Scientific Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
53.8Accuracy
18
Feb 26, 2026
54.96Score
18
Feb 26, 2026
76.4Average Score
17
Jul 3, 2026
44.6Average Score
17
Feb 26, 2026
612pass@1
17
Feb 26, 2026
32.4Pass@1
17
Feb 26, 2026
56.2Accuracy
16
May 14, 2026
70.8Pass@1
16
Apr 23, 2026
40.91Accuracy
16
Apr 7, 2026
78Average Score @16 (1h)
16
Apr 3, 2026
69.5Avg@16 (1h)
16
Apr 3, 2026
71.6Avg Score @16 (1h)
16
Apr 3, 2026
91.96Pass@16
16
Feb 26, 2026
0.609Accuracy
15
Jul 2, 2026
70.851-σ Score
15
May 22, 2026
55.19Average@32
15
May 11, 2026
44.7Accuracy
15
Feb 27, 2026
58.5Average Reward
15
Jun 4, 2026
57.9Overall Accuracy
15
Jul 3, 2026
44.36pass@3
14
Jun 4, 2026
54.5Pass Rate
14
May 26, 2026
33.9Pass Rate
14
May 26, 2026
26.5Pass Rate
14
May 26, 2026
49.08Accuracy
14
May 22, 2026
87.3Accuracy
14
Feb 26, 2026