Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
72.4Accuracy
28
Mar 5, 2026
68.8Accuracy
28
Mar 5, 2026
70.1Accuracy
28
Mar 5, 2026
65.6Accuracy
28
Mar 5, 2026
63.3Accuracy
28
Mar 5, 2026
74.4Accuracy
28
Mar 5, 2026
62.43Score
28
Mar 4, 2026
90.7Score
28
Jul 7, 2026
24.9Pass@2 Exact Match Accuracy
28
Apr 23, 2026
99.2Accuracy
28
Feb 26, 2026
100Factuality Acc
28
Feb 26, 2026
91.9Accuracy
28
Mar 5, 2026
0Degeneration Count
27
May 12, 2026
0Degeneracy Score
27
May 12, 2026
0Degeneration Count
27
May 12, 2026
32.89Accuracy (Multi-choice)
27
May 12, 2026
95.1Accuracy
27
Apr 8, 2026
59.83Pass@1
27
Mar 17, 2026
71Pass@1
27
Apr 14, 2026
54.25LiveCodeBench Score
27
Feb 27, 2026
73.33AIME Score
27
Feb 27, 2026
94.2Math Score
27
Feb 27, 2026
69.99Overall Zero-Shot Accuracy
26
May 26, 2026
87.2Accuracy
25
May 15, 2026
75.9CACC
25
Apr 10, 2026