| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| IPhO Mechanics | Qwen3-30B + RL (synthetic) | Accuracy40 | 10 | 5d ago | |
| HCV | Qwen3-30B + RL (synthetic) | Accuracy59 | 10 | 5d ago | |
| Synthetic Symbolic | Qwen2.5-32B + RL (synthetic) | Accuracy10.4 | 10 | 5d ago | |
| Synthetic Numeric | Qwen2.5-32B + RL (synthetic) | Accuracy21.9 | 10 | 5d ago | |
| PhyBench | Ministral 3 | pass@1626 | 6 | 1mo ago | |
| PhysReason | ARYA | Overall Score73.3 | 4 | 26d ago | |
| PHYSICS | Qwen2.5 32B + RL (synthetic) | Mean Accuracy43.09 | 2 | 5d ago |