Scientific Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
50.1Mean@1
34
Apr 14, 2026
44.3Accuracy
33
May 27, 2026
79Recall
32
May 26, 2026
53.67Accuracy
32
Apr 23, 2026
80.3Pass@1
32
Apr 24, 2026
64.58Pass@1
32
Feb 26, 2026
60.9Accuracy
30
Jun 30, 2026
61.19Accuracy
29
May 27, 2026
86.41Score
29
Feb 26, 2026
69.64Accuracy
28
Jun 5, 2026
44.1avg@16
28
Mar 20, 2026
66.2Accuracy
28
Apr 10, 2026
94.3mean@16
27
Jun 30, 2026
75.8Accuracy
27
May 19, 2026
75.9Success Rate
26
Jun 5, 2026
49Pass@1
25
May 22, 2026
77.7Pass@1
25
May 22, 2026
97.08Accuracy
25
May 8, 2026
72.1Accuracy (%)
25
Apr 21, 2026
63.1Accuracy
24
Jun 16, 2026
63.39Mean@16
24
May 28, 2026
71.48Mean@16
24
May 28, 2026
37.08Mean@16
24
May 28, 2026
73.74Accuracy
24
May 19, 2026
69.5Accuracy
24
Apr 21, 2026