Official benchmarks map / yc-bench
MiniMaxAI/MiniMax-M3 is ranked first on the yc-bench leaderboard with 2,100,000, 39.0% ahead of zai-org/GLM-5.1. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | MiniMaxAI/MiniMax-M3 | MiniMaxAI | 2,100,000 |
| 2 | zai-org/GLM-5.1 | zai-org | 1,510,772 |
| 3 | zai-org/GLM-5 | zai-org | 1,208,190 |
| 4 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 1,066,426 |
| 5 | moonshotai/Kimi-K2.6 | moonshotai | 511,137 |
| 6 | moonshotai/Kimi-K2.5 | moonshotai | 408,822 |
| 7 | zai-org/GLM-4.7 | zai-org | 398,410 |
| 8 | MiniMaxAI/MiniMax-M2.5 | MiniMaxAI | 230,465 |
| 9 | Qwen/Qwen3.5-397B-A17B | Qwen | 90,787 |
| 10 | Qwen/Qwen3.5-122B-A10B | Qwen | 0 |
yc-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/collinear-ai/yc-bench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.