Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Cross-task physical reasoning on PHYRE Set 2 (test)

0.472Pass@1

Human

-0.002240.120880.2440.36712Jul 7, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.07
0.4720.8220.92
2026.07
0.260.3680.418
2026.07
0.220.3680.42
2026.07
0.1980.390.472
2026.07
0.1920.3020.352
2026.07
0.1780.3120.362
2026.07
0.1460.3440.452
2026.07
0.0480.0960.144
2026.07
0.0420.1240.172
2026.07
0.0360.0880.122
2026.07
0.0280.0840.13
2026.07
0.0180.0440.078
2026.07
0.0160.0380.056