "date": "2025-09-09" | |
| }, | |
| { | |
| "model_id": "nvidia/GR00T-N1-2B", | |
| "short_name": "GR00T-N1-2B", | |
| "provider": "nvidia", | |
| "score": 39.7, | |
| "date": "2025-03-05" | |
| }, | |
| { | |
| "model_id": "lerobot/pi0fast-base", | |
| "short_name": "pi0fast-base", | |
| "provider": "lerobot", | |
| "score": 34.1, | |
| "date": "2026-01-09" | |
| } | |
| ] | |
| }, | |
| "evasionBench": { | |
| "name": "EvasionBench", | |
| "dataset": "FutureMa/EvasionBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 82.91, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", | |
| "short_name": "Qwen3-Coder-480B-A35B-Instruct", | |
| "provider": "Qwen", | |
| "score": 78.16, | |
| "date": "2025-07-22" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 71.31, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Instruct-0905", | |
| "short_name": "Kimi-K2-Instruct-0905", | |
| "provider": "moonshotai", | |
| "score": 66.68, | |
| "date": "2025-09-03" | |
| } | |
| ] | |
| }, | |
| "terminalBench": { | |
| "name": "Terminal-Bench 2.0", | |
| "dataset": "harborframework/terminal-bench-2.0", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 69.0, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 68.4, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 67.9, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 66.7, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5", | |
| "short_name": "MiMo-V2.5", | |
| "provider": "XiaomiMiMo", | |
| "score": 65.8, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 59.3, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.7", | |
| "short_name": "MiniMax-M2.7", | |
| "provider": "MiniMaxAI", | |
| "score": 57.0, | |
| "date": "2026-04-09" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 56.9, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3-preview", | |
| "short_name": "Hy3-preview", | |
| "provider": "tencent", | |
| "score": 54.4, | |
| "date": "2026-04-13" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 52.5, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "score": 52.4, | |
| "date": "2026-02-11" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-35B-A3B", | |
| "short_name": "Qwen3.6-35B-A3B", | |
| "provider": "Qwen", | |
| "score": 51.5, | |
| "date": "2026-04-15" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 51.0, | |
| "date": "2026-02-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-122B-A10B", | |
| "short_name": "Qwen3.5-122B-A10B", | |
| "provider": "Qwen", | |
| "score": 49.4, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-M.1", | |
| "short_name": "Laguna-M.1", | |
| "provider": "poolside", | |
| "score": 45.8, | |
| "date": "2026-06-15" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 43.2, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-27B", | |
| "short_name": "Qwen3.5-27B", | |
| "provider": "Qwen", | |
| "score": 41.6, | |
| "date": "2026-02-24" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-XS-2.1", | |
| "short_name": "Laguna-XS-2.1", | |
| "provider": "poolside", | |
| "score": 37.5, | |
| "date": "2026-06-20" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-Next", | |
| "short_name": "Qwen3-Coder-Next", | |
| "provider": "Qwen", | |
| "score": 36.2, | |
| "date": "2026-01-30" | |
| }, | |
| { | |
| "model_id": "CohereLabs/North-Mini-Code-1.0", | |
| "short_name": "North-Mini-Code-1.0", | |
| "provider": "CohereLabs", | |
| "score": 36.0, | |
| "date": "2026-06-05" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Thinking", | |
| "short_name": "Kimi-K2-Thinking", | |
| "provider": "moonshotai", | |
| "score": 35.7, | |
| "date": "2025-11-04" | |
| }, | |
| { | |
| "model_id": "poolside/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "poolside", | |
| "score": 35.7, | |
| "date": "2026-04-23" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.7", | |
| "short_name": "GLM-4.7", | |
| "provider": "zai-org", | |
| "score": 33.4, | |
| "date": "2025-12-22" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 31.0, | |
