STEM
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.1Pass@1
7
Jul 2, 2026
54.6Pass@1
7
Jul 2, 2026
81.8Pass@1
7
Jul 2, 2026
61.9Pass@1
7
Jul 2, 2026
72Pass@1
7
Jul 2, 2026
81Pass@1
7
Jul 2, 2026
87Pass@1
7
Jul 2, 2026
17.4Pass@1
6
Feb 26, 2026
37.8Pass@1
6
Feb 26, 2026
70.8Accuracy
6
Feb 26, 2026
44.8pass@1
6
Feb 26, 2026
69.7Pass@1
6
Feb 26, 2026
80.8pass@1
6
Feb 26, 2026
63.2Score
5
Jul 2, 2026
92.4Score
5
Jul 2, 2026
44.56Accuracy
3
Jun 30, 2026