Scientific Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
83Accuracy
10
Jun 30, 2026
47.16Mean@32
10
Jun 11, 2026
69.58Exact Match
10
Jun 2, 2026
7.4Accuracy
10
May 12, 2026
34.6Pass@1
10
Apr 14, 2026
31.1Pass@1 Accuracy
10
Apr 14, 2026
33.27Avg.@8
10
Apr 14, 2026
68.7Accuracy
10
Mar 24, 2026
87.64Mechanics Score 1
10
Feb 26, 2026
71.6Average Reward
10
Feb 26, 2026
72.7Accuracy (MV)
9
Jul 1, 2026
94.3Avg@16
9
Jun 16, 2026
58.6Biology Score
9
Mar 24, 2026
60.6Pass@1
9
Feb 26, 2026
51.12Score
9
Feb 26, 2026
35.69Score
9
Feb 26, 2026
36.49Score
9
Feb 26, 2026
64.41Score
9
Feb 26, 2026
63.54Score
9
Feb 26, 2026
13.6Score
9
Feb 26, 2026
13.2Score
9
Feb 26, 2026
50.05Score
9
Feb 26, 2026
61.75Score
9
Feb 26, 2026
65.1Score
9
Feb 26, 2026
83.61Score
9
Feb 26, 2026