Official benchmarks map / OmniCompass
moonshotai/Kimi-K3.1-Pro is ranked first on the OmniCompass leaderboard with 43.5, 9.8% ahead of moonshotai/Kimi-K3. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 43.5 |
| 2 | moonshotai/Kimi-K3 | moonshotai | 39.6 |
| 3 | Qwen/Qwen3.5-397B-A17B | Qwen | 37.2 |
| 4 | Qwen/Qwen3-VL-235B-A22B-Instruct | Qwen | 34.5 |
| 5 | Qwen/Qwen3.5-122B-A10B | Qwen | 33.5 |
| 6 | zai-org/GLM-5.3-Flash | zai-org | 30.8 |
| 7 | Qwen/Qwen3.8-27B | Qwen | 29.6 |
| 8 | Qwen/Qwen3.5-27B | Qwen | 28.9 |
| 9 | Qwen/Qwen3.6-27B | Qwen | 28.6 |
| 10 | Qwen/Qwen3.6-35B-A3B | Qwen | 28.5 |
OmniCompass 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/VCLab-PolyU/OmniCompass
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.