Science Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.92Accuracy
10
May 11, 2026
81.2BCA
9
May 13, 2026
33.3Accuracy
9
May 13, 2026
62.9FRS Score
9
Apr 15, 2026
52Pass@1
8
Apr 21, 2026
79.48Accuracy
8
Mar 4, 2026
32.25Accuracy
7
Jun 26, 2026
95Accuracy
6
Jul 1, 2026
90.5Accuracy
6
Jul 1, 2026
75.7Accuracy
6
Jun 30, 2026
92.08TPS
6
Apr 9, 2026
65.12Accuracy
6
Feb 26, 2026
70Accuracy
6
Feb 26, 2026
37.1Accuracy
5
Apr 28, 2026
0.751Hypervolume
4
Mar 12, 2026
73Pass@1
3
Feb 26, 2026
64Pass@1
3
Feb 26, 2026