Physical Reasoning on PhyX
48.6Accuracy
SketchThinker-R1-7B
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 48.6 | 75.3 | 0.645 | - | |
2026.01 | 46.7 | 225.1 | 0.207 | - | |
2026.01 | 46.3 | 163.7 | 0.283 | - | |
2026.01 | 45.5 | 132.7 | 0.343 | - | |
2026.01 | 45.1 | 153.4 | 0.294 | - | |
2026.01 | 43.8 | 117.5 | 0.373 | - | |
2026.04 | 42.9 | - | - | - | |
2026.01 | 42.4 | 73.4 | 0.578 | - | |
2026.01 | 42.2 | 85.2 | 0.495 | - | |
2026.04 | 41.5 | - | - | - | |
2026.04 | 41.5 | - | - | - | |
2026.04 | 39.7 | - | - | - | |
2026.04 | 39.5 | - | - | - | |
2026.04 | 37.4 | - | - | - | |
2026.01 | 35.1 | 67.3 | 0.522 | - | |
2026.01 | 34.8 | 173.2 | 0.201 | - | |
2026.01 | 33.2 | 82.2 | 0.404 | - | |
2026.01 | 33.1 | 93.2 | 0.355 | - | |
2026.01 | 32.6 | 92.1 | 0.354 | - | |
2026.01 | 32.5 | 71.2 | 0.456 | - | |
2026.01 | 32.2 | 83.4 | 0.386 | - | |
2026.04 | 32.1 | - | - | - | |
2026.01 | 31.5 | 63.6 | 0.495 | - | |
2026.04 | 30.6 | - | - | - | |
2025.12 | - | - | - | 28.3 | |
2025.12 | - | - | - | 31.1 | |
2025.12 | - | - | - | 24 | |
2025.12 | - | - | - | 33 | |
2025.12 | - | - | - | 41.9 |