Official benchmarks map / hle
moonshotai/Kimi-K3.1-Pro is ranked first on the hle leaderboard with 70, 9.5% ahead of deepseek-ai/DeepSeek-V4.1-Flash. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 70 |
| 2 | deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai | 63.9 |
| 3 | zai-org/GLM-5.3 | zai-org | 62.5 |
| 4 | meta-models/Muse-Spark-Open-816B-A42B | meta-models | 61 |
| 5 | ornith-ai/Ornith-1.5-397B | ornith-ai | 56.1 |
| 6 | moonshotai/Kimi-K3 | moonshotai | 56 |
| 7 | tencent/Hy4-preview | tencent | 55.4 |
| 8 | zai-org/GLM-5.3-Flash | zai-org | 55.3 |
| 9 | inference-optimization/GLM-5.3-Flash-MXFP4xFP8 | inference-optimization | 55.3 |
| 10 | zai-org/GLM-5.2 | zai-org | 54.7 |
hle 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/cais/hle
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.