Hugging Face Official Benchmarks: Daily Update 2026-11-06
aibenchmarkshuggingfacellm
This is the daily update of the Hugging Face Official Benchmarks map, which reads every Hugging Face official benchmark leaderboard straight from the public API.
As of 2026-11-06 (KST): 58 official benchmarks, 1,313 leaderboard entries.
What changed since the last snapshot
- hle: new #1 moonshotai/Kimi-K3.1-Pro (score 70), previously deepseek-ai/DeepSeek-V4.1-Flash.
- apex-agents: new #1 moonshotai/Kimi-K3.1-Pro (score 69.4), previously moonshotai/Kimi-K3.
- terminal-bench: new #1 moonshotai/Kimi-K3.1-Pro (score 65.7), previously inclusionAI/Ling-3.1-flash.
- agents-last-exam: new #1 moonshotai/Kimi-K3.1-Pro (score 43.2), previously deepseek-ai/DeepSeek-V4.1-Flash-1017.
- terminal-bench-science: new #1 moonshotai/Kimi-K3.1-Pro (score 38.1), previously deepseek-ai/DeepSeek-V4.1-Flash-1017.
- VDEBench: new #1 sensenova/SenseNova-U1.5-8B-MoT (score 0.828), previously black-forest-labs/FLUX.2-klein-4B.
- MMMU_Pro: new #1 moonshotai/Kimi-K3.1-Pro (score 90), previously FINAL-Bench/Darwin-180B-RSI.
- OmniCompass: new #1 moonshotai/Kimi-K3.1-Pro (score 43.5), previously moonshotai/Kimi-K3.
- 33 new leaderboard entries across all boards.
Organizations by number of #1 spots
| Rank | Organization | #1 spots |
|---|---|---|
| 1 | FINAL-Bench | 11 |
| 2 | moonshotai | 8 |
| 3 | zai-org | 5 |
| 4 | deepseek-ai | 3 |
| 5 | MiniMaxAI | 2 |
| 6 | PCL-RSI-lab | 2 |
| 7 | Qwen | 2 |
| 8 | XiaomiMiMo | 2 |
| 9 | inclusionAI | 2 |
| 10 | ornith-ai | 2 |
Current #1 on every official benchmark
| Benchmark | #1 model | Score | Entries |
|---|---|---|---|
| MMLU-Pro | internlm/Intern-S2-Preview-397B | 89.75 | 163 |
| gpqa | FINAL-Bench/Darwin-180B-RSI | 94.44 | 123 |
| hle | moonshotai/Kimi-K3.1-Pro | 70 | 102 |
| SWE-bench_Verified | ornith-ai/Ornith-1.5-397B | 86 | 78 |
| open-asr-leaderboard | Edge0/ARK-ASR-3B | 4.76 | 65 |
| SWE-bench_Pro | PCL-RSI-lab/Seshat-agent | 94.94 | 55 |
| WildClawBench | Qwen/Qwen3.8-2.4T-A95B | 708 | 52 |
| terminal-bench-2.0 | mindlab-research/Macaron-V1-Venti | 87.6 | 44 |
| terminal-bench-2.1 | deepseek-ai/DeepSeek-V4.1-Flash | 90.6 | 43 |
| aime_2026 | deepseek-ai/DeepSeek-V4.1-Flash | 100 | 39 |
| ParseBench | KDLAI/KDL-Frontier-Parser-nano-v2 | 78.95935214038234 | 34 |
| SWE-bench_Multilingual | inclusionAI/Ling-3.1-flash | 88.5 | 34 |
| deep-swe | PCL-RSI-lab/Seshat-agent | 90.3 | 32 |
| ScreenSpot-Pro | beipo-ai/NorthCUA-Pro | 93.3 | 31 |
| gsm8k | XiaomiMiMo/MiMo-V2.5-Pro | 99.6 | 28 |
| hmmt_feb_2026 | FINAL-Bench/Darwin-180B-RSI | 100 | 25 |