| "date": "2026-03-10" | |
| }, | |
| { | |
| "model_id": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "RedHatAI", | |
| "score": 31.0, | |
| "date": "2026-03-26" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q3_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 31.0, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_M-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 31.0, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "exolabs/NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-MXFP4_MOE-dequant-bf16-vllm", | |
| "provider": "exolabs", | |
| "score": 31.0, | |
| "date": "2026-06-27" | |
| }, | |
| { | |
| "model_id": "MuVeraAI/Laguna-XS.2", | |
| "short_name": "Laguna-XS.2", | |
| "provider": "MuVeraAI", | |
| "score": 30.1, | |
| "date": "2026-04-28" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2", | |
| "short_name": "MiniMax-M2", | |
| "provider": "MiniMaxAI", | |
| "score": 30.0, | |
| "date": "2025-10-22" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.1", | |
| "short_name": "MiniMax-M2.1", | |
| "provider": "MiniMaxAI", | |
| "score": 29.2, | |
| "date": "2025-12-20" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2-Instruct", | |
| "short_name": "Kimi-K2-Instruct", | |
| "provider": "moonshotai", | |
| "score": 27.8, | |
| "date": "2025-07-11" | |
| }, | |
| { | |
| "model_id": "nvidia/Nemotron-Terminal-32B", | |
| "short_name": "Nemotron-Terminal-32B", | |
| "provider": "nvidia", | |
| "score": 27.4, | |
| "date": "2026-02-17" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-4.6", | |
| "short_name": "GLM-4.6", | |
| "provider": "zai-org", | |
| "score": 24.5, | |
| "date": "2025-09-29" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct", | |
| "short_name": "Qwen3-Coder-480B-A35B-Instruct", | |
| "provider": "Qwen", | |
| "score": 23.9, | |
| "date": "2025-07-22" | |
| }, | |
| { | |
| "model_id": "nvidia/Nemotron-Terminal-14B", | |
| "short_name": "Nemotron-Terminal-14B", | |
| "provider": "nvidia", | |
| "score": 20.2, | |
| "date": "2026-02-17" | |
| }, | |
| { | |
| "model_id": "nvidia/Nemotron-Terminal-8B", | |
| "short_name": "Nemotron-Terminal-8B", | |
| "provider": "nvidia", | |
| "score": 13.0, | |
| "date": "2026-02-17" | |
| } | |
| ] | |
| }, | |
| "yc_bench": { | |
| "name": "YC-Bench", | |
| "dataset": "collinear-ai/yc-bench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 2100000.0, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 1510772.0, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5", | |
| "short_name": "GLM-5", | |
| "provider": "zai-org", | |
| "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": "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": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 43.7, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "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" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 30.8, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.5", | |
| "short_name": "MiniMax-M2.5", | |
| "provider": "MiniMaxAI", | |
| "score": 27.1, | |
| "date": "2026-02-12" | |
| }, | |
| { | |
| "model_id": "stepfun-ai/Step-3.5-Flash", | |
| "short_name": "Step-3.5-Flash", | |
| "provider": "stepfun-ai", | |
| "score": 26.7, | |
| "date": "2026-02-01" | |
| } | |
| ] | |
| }, | |
| "Claw_Eval": { | |
| "name": "Claw-Eval", | |
| "dataset": "claw-eval/Claw-Eval", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-397B", | |
| "short_name": "Ornith-1.0-397B", | |
| "provider": "deepreinforce-ai", | |
| "score": 77.1, | |
| "date": "2026-06-23" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 74.5, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-35B", | |
| "short_name": "Ornith-1.0-35B", | |
| "provider": "deepreinforce-ai", | |
| "score": 69.8, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5-Pro", | |
| "short_name": "MiMo-V2.5-Pro", | |
| "provider": "XiaomiMiMo", | |
