Scientific Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98Accuracy
281
Jul 9, 2026
84.4Accuracy
131
Jun 9, 2026
94.4Accuracy
83
Jul 1, 2026
54.44Accuracy
51
Jul 8, 2026
91.4Accuracy
35
May 26, 2026
1.58Average Inference Time (s)
30
Mar 25, 2026
33.48Score
28
Mar 23, 2026
79.45Accuracy
27
Apr 30, 2026
53.03Accuracy (ACC)
22
May 13, 2026
79.29Pass@8
21
May 20, 2026
38.5Accuracy (mean@4)
21
May 12, 2026
81.52Accuracy
20
Jul 7, 2026
23.04P@1
20
May 22, 2026
14.43Accuracy (GPQA-D)
20
Feb 27, 2026
46.86F1 Score
19
Feb 26, 2026
46.55F1 Score
19
Feb 26, 2026
53.1Accuracy (ACC)
18
Jun 5, 2026
18.2pass@1
18
Feb 26, 2026
98.39LLM Trust Score
16
May 22, 2026
84.61Accuracy
16
Jul 1, 2026
88.6Accuracy
16
May 29, 2026
49Pass@1
16
Feb 26, 2026
68.5Accuracy (Biology)
15
Jul 3, 2026
65.8Biology Domain Score
14
May 27, 2026
65.2pass@1
14
May 14, 2026