Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.2Accuracy
26
Jun 17, 2026
94.5Accuracy
26
Feb 26, 2026
92.4Pass@1 Rate
26
Mar 19, 2026
89.82TPS
26
Feb 26, 2026
98Accuracy
26
Feb 26, 2026
91.6Accuracy
26
Feb 26, 2026
83.3Acc
26
Feb 26, 2026
85Accuracy
26
Feb 26, 2026
100Accuracy
26
Feb 26, 2026
95.5Accuracy
26
Feb 26, 2026
66.9Accuracy
26
Mar 13, 2026
53.37Accuracy
26
Feb 26, 2026
20.6Minerva Math 4-shot Accuracy
25
May 26, 2026
61.56GSM8K 8-shot Accuracy
25
May 26, 2026
55.3Pass@4
25
May 20, 2026
60Pass@4
25
May 20, 2026
38Mean@8
25
Jun 23, 2026
86.4Accuracy (AIME 25)
25
May 15, 2026
84.17Accuracy
25
Apr 21, 2026
39.55Overall Accuracy
25
Apr 15, 2026
76Accuracy
25
Apr 7, 2026
94Overall Score
25
May 18, 2026
92Accuracy
25
Mar 23, 2026
93.5Accuracy
25
Mar 23, 2026
14Accuracy
25
Jun 11, 2026