| "score": 64.0, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "inclusionAI/Ring-2.6-1T", | |
| "short_name": "Ring-2.6-1T", | |
| "provider": "inclusionAI", | |
| "score": 63.82, | |
| "date": "2026-05-14" | |
| }, | |
| { | |
| "model_id": "deepreinforce-ai/Ornith-1.0-9B", | |
| "short_name": "Ornith-1.0-9B", | |
| "provider": "deepreinforce-ai", | |
| "score": 63.1, | |
| "date": "2026-06-21" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 62.7, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "XiaomiMiMo/MiMo-V2.5", | |
| "short_name": "MiMo-V2.5", | |
| "provider": "XiaomiMiMo", | |
| "score": 62.1, | |
| "date": "2026-04-27" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 61.5, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 58.4, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "openpangu/openPangu-2.0-Flash", | |
| "short_name": "openPangu-2.0-Flash", | |
| "provider": "openpangu", | |
| "score": 58.2, | |
| "date": "2026-06-30" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 57.8, | |
| "date": "2026-02-16" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 57.8, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 52.8, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.7", | |
| "short_name": "MiniMax-M2.7", | |
| "provider": "MiniMaxAI", | |
| "score": 49.7, | |
| "date": "2026-04-09" | |
| }, | |
| { | |
| "model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "short_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16", | |
| "provider": "nvidia", | |
| "score": 6.8, | |
| "date": "2026-03-10" | |
| } | |
| ] | |
| }, | |
| "MDPBench": { | |
| "name": "MDPBench", | |
| "dataset": "Delores-Lin/MDPBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "dots-studio/dots.mocr", | |
| "short_name": "dots.mocr", | |
| "provider": "dots-studio", | |
| "score": 80.5, | |
| "date": "2026-03-19" | |
| }, | |
| { | |
| "model_id": "datalab-to/chandra-ocr-2", | |
| "short_name": "chandra-ocr-2", | |
| "provider": "datalab-to", | |
| "score": 79.7, | |
| "date": "2026-03-16" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 77.5, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "dots-studio/dots.ocr", | |
| "short_name": "dots.ocr", | |
| "provider": "dots-studio", | |
| "score": 76.5, | |
| "date": "2025-07-30" | |
| }, | |
| { | |
| "model_id": "opendatalab/MinerU2.5-Pro-2605-1.2B", | |
| "short_name": "MinerU2.5-Pro-2605-1.2B", | |
| "provider": "opendatalab", | |
| "score": 71.0, | |
| "date": "2026-05-20" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-VL-8B-Instruct", | |
| "short_name": "Qwen3-VL-8B-Instruct", | |
| "provider": "Qwen", | |
| "score": 68.3, | |
| "date": "2025-10-11" | |
| }, | |
| { | |
| "model_id": "tencent/HunyuanOCR", | |
| "short_name": "HunyuanOCR", | |
| "provider": "tencent", | |
| "score": 68.3, | |
| "date": "2025-11-18" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-OCR", | |
| "short_name": "GLM-OCR", | |
| "provider": "zai-org", | |
| "score": 67.3, | |
| "date": "2026-01-30" | |
| }, | |
| { | |
| "model_id": "XCurOS/XCurOS-OCR", | |
| "short_name": "XCurOS-OCR", | |
| "provider": "XCurOS", | |
| "score": 67.3, | |
| "date": "2026-06-01" | |
| }, | |
| { | |
| "model_id": "lightonai/LightOnOCR-2-1B", | |
| "short_name": "LightOnOCR-2-1B", | |
| "provider": "lightonai", | |
| "score": 63.9, | |
| "date": "2026-01-16" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-OCR", | |
| "short_name": "DeepSeek-OCR", | |
| "provider": "deepseek-ai", | |
| "score": 51.8, | |
| "date": "2025-10-17" | |
| }, | |
| { | |
| "model_id": "opendatalab/MinerU2.5-2509-1.2B", | |
| "short_name": "MinerU2.5-2509-1.2B", | |
| "provider": "opendatalab", | |
| "score": 46.3, | |
| "date": "2025-09-17" | |
| } | |
| ] | |
| }, | |
| "Video_MME_v2": { | |
| "name": "Video-MME-v2", | |
| "dataset": "MME-Benchmarks/Video-MME-v2", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 85.4, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.5", | |
| "short_name": "Kimi-K2.5", | |
