Cross-task physical reasoning on PHYRE Set 1 (test)
52Pass@1
Human
Updated 17d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.07 | 52 | 75.8 | 80 | |
2026.07 | 38.2 | 52.4 | 59.4 | |
2026.07 | 32.6 | 43.4 | 47.6 | |
2026.07 | 27.8 | 47.2 | 55.2 | |
2026.07 | 27 | 43.6 | 51.2 | |
2026.07 | 17.6 | 38 | 47 | |
2026.07 | 17 | 34 | 41.6 | |
2026.07 | 6.4 | 13.2 | 18.6 | |
2026.07 | 4.4 | 9.4 | 13.4 | |
2026.07 | 4.2 | 10.4 | 14.2 | |
2026.07 | 2 | 2.6 | 3 | |
2026.07 | 0.6 | 4 | 6.2 | |
2026.07 | 0.2 | 0.8 | 20 |