Scientific Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
62.6Accuracy
24
Apr 21, 2026
74.4Avg@16
24
Jun 30, 2026
73.4Accuracy
24
Jun 17, 2026
63Accuracy
22
Jun 19, 2026
68.2Accuracy
22
Apr 21, 2026
57.34Mean Accuracy
22
Jul 7, 2026
79.2Pass@1
22
Feb 26, 2026
68.3Mean@1
22
Feb 26, 2026
61.6Accuracy
21
Apr 8, 2026
91.94P@16
21
Feb 26, 2026
73.21Overall Accuracy
21
Mar 4, 2026
83.78Average Score @8
20
Jun 25, 2026
82.4Accuracy
20
May 26, 2026
73.2Accuracy
20
May 26, 2026
73.93Score
20
Feb 26, 2026
66.19Score
20
Feb 26, 2026
35.7Biology Score
19
Apr 23, 2026
69.5pass@1
19
Mar 4, 2026
85.4Score
18
Jun 23, 2026
43.43Pass@1 Accuracy
18
Jun 16, 2026
81Chemistry Score
18
Jun 4, 2026
43.2Pass@1 Accuracy
18
May 22, 2026
52.02Avg@4 Accuracy
18
Apr 29, 2026
3.26SampleQA Score
18
Feb 26, 2026
58.13Accuracy (avg@32)
18
Feb 26, 2026