Official benchmarks map / agents-last-exam
moonshotai/Kimi-K3.1-Pro is ranked first on the agents-last-exam leaderboard with 43.2, 22.0% ahead of deepseek-ai/DeepSeek-V4.1-Flash-1017. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 43.2 |
| 2 | deepseek-ai/DeepSeek-V4.1-Flash-1017 | deepseek-ai | 35.4 |
| 3 | XiaomiMiMo/MiMo-V2.6-Pro-RL | XiaomiMiMo | 31.6 |
| 4 | MiniMaxAI/MiniMax-M3.1-Flash | MiniMaxAI | 29.6 |
| 5 | moonshotai/Kimi-K3 | moonshotai | 28.29 |
| 6 | XiaomiMiMo/MiMo-V2.6-Flash-RL | XiaomiMiMo | 27.6 |
| 7 | moonshotai/Kimi-K3 | moonshotai | 26.97 |
| 8 | Qwen/Qwen3.8-Flash-Next | Qwen | 24.3 |
| 9 | Qwen/Qwen3.8-27B | Qwen | 20.39 |
| 10 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 12.39 |
agents-last-exam 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/agents-last-exam/agents-last-exam
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.