Official benchmarks map / MMMU_Pro
moonshotai/Kimi-K3.1-Pro is ranked first on the MMMU_Pro leaderboard with 90, 7.0% ahead of moonshotai/Kimi-K3.1-Pro. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 90 |
| 2 | moonshotai/Kimi-K3.1-Pro | moonshotai | 84.1 |
| 3 | FINAL-Bench/Darwin-180B-RSI | FINAL-Bench | 79.48 |
| 4 | moonshotai/Kimi-K2.6 | moonshotai | 79.4 |
| 5 | moonshotai/Kimi-K2.5 | moonshotai | 78.5 |
| 6 | internlm/Intern-S2-Preview | internlm | 76.88 |
| 7 | Qwen/Qwen3.6-27B | Qwen | 75.8 |
| 8 | Qwen/Qwen3.6-35B-A3B | Qwen | 75.3 |
| 9 | Qwen/Qwen3.5-27B | Qwen | 75 |
| 10 | ATH-MaaS/Ovis2.6-80B-A3B | ATH-MaaS | 66.3 |
MMMU_Pro is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/MMMU/MMMU_Pro
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.