Physics Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.4Average Accuracy
41
Jul 7, 2026
88.5Accuracy
20
Jul 9, 2026
11.63Success Metric
20
Jun 17, 2026
80.15C-Eval Score
18
Apr 21, 2026
4.5Acceptance Length
12
May 12, 2026
40Accuracy
10
Apr 14, 2026
59Accuracy
10
Apr 14, 2026
10.4Accuracy
10
Apr 14, 2026
21.9Accuracy
10
Apr 14, 2026
44.5Accuracy
6
Apr 23, 2026
88.8Accuracy
6
Apr 23, 2026
89Accuracy
6
Apr 23, 2026
60.4Accuracy (hep-th)
6
Apr 23, 2026
61.4Accuracy (Textbooks)
6
Apr 23, 2026
26pass@16
6
Feb 26, 2026
73.3Overall Score
4
Mar 24, 2026
34Accuracy
2
Jun 30, 2026
32Accuracy
2
Jun 30, 2026
44Accuracy
2
Jun 30, 2026
43.09Mean Accuracy
2
Apr 14, 2026