| "provider": "moonshotai", | |
| "score": 61.1, | |
| "date": "2026-01-01" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.5-397B-A17B", | |
| "short_name": "Qwen3.5-397B-A17B", | |
| "provider": "Qwen", | |
| "score": 55.9, | |
| "date": "2026-02-16" | |
| } | |
| ] | |
| }, | |
| "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" | |
| } | |
| ] | |
| }, | |
| "skillsbench": { | |
| "name": "SkillsBench v1.1", | |
| "dataset": "benchflow/skillsbench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "zai-org/GLM-5.1", | |
| "short_name": "GLM-5.1", | |
| "provider": "zai-org", | |
| "score": 58.4, | |
| "date": "2026-04-03" | |
| }, | |
| { | |
| "model_id": "tencent/Hy3", | |
| "short_name": "Hy3", | |
| "provider": "tencent", | |
| "score": 55.3, | |
| "date": "2026-07-02" | |
| }, | |
| { | |
| "model_id": "moonshotai/Kimi-K2.6", | |
| "short_name": "Kimi-K2.6", | |
| "provider": "moonshotai", | |
| "score": 54.0, | |
| "date": "2026-04-14" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M3", | |
| "short_name": "MiniMax-M3", | |
| "provider": "MiniMaxAI", | |
| "score": 53.0, | |
| "date": "2026-06-02" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Pro", | |
| "short_name": "DeepSeek-V4-Pro", | |
| "provider": "deepseek-ai", | |
| "score": 50.1, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3.6-27B", | |
| "short_name": "Qwen3.6-27B", | |
| "provider": "Qwen", | |
| "score": 48.2, | |
| "date": "2026-04-21" | |
| }, | |
| { | |
| "model_id": "deepseek-ai/DeepSeek-V4-Flash", | |
| "short_name": "DeepSeek-V4-Flash", | |
| "provider": "deepseek-ai", | |
| "score": 44.7, | |
| "date": "2026-04-22" | |
| }, | |
| { | |
| "model_id": "MiniMaxAI/MiniMax-M2.7", | |
| "short_name": "MiniMax-M2.7", | |
| "provider": "MiniMaxAI", | |
| "score": 34.9, | |
| "date": "2026-04-09" | |
| } | |
| ] | |
| }, | |
| "WBench": { | |
| "name": "WBench", | |
| "dataset": "meituan-longcat/WBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "robbyant/lingbot-world-fast", | |
| "short_name": "lingbot-world-fast", | |
| "provider": "robbyant", | |
| "score": 78.8, | |
| "date": "2026-04-01" | |
| }, | |
| { | |
| "model_id": "tencent/HY-WorldPlay", | |
| "short_name": "HY-WorldPlay", | |
| "provider": "tencent", | |
| "score": 78.4, | |
| "date": "2025-12-12" | |
| }, | |
| { | |
| "model_id": "tencent/HunyuanVideo-1.5", | |
| "short_name": "HunyuanVideo-1.5", | |
| "provider": "tencent", | |
| "score": 78.2, | |
| "date": "2025-11-18" | |
| }, | |
| { | |
| "model_id": "Lightricks/LTX-2.3", | |
| "short_name": "LTX-2.3", | |
| "provider": "Lightricks", | |
| "score": 74.4, | |
| "date": "2026-03-04" | |
| }, | |
| { | |
| "model_id": "inspatio/world", | |
| "short_name": "world", | |
| "provider": "inspatio", | |
| "score": 74.3, | |
| "date": "2026-03-16" | |
| }, | |
| { | |
| "model_id": "meituan-longcat/LongCat-Video", | |
| "short_name": "LongCat-Video", | |
| "provider": "meituan-longcat", | |
| "score": 73.7, | |
| "date": "2025-10-24" | |
| }, | |
| { | |
| "model_id": "ACERobotics/kairos-sensenova-robot-4B-480P", | |
| "short_name": "kairos-sensenova-robot-4B-480P", | |
| "provider": "ACERobotics", | |
| "score": 70.7, | |
| "date": "2026-03-23" | |
| }, | |
| { | |
| "model_id": "tencent/Hunyuan-GameCraft-1.0", | |
| "short_name": "Hunyuan-GameCraft-1.0", | |
| "provider": "tencent", | |
| "score": 68.5, | |
| "date": "2025-08-13" | |
| } | |
| ] | |
| }, | |
| "Vaani_Benchmark_V1_0": { | |
| "name": "Vaani-Benchmark-V1.0", | |
| "dataset": "ARTPARK-IISc/Vaani-Benchmark-V1.0", | |
| "lower_is_better": true, | |
| "models": [ | |
| { | |
| "model_id": "ARTPARK-IISc/SraVaani-1.0", | |
| "short_name": "SraVaani-1.0", | |
| "provider": "ARTPARK-IISc", | |
| "score": 10.9, | |
| "date": "2026-02-02" | |
| }, | |
| { | |
| "model_id": "bharatgenai/Shrutam-2", | |
| "short_name": "Shrutam-2", | |
| "provider": "bharatgenai", | |
| "score": 17.4, | |
| "date": "2026-02-23" | |
| }, | |
| { | |
