Official benchmarks map / physical-engineerings-last-exam
zai-org/GLM-5.2 is ranked first on the physical-engineerings-last-exam leaderboard with 26, 52.9% ahead of deepseek-ai/DeepSeek-V4.1-Flash. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | zai-org/GLM-5.2 | zai-org | 26 |
| 2 | deepseek-ai/DeepSeek-V4.1-Flash | deepseek-ai | 17 |
| 3 | Qwen/Qwen3-Coder-480B-A35B-Instruct | Qwen | 6.1 |
| 4 | moonshotai/Kimi-K2-Thinking | moonshotai | 5.7 |
| 5 | MiniMaxAI/MiniMax-M2 | MiniMaxAI | 4.8 |
| 6 | openai/gpt-oss-120b | openai | 3.8 |
| 7 | Qwen/Qwen3-Next-80B-A3B-Instruct | Qwen | 2.6 |
physical-engineerings-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/google/physical-engineerings-last-exam
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.