Graduate-Level Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.9Accuracy
44
Apr 29, 2026
98.74Accuracy
40
May 26, 2026
70.18Pass@1
31
Jun 11, 2026
61.1Score
16
Jun 16, 2026
36Pass@1
14
Mar 12, 2026
49.5Accuracy
12
May 27, 2026
50Accuracy
6
Apr 14, 2026
78.29Pass@10
6
Feb 26, 2026
76.7Pass@10
6
Feb 26, 2026
33.6Accuracy
3
Mar 4, 2026