| "model_id": "bharatgenai/Shrutam-HindiASR-1.0", | |
| "short_name": "Shrutam-HindiASR-1.0", | |
| "provider": "bharatgenai", | |
| "score": 18.1, | |
| "date": "2025-06-02" | |
| }, | |
| { | |
| "model_id": "nvidia/nemotron-3.5-asr-streaming-0.6b", | |
| "short_name": "nemotron-3.5-asr-streaming-0.6b", | |
| "provider": "nvidia", | |
| "score": 20.2, | |
| "date": "2026-05-15" | |
| }, | |
| { | |
| "model_id": "Qwen/Qwen3-ASR-0.6B-hf", | |
| "short_name": "Qwen3-ASR-0.6B-hf", | |
| "provider": "Qwen", | |
| "score": 20.6, | |
| "date": "2026-06-26" | |
| }, | |
| { | |
| "model_id": "mistralai/Voxtral-Mini-3B-2507", | |
| "short_name": "Voxtral-Mini-3B-2507", | |
| "provider": "mistralai", | |
| "score": 21.3, | |
| "date": "2025-07-01" | |
| }, | |
| { | |
| "model_id": "shunyalabs/pingala-v1-universal", | |
| "short_name": "pingala-v1-universal", | |
| "provider": "shunyalabs", | |
| "score": 22.1, | |
| "date": "2025-07-28" | |
| }, | |
| { | |
| "model_id": "SPRINGLab/data2vec_aqc", | |
| "short_name": "data2vec_aqc", | |
| "provider": "SPRINGLab", | |
| "score": 23.7, | |
| "date": "2024-11-05" | |
| }, | |
| { | |
| "model_id": "google/gemma-4-12B", | |
| "short_name": "gemma-4-12B", | |
| "provider": "google", | |
| "score": 24.6, | |
| "date": "2026-05-23" | |
| }, | |
| { | |
| "model_id": "facebook/omniASR-LLM-1B", | |
| "short_name": "omniASR-LLM-1B", | |
| "provider": "facebook", | |
| "score": 25.6, | |
| "date": "2025-11-27" | |
| }, | |
| { | |
| "model_id": "openai/whisper-large-v3", | |
| "short_name": "whisper-large-v3", | |
| "provider": "openai", | |
| "score": 26.8, | |
| "date": "2023-11-07" | |
| } | |
| ] | |
| }, | |
| "RedlineBench": { | |
| "name": "RedlineBench", | |
| "dataset": "crosbylegal/RedlineBench", | |
| "lower_is_better": false, | |
| "models": [ | |
| { | |
| "model_id": "crosbylegal/gpt-5.5", | |
| "short_name": "gpt-5.5", | |
| "provider": "crosbylegal", | |
| "score": 50.5, | |
| "date": "2026-06-17" | |
| }, | |
| { | |
| "model_id": "crosbylegal/claude-fable-5", | |
| "short_name": "claude-fable-5", | |
| "provider": "crosbylegal", | |
| "score": 47.3, | |
| "date": "2026-06-17" | |
| }, | |
| { | |
| "model_id": "zai-org/GLM-5.2", | |
| "short_name": "GLM-5.2", | |
| "provider": "zai-org", | |
| "score": 45.7, | |
| "date": "2026-06-16" | |
| }, | |
| { | |
| "model_id": "crosbylegal/gemini-3.5-flash", | |
| "short_name": "gemini-3.5-flash", | |
| "provider": "crosbylegal", | |
| "score": 45.1, | |
| "date": "2026-06-17" | |
| }, | |
| { | |
| "model_id": "crosbylegal/claude-opus-4-8", | |
| "short_name": "claude-opus-4-8", | |
| "provider": "crosbylegal", | |
| "score": 44.4, | |
| "date": "2026-06-17" | |
| } | |
| ] | |
| } | |
| }, | |
| "logos": { | |
| "distil-whisper": "https://cdn-avatars.huggingface.co/v1/production/uploads/61f91cf54a8e5a275b2b3e7c/cUNzV7MAYi8lo9LsCYixp.png", | |
| "jdopensource": "https://cdn-avatars.huggingface.co/v1/production/uploads/68c0e2ab44ea28a974e3074b/g-4gTubd16qUtwmGZ0n4h.png", | |
| "PolarSeeker": "https://www.gravatar.com/avatar/55d9cc59db4e30206a307c186cc6d5bb?d=retro&size=100", | |
| "01-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6536187279f1de44b5e02d0f/-T8Xw0mX67_R73b7Re1y-.png", | |
| "ai21labs": "https://cdn-avatars.huggingface.co/v1/production/uploads/67baf6e5489cb4dc98a4bff4/9Rkvk1VGhK1woxWvhqDyb.png", | |
| "GSAI-ML": "https://cdn-avatars.huggingface.co/v1/production/uploads/624f909eac5dd186b01ac3f5/6tfvx3XT5Sx6YDGl7KUAU.jpeg", | |
| "InternScience": "https://cdn-avatars.huggingface.co/v1/production/uploads/65f2a4198404ac0e4c0f175f/XIPU4aCPBogXSrj6NrfLk.png", | |
| "Audio8": "https://cdn-avatars.huggingface.co/v1/production/uploads/64361bcaf81a16e74367d2e2/JQ6EmWRYtNLKFKr1MchAV.jpeg", | |
| "stepfun-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/644f7e6233ac8f46fa0b9e26/CmF2ocXhkr2UtHXgmwq7-.png", | |
| "openpangu": "https://cdn-avatars.huggingface.co/v1/production/uploads/66446e5f8c16ba43d3952eb8/_d3vpdB-0d6umBvgKND6m.png", | |
