Official benchmarks map / skillsbench
inclusionAI/Ling-3.1-flash is ranked first on the skillsbench leaderboard with 68.7, 9.2% ahead of tencent/Hy4-preview. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | inclusionAI/Ling-3.1-flash | inclusionAI | 68.7 |
| 2 | tencent/Hy4-preview | tencent | 62.9 |
| 3 | zai-org/GLM-5.1 | zai-org | 58.4 |
| 4 | tencent/Hy3 | tencent | 55.3 |
| 5 | moonshotai/Kimi-K2.6 | moonshotai | 54 |
| 6 | MiniMaxAI/MiniMax-M3 | MiniMaxAI | 53 |
| 7 | dots-studio/dots3-note-prev | dots-studio | 52.8 |
| 8 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 50.1 |
| 9 | Qwen/Qwen3.6-27B | Qwen | 48.2 |
| 10 | deepseek-ai/DeepSeek-V4-Flash | deepseek-ai | 44.7 |
skillsbench 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/benchflow/skillsbench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.