| OmniCompass | moonshotai/Kimi-K3.1-Pro | 43.5 | 25 |
| olmOCR-bench | SoMarkAI/OXR-1.0 | 87.84 | 24 |
| Claw-Eval | ornith-ai/Ornith-1.5-397B | 81.4 | 22 |
| Real5-OmniDocBench | PaddlePaddle/PaddleOCR-VL-1.6 | 93.19 | 18 |
| Toolathlon | XiaomiMiMo/MiMo-V2.6-Pro-RL | 76.9 | 18 |
| terminal-bench | moonshotai/Kimi-K3.1-Pro | 65.7 | 16 |
| VDEBench | sensenova/SenseNova-U1.5-8B-MoT | 0.828 | 16 |
| MDPBench | FINAL-Bench/Darwin-180B-RSI | 83.65 | 16 |
| RedlineBench | crosbylegal/gemini-4-argon | 59.5 | 15 |
| apex-agents | moonshotai/Kimi-K3.1-Pro | 69.4 | 14 |
| MMMU_Pro | moonshotai/Kimi-K3.1-Pro | 90 | 14 |
| ExtractBench | FINAL-Bench/Darwin-180B-RSI-R3 | 90.29 | 12 |
| skillsbench | inclusionAI/Ling-3.1-flash | 68.7 | 12 |
| LEXam-hard | FINAL-Bench/Darwin-180B-RSI | 45.72 | 12 |
| agents-last-exam | moonshotai/Kimi-K3.1-Pro | 43.2 | 11 |
| Vaani-Benchmark-V1.0 | gnani/gnani | 13 | 11 |
| LEXam | FINAL-Bench/Darwin-180B-RSI | 68.94 | 10 |
| yc-bench | MiniMaxAI/MiniMax-M3 | 2100000 | 10 |
| typed-decisions | FINAL-Bench/Darwin-27B-ZTC-v5 | 0.812 | 9 |
| terminal-bench-science | moonshotai/Kimi-K3.1-Pro | 38.1 | 9 |
| Long-Horizon-Terminal-Bench | moonshotai/Kimi-K3 | 6 | 9 |
| WBench | robbyant/lingbot-world-fast | 78.8 | 8 |
| physical-engineerings-last-exam | zai-org/GLM-5.2 | 26 | 7 |
| ResearchClawBench | zai-org/GLM-5.2 | 20.709230769230768 | 7 |
| Video-MME-v2 | MiniMaxAI/MiniMax-M3 | 85.4 | 7 |
| ifstruct-v1.0 | FINAL-Bench/Darwin-180B-RSI | 98.95 | 6 |
| EvasionBench | zai-org/GLM-4.7 | 82.91 | 5 |
| cwe-bench | deepseek-ai/DeepSeek-V4.1-Flash-1017 | 57 | 4 |
| arguana | FINAL-Bench/Darwin-180B-RSI-R3 | 83.83 | 4 |
| chi-bench | zai-org/GLM-5.1 | 18.7 | 3 |
| mmi | Qwen/Qwen3-Omni-30B-A3B-Instruct | 13.54 | 3 |
| safeagents-judge-bench | vllm-sr/d3-ultra | 0.756 | 2 |
| BRIGHT | FINAL-Bench/Darwin-BRIGHT-Retriever | 0.307 | 2 |
| APEX-v1-extended | zai-org/GLM-4.7 | 51.7 | 2 |
| decision-index-leaderboard | FINAL-Bench/Darwin-27B-ZTC | 63.03 | 1 |
| vlabench_primitive_ft_lerobot_video | nvidia/GR00T-N1-2B | 39.7 | 1 |
How to read this
Most leaderboard entries are self-reported by model authors, and evaluation settings differ between submissions (sampling, voting, thinking budget). An entry is marked verified only where Hugging Face marks it so. Ties at rank 1 count for each tied organization.
Disclosure: QuantID is a technology partner of VIDRAFT, whose FINAL-Bench organization appears in these rankings. This post reports the public leaderboard data as published on Hugging Face; it is not an independent evaluation.