Official benchmarks map / chi-bench
zai-org/GLM-5.1 is ranked first on the chi-bench leaderboard with 18.7, 19.9% ahead of moonshotai/Kimi-K2.6. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | zai-org/GLM-5.1 | zai-org | 18.7 |
| 2 | moonshotai/Kimi-K2.6 | moonshotai | 15.6 |
| 3 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 14.2 |
chi-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/actava/chi-bench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.