Official benchmarks map / terminal-bench
moonshotai/Kimi-K3.1-Pro is ranked first on the terminal-bench leaderboard with 65.7, 42.7% ahead of inclusionAI/Ling-3.1-flash. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 65.7 |
| 2 | inclusionAI/Ling-3.1-flash | inclusionAI | 46.03 |
| 3 | deepseek-ai/DeepSeek-V4.1-Flash-1017 | deepseek-ai | 42.3 |
| 4 | zai-org/GLM-5.3 | zai-org | 41.9 |
| 5 | mistralai/Mistral-Large-4-1T-A52B | mistralai | 41 |
| 6 | MiniMaxAI/MiniMax-M3.1-Flash | MiniMaxAI | 38.1 |
| 7 | XiaomiMiMo/MiMo-V2.6-Pro-RL | XiaomiMiMo | 34.9 |
| 8 | stepfun-ai/Step-5-Preview | stepfun-ai | 33.3 |
| 9 | inclusionAI/Ling-3.1-flash-1019 | inclusionAI | 32.8 |
| 10 | deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai | 31.2 |
terminal-bench 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
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.