| "JGOS-Model": "https://cdn-avatars.huggingface.co/v1/production/uploads/66e54edddba1e4fee4500a5a/mHGK5-lBrEy1xKZmRqtfc.png", | |
| "moonshotai": "https://cdn-avatars.huggingface.co/v1/production/uploads/641c1e77c3983aa9490f8121/X1yT2rsaIbR9cdYGEVu0X.jpeg", | |
| "upstage": "https://cdn-avatars.huggingface.co/v1/production/uploads/649144feeb13c70f7671c603/bUxWC5jKltd-MyrrCNCv5.png", | |
| "exolabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/6505987dd5578ef7e2c69012/ldu1PyAG4nPdABx_m4O5r.png", | |
| "SPRINGLab": "https://cdn-avatars.huggingface.co/v1/production/uploads/65fd29f704a313d0597e01bb/BNz5HpwEo_DR9Et03MmEh.png", | |
| "Salesforce": "https://cdn-avatars.huggingface.co/v1/production/uploads/1602756670970-noauth.jpeg", | |
| "soundsgoodai": "https://www.gravatar.com/avatar/2e7e38eb40d5e4429d62544c73640cc6?d=retro&size=100", | |
| "Surpem": "https://cdn-avatars.huggingface.co/v1/production/uploads/69625a973527f984b1d0cec1/0jGoHYar6rASTHnqLnEzr.png", | |
| "nex-agi": "https://cdn-avatars.huggingface.co/v1/production/uploads/65435cad429b80b14922ab8d/a_O9jT_daz_NXTfxtcw6S.png", | |
| "Multilingual-Multimodal-NLP": "https://www.gravatar.com/avatar/cdabcf4c0ac6a92af4940fe0eb6924eb?d=retro&size=100", | |
| "HuggingFaceTB": "https://cdn-avatars.huggingface.co/v1/production/uploads/651e96991b97c9f33d26bde6/e4VK7uW5sTeCYupD0s_ob.png", | |
| "ATH-MaaS": "https://cdn-avatars.huggingface.co/v1/production/uploads/666a9d46a638e57bb7907929/CRc-9MCuH2q9hjTScyTPE.png", | |
| "ibm-granite": "https://cdn-avatars.huggingface.co/v1/production/uploads/639bcaa2445b133a4e942436/CEW-OjXkRkDNmTxSu8Egh.png", | |
| "tencent": "https://cdn-avatars.huggingface.co/v1/production/uploads/5dd96eb166059660ed1ee413/Lp3m-XLpjQGwBItlvn69q.png", | |
| "HelpingAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/6612aedf09f16e7347dfa7e1/jHRLPBTlyykFwrd6-Mak_.png", | |
| "UsefulSensors": "https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/TXG6u2PtGnohUXBQwj2Ks.png", | |
| "EleutherAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/1614054059123-603481bb60e3dd96631c9095.png", | |
| "abacusai": "https://cdn-avatars.huggingface.co/v1/production/uploads/63128dd099791aa61d180c72/dJ6uR23m09M-YEafBpmea.png", | |
| "facebook": "https://cdn-avatars.huggingface.co/v1/production/uploads/1592839207516-noauth.png", | |
| "meituan-longcat": "https://cdn-avatars.huggingface.co/v1/production/uploads/68a2a29ab9d4c5698e02c747/CDCAx7X7rXDt7xjI-DoxG.png", | |
| "dots-studio": "https://cdn-avatars.huggingface.co/v1/production/uploads/6807a1d6504547b3554b9c73/VpobPxqeksEQcMwA_lYS6.jpeg", | |
| "MuVeraAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/65ba8b772db90cb31145dbee/SLiEhXDF9tuzu5GswaqgR.png", | |
| "docling-project": "https://cdn-avatars.huggingface.co/v1/production/uploads/63c64dd877caf00391004e20/aWC70TyF2UhxyaUh1alpu.png", | |
| "RedHatAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/60466e4b4f40b01b66151416/cdABRow21BL0sl1vSVTPk.png", | |
| "zai-org": "https://cdn-avatars.huggingface.co/v1/production/uploads/62dc173789b4cf157d36ebee/i_pxzM2ZDo3Ub-BEgIkE9.png", | |
| "thinkingmachines": "https://cdn-avatars.huggingface.co/v1/production/uploads/680a76de1b8d08640089fab0/r60-JyW_pv4llgjEyDYj9.png", | |
| "robbyant": "https://cdn-avatars.huggingface.co/v1/production/uploads/67aeffda7330db26f93cd62f/ZTuImney4XzRmBHyUL47F.png", | |
| "ACERobotics": "https://cdn-avatars.huggingface.co/v1/production/uploads/6a4a45de4ba0a921a91a548a/MSX_HJLXaBYKy2ZByYTnN.png", | |
| "lightonai": "https://cdn-avatars.huggingface.co/v1/production/uploads/1651597775471-62715572ab9243b5d40cbb1d.png", | |
| "KDLAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/63687f5246919b9619c181b2/YzQFwtOJHPswxma-nG-vy.png", | |
| "crosbylegal": "https://cdn-avatars.huggingface.co/v1/production/uploads/6342f326aa45ed8ecf954c80/bjQGFQhNkm75Za3XOByzu.png", | |
| "KDEGroup": "https://cdn-avatars.huggingface.co/v1/production/uploads/688dc279b2d5ebe029e8aafe/GZis_Qxofgb67RkJsllJ6.png", | |
