基准测试
Graduate-level physics, chemistry and biology questions written to be Google-proof.
分数历史 →| # | 模型 | 分数 |
|---|---|---|
| 1 | GPT-6 Astra | 96% |
| 2 | Gemini 3.1 Pro | 94.3% |
| 3 | GPT 5.6-Sol | 94.1% |
| 4 | Claude Opus 5 | 93.4% |
| 5 | Kimi K3 | 92.9% |
| 6 | DeepSeek V4-Pro 0813 | 92.4% |
| 7 | DeepSeek V4.1-Flash 0910 | 90.9% |
| 8 | DeepSeek V4-Flash 0731 | 89.9% |
| 9 | GLM 5.3 | 88.1% |