Official benchmarks map / apex-agents
moonshotai/Kimi-K3.1-Pro is ranked first on the apex-agents leaderboard with 69.4, 69.3% ahead of moonshotai/Kimi-K3. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | moonshotai/Kimi-K3.1-Pro | moonshotai | 69.4 |
| 2 | moonshotai/Kimi-K3 | moonshotai | 41 |
| 3 | tencent/Hy4-preview | tencent | 37.1 |
| 4 | dots-studio/dots3-note-prev | dots-studio | 30.8 |
| 5 | MiniMaxAI/MiniMax-M3 | MiniMaxAI | 27.7 |
| 6 | tencent/Hy3 | tencent | 25.6 |
| 7 | zai-org/GLM-5 | zai-org | 17.2 |
| 8 | upstage/Solar-Open2-250B | upstage | 16.6 |
| 9 | moonshotai/Kimi-K2.5 | moonshotai | 14.4 |
| 10 | Qwen/Qwen3.5-397B-A17B | Qwen | 13.6 |
apex-agents 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/mercor/apex-agents
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.