| "tiiuae": "https://cdn-avatars.huggingface.co/v1/production/uploads/61a8d1aac664736898ffc84f/AT6cAB5ZNwCcqFMal71WD.jpeg", | |
| "espnet": "https://cdn-avatars.huggingface.co/v1/production/uploads/1625224006560-60d28bba010d938bba5c6ae9.png", | |
| "OpenMOSS-Team": "https://cdn-avatars.huggingface.co/v1/production/uploads/61457b8deff2c9fdb4de4988/N5b9663zQ4uq5_OTNlnmw.png", | |
| "ByteDance-Seed": "https://cdn-avatars.huggingface.co/v1/production/uploads/6535c9e88bde2fae19b6fb25/flkDUqd_YEuFsjeNET3r-.png", | |
| "lerobot": "https://cdn-avatars.huggingface.co/v1/production/uploads/631ce4b244503b72277fc89f/pcLUTLsvMQiR-ujlTgLYF.png", | |
| "kyutai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6355a3c1805be5a8f30fea49/8xGdIOlfkopZfhbMitw_k.jpeg", | |
| "MiniMaxAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/676e38ad04af5bec20bc9faf/dUd-LsZEX0H_d4qefO_g6.jpeg", | |
| "mistralai": "https://cdn-avatars.huggingface.co/v1/production/uploads/634c17653d11eaedd88b314d/9OgyfKstSZtbmsmuG8MbU.png", | |
| "openbmb": "https://cdn-avatars.huggingface.co/v1/production/uploads/1670387859384-633fe7784b362488336bbfad.png", | |
| "meta-llama": "https://cdn-avatars.huggingface.co/v1/production/uploads/646cf8084eefb026fb8fd8bc/oCTqufkdTkjyGodsx1vo1.png", | |
| "skt": "https://cdn-avatars.huggingface.co/v1/production/uploads/6311a3f4d5a165db5d1d6862/XUPnKE9YqJcgORZoVOXMR.jpeg", | |
| "XiaomiMiMo": "https://cdn-avatars.huggingface.co/v1/production/uploads/680cb7d1233834890a64acee/5w_4aLfF-7MAyaIPOV498.jpeg", | |
| "openai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68783facef79a05727260de3/UPX5RQxiPGA-ZbBmArIKq.png", | |
| "Lightricks": "https://cdn-avatars.huggingface.co/v1/production/uploads/669524bcbcd81f395e8f60f6/0ynfqKEWMh_dn3h4ff1K5.png", | |
| "Qwen": "https://cdn-avatars.huggingface.co/v1/production/uploads/6215ca5692c0ecfba9186921/hrRM50-6XcdWgg2AKpENG.jpeg", | |
| "mistral-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/HAdAzcs1CDB9OxgxT2W9K.png", | |
| "ARTPARK-IISc": "https://cdn-avatars.huggingface.co/v1/production/uploads/66bb298fb7e24ecb59621609/qmvxRlx9oAu-j3xkEgMbK.png", | |
| "inclusionAI": "https://cdn-avatars.huggingface.co/v1/production/uploads/662e1f9da266499277937d33/fyKuazRifqiaIO34xrhhm.jpeg", | |
| "shunyalabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/689dc0f0e770d8d76631f8a5/MwkDIbJ3xqS2Cb5MwexLR.jpeg", | |
| "mteb": "https://cdn-avatars.huggingface.co/v1/production/uploads/5ff5943752c26e9bc240bada/OrZxdlg8doDNO2TZ6Q58G.png", | |
| "datalab-to": "https://cdn-avatars.huggingface.co/v1/production/uploads/67ab6afe315e622f597bf9e8/YOgg0gVYVXZC1PDIHFTWK.png", | |
| "internlm": "https://cdn-avatars.huggingface.co/v1/production/uploads/6432683407bad11484a68457/Q3Y0dL79GcsnaBCGRMooZ.png", | |
| "baidu": "https://cdn-avatars.huggingface.co/v1/production/uploads/64f187a2cc1c03340ac30498/TYYUxK8xD1AxExFMWqbZD.png", | |
| "Muse-research": "https://cdn-avatars.huggingface.co/v1/production/uploads/6a13468fa5de9d5481e61221/fquDZ0zSTMPVpPLHpStWE.png", | |
| "nvidia": "https://cdn-avatars.huggingface.co/v1/production/uploads/65df9200dc3292a8983e5017/Vs5FPVCH-VZBipV3qKTuy.png", | |
| "poolside": "https://cdn-avatars.huggingface.co/v1/production/uploads/699484cbe85a4b61cbc5ee0f/GpYWuz-CovEFgbPOW21dZ.png", | |
| "xlangai": "https://cdn-avatars.huggingface.co/v1/production/uploads/628f6e5ab90dde28ef57d293/PHIYPvE_tCM94SgoUzd7l.jpeg", | |
| "onnx-community": "https://cdn-avatars.huggingface.co/v1/production/uploads/61b253b7ac5ecaae3d1efe0c/BpiYJ-m5mXPXfjkzEt6yZ.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", | |
| "CohereLabs": "https://cdn-avatars.huggingface.co/v1/production/uploads/1678549441248-5e70f6048ce3c604d78fe133.png", | |
| "bharatgenai": "https://cdn-avatars.huggingface.co/v1/production/uploads/67b462a1f4f414c2b3e2bc2f/EnVeNWEIeZ6yF6ueZ7E3Y.jpeg", | |
| "FINAL-Bench": "https://cdn-avatars.huggingface.co/v1/production/uploads/6905bc786cb49b1f11d32728/VZmuKH-liifeL2GCXlwka.jpeg", | |
