Official benchmarks map / ResearchClawBench
zai-org/GLM-5.2 is ranked first on the ResearchClawBench leaderboard with 20.71, 13.8% ahead of zai-org/GLM-5.1. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | zai-org/GLM-5.2 | zai-org | 20.71 |
| 2 | zai-org/GLM-5.1 | zai-org | 18.19 |
| 3 | moonshotai/Kimi-K2.6 | moonshotai | 18 |
| 4 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 17.12 |
| 5 | XiaomiMiMo/MiMo-V2.5 | XiaomiMiMo | 16.91 |
| 6 | Qwen/Qwen3.5-397B-A17B | Qwen | 14.23 |
| 7 | moonshotai/Kimi-K2.5 | moonshotai | 13.96 |
ResearchClawBench 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/InternScience/ResearchClawBench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.