Cross-task physical reasoning on PHYRE Set 3 (test)
52Pass@1
Human
Updated 17d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.07 | 52 | 73.2 | 82 | |
2026.07 | 33.8 | 41.2 | 46.6 | |
2026.07 | 30 | 45.6 | 51.2 | |
2026.07 | 27.8 | 48.4 | 55.4 | |
2026.07 | 21.8 | 34 | 39.2 | |
2026.07 | 17.6 | 36.8 | 45.2 | |
2026.07 | 14.2 | 29.4 | 37.6 | |
2026.07 | 5 | 10.4 | 15.4 | |
2026.07 | 4.4 | 8.6 | 14 | |
2026.07 | 3 | 7.4 | 10.8 | |
2026.07 | 2.4 | 6 | 10.8 | |
2026.07 | 2.2 | 7.8 | 10.2 | |
2026.07 | 1.6 | 4 | 7.4 |