| "LGAI-EXAONE": "https://cdn-avatars.huggingface.co/v1/production/uploads/66a899a72f11aaf66001a8dc/UfdrP3GMo9pNT62BaMnhw.png", | |
| "infly": "https://cdn-avatars.huggingface.co/v1/production/uploads/63ed9862679c2cc40abb55d2/0n6g0jngiKkRjaEoAvPmM.png", | |
| "inspatio": "https://www.gravatar.com/avatar/0e9900671188e39a6c9589e882d99e9c?d=retro&size=100", | |
| "XCurOS": "https://cdn-avatars.huggingface.co/v1/production/uploads/699ed95abe63e5e1a61173ee/cHYWBNTarJWCAUvTjuH2U.png", | |
| "opendatalab": "https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png", | |
| "TIGER-Lab": "https://cdn-avatars.huggingface.co/v1/production/uploads/6313a86154e6e5d9f0f94e04/Noi3Qq3RYz8Jdq6BaFteq.png", | |
| "JetBrains": "https://cdn-avatars.huggingface.co/v1/production/uploads/6645d54b780d46f274dd4145/8RHS3MzGGBFWtH1-bynJ0.png", | |
| "deepseek-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png", | |
| "microsoft": "https://cdn-avatars.huggingface.co/v1/production/uploads/1583646260758-5e64858c87403103f9f1055d.png", | |
| "abr-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68e56cb442da034c65305b1b/DYHvx48l1-zt0G5VRj95j.png", | |
| "deepreinforce-ai": "https://cdn-avatars.huggingface.co/v1/production/uploads/68661bce022667cf9c7534fb/9BFOcjICEpj0xvyOHVp1h.png" | |
| }, | |
| "colors": { | |
| "01-ai": "#6366f1", | |
| "ACERobotics": "#0d9488", | |
| "ARTPARK-IISc": "#d97706", | |
| "ATH-MaaS": "#e11d48", | |
| "Audio8": "#7c3aed", | |
| "ByteDance-Seed": "#16a34a", | |
| "CohereLabs": "#2563eb", | |
| "EleutherAI": "#ea580c", | |
| "FINAL-Bench": "#8b5cf6", | |
| "GSAI-ML": "#0891b2", | |
| "HelpingAI": "#c026d3", | |
| "HuggingFaceTB": "#65a30d", | |
| "InternScience": "#dc2626", | |
| "JGOS-Model": "#0284c7", | |
| "JetBrains": "#a21caf", | |
| "KDEGroup": "#059669", | |
| "KDLAI": "#9333ea", | |
| "LGAI-EXAONE": "#ca8a04", | |
| "Lightricks": "#be185d", | |
| "MiniMaxAI": "#0369a1", | |
| "MuVeraAI": "#6366f1", | |
| "Multilingual-Multimodal-NLP": "#0d9488", | |
| "Muse-research": "#d97706", | |
| "OpenMOSS-Team": "#e11d48", | |
| "PolarSeeker": "#7c3aed", | |
| "Qwen": "#16a34a", | |
| "RedHatAI": "#2563eb", | |
| "SPRINGLab": "#ea580c", | |
| "Salesforce": "#8b5cf6", | |
| "Surpem": "#0891b2", | |
| "TIGER-Lab": "#c026d3", | |
| "UsefulSensors": "#65a30d", | |
| "XCurOS": "#dc2626", | |
| "XiaomiMiMo": "#0284c7", | |
| "abacusai": "#a21caf", | |
| "abr-ai": "#059669", | |
| "ai21labs": "#9333ea", | |
| "baidu": "#ca8a04", | |
| "bharatgenai": "#be185d", | |
| "crosbylegal": "#0369a1", | |
| "datalab-to": "#6366f1", | |
| "deepreinforce-ai": "#0d9488", | |
| "deepseek-ai": "#d97706", | |
| "distil-whisper": "#e11d48", | |
| "docling-project": "#7c3aed", | |
| "dots-studio": "#16a34a", | |
| "espnet": "#2563eb", | |
| "exolabs": "#ea580c", | |
| "facebook": "#8b5cf6", | |
| "google": "#0891b2", | |
| "ibm-granite": "#c026d3", | |
| "inclusionAI": "#65a30d", | |
| "infly": "#dc2626", | |
| "inspatio": "#0284c7", | |
| "internlm": "#a21caf", | |
| "jdopensource": "#059669", | |
| "kyutai": "#9333ea", | |
| "lerobot": "#ca8a04", | |
| "lightonai": "#be185d", | |
| "meituan-longcat": "#0369a1", | |
| "meta-llama": "#6366f1", | |
| "microsoft": "#0d9488", | |
| "mistral-community": "#d97706", | |
| "mistralai": "#e11d48", | |
| "moonshotai": "#7c3aed", | |
| "mteb": "#16a34a", | |
| "nex-agi": "#2563eb", | |
| "nvidia": "#ea580c", | |
| "onnx-community": "#8b5cf6", | |
| "openai": "#0891b2", | |
| "openbmb": "#c026d3", | |
| "opendatalab": "#65a30d", | |
| "openpangu": "#dc2626", | |
| "poolside": "#0284c7", | |
| "robbyant": "#a21caf", | |
| "shunyalabs": "#059669", | |
| "skt": "#9333ea", | |
| "soundsgoodai": "#ca8a04", | |
| "speechbrain": "#be185d", | |
| "stepfun-ai": "#0369a1", | |
| "tencent": "#6366f1", | |
| "thinkingmachines": "#0d9488", | |
| "tiiuae": "#d97706", | |
| "upstage": "#e11d48", | |
| "xlangai": "#7c3aed", | |
| "zai-org": "#16a34a" | |
| }, | |
| "generated_at": "2026-08-03T20:00:49.787749+00:00" | |
| } |