Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.6GSM8K Accuracy
15
Mar 24, 2026
44.02Accuracy
15
Feb 26, 2026
24.17AIME 25 Accuracy
15
Feb 26, 2026
28.54Accuracy
15
Feb 26, 2026
65.74Reasoning Accuracy
15
Feb 26, 2026
56.32AVG@8
15
Feb 26, 2026
0.745Average Success Rate @8
15
Feb 26, 2026
78.5Accuracy
15
Feb 26, 2026
74Accuracy
15
Feb 26, 2026
80Accuracy
15
Feb 26, 2026
14.64AAI
15
Feb 26, 2026
89.8Success Score (MATH)
15
May 12, 2026
89.4Accuracy
15
Feb 27, 2026
60.11Accuracy
15
May 11, 2026
86.5Score
14
Jun 16, 2026
59.7Pass Rate
14
May 26, 2026
68.94Accuracy
14
May 20, 2026
86.71Accuracy
14
May 8, 2026
38.6Accuracy
14
Apr 28, 2026
26Accuracy
14
Apr 28, 2026
18.58Accuracy
14
Apr 7, 2026
84.4MATH Accuracy
14
Mar 10, 2026
64.22Pass@1
14
Mar 19, 2026
38.3Accuracy
14
Feb 26, 2026
34.5Accuracy
14
Feb 26, 2026