Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
35.47Accuracy
9
Feb 26, 2026
37.3Accuracy
8
Jul 3, 2026
77.4Best-of-K Accuracy
8
Jun 23, 2026
61.03Pass@1
8
Jun 12, 2026
79.65Accuracy
8
Jun 9, 2026
56Accuracy
8
Jun 1, 2026
61.9Accuracy
8
Jun 1, 2026
34.4Accuracy
8
Jun 1, 2026
80.8Accuracy
8
Jun 1, 2026
60.9Accuracy (ARC-E Corrupt)
8
Jun 1, 2026
43.3Accuracy
8
Jun 1, 2026
73.9Accuracy
8
Jun 1, 2026
84.2Accuracy
8
Jun 1, 2026
46Accuracy
8
Jun 1, 2026
89.4Accuracy
8
Jun 1, 2026
84.6Accuracy
8
Jun 1, 2026
0.765Accuracy
8
May 13, 2026
70.43Accuracy
8
May 13, 2026
12.9Accuracy (LMGH)
8
May 12, 2026
86Accuracy
8
May 11, 2026
73.33Pass@1 Accuracy
8
May 11, 2026
55.28Accuracy
8
May 4, 2026
54.72Accuracy
8
May 4, 2026
80.39Accuracy
8
May 4, 2026
71.5T Score (BBH)
8
Apr 28, 2026