Scientific Reasoning on SciBench Physics
82.4Accuracy
Single Agent
Updated 8d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 82.4 | |
2026.05 | 76.5 | |
2026.05 | 71 | |
2026.05 | 68.4 | |
2026.05 | 67.6 | |
2026.05 | 67.6 | |
2026.05 | 64.7 | |
2026.05 | 61.8 | |
2026.05 | 61.8 | |
2026.05 | 61.8 | |
2026.05 | 61.8 | |
2026.05 | 61.8 | |
2026.05 | 60.2 | |
2026.05 | 58.8 | |
2026.05 | 58.8 | |
2026.05 | 58.8 | |
2026.05 | 41.2 | |
2026.05 | 36.7 | |
2026.05 | 35.3 | |
2026.05 | 23.5 |