Official benchmarks map / terminal-bench-2.1
deepseek-ai/DeepSeek-V4.1-Flash is ranked first on the terminal-bench-2.1 leaderboard with 90.6, 0.8% ahead of XiaomiMiMo/MiMo-V2.6-Pro-RL. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai | 90.6 |
| 2 | XiaomiMiMo/MiMo-V2.6-Pro-RL | XiaomiMiMo | 89.9 |
| 3 | zai-org/GLM-5.3 | zai-org | 88.2 |
| 4 | deepseek-ai/DeepSeek-V4-Pro-0813 | deepseek-ai | 87.9 |
| 5 | XiaomiMiMo/MiMo-V2.6-Flash-RL | XiaomiMiMo | 87.6 |
| 6 | Qwen/Qwen3.8-2.4T-A95B | Qwen | 86.6 |
| 7 | ornith-ai/Ornith-1.5-397B | ornith-ai | 86.1 |
| 8 | tencent/Hy4-preview | tencent | 85.4 |
| 9 | ornith-ai/Ornith-1.5-397B | ornith-ai | 85.2 |
| 10 | zai-org/GLM-5.3-Flash | zai-org | 84.3 |
terminal-bench-2.1 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/harborframework/terminal-bench-2.1
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.