Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
78.9Pass@1 Accuracy
117
May 12, 2026
92.5Accuracy (%)
115
May 20, 2026
68.13Pass@1 Accuracy
115
Feb 26, 2026
90.8Accuracy
115
Jun 17, 2026
98.8Accuracy
113
May 29, 2026
96.6Pass@1 Rate
113
Jun 26, 2026
71.1Accuracy
113
Feb 26, 2026
86.7Accuracy
112
Jun 1, 2026
97.5Pass@1
112
Feb 26, 2026
92.71Pass@1
112
Feb 26, 2026
92.4Accuracy
111
Feb 26, 2026
100Pass@1 Accuracy
109
May 15, 2026
91Accuracy
109
Jul 9, 2026
97.3Accuracy
107
May 29, 2026
97.9MATH 500 Accuracy
106
Feb 26, 2026
93Accuracy
105
Jun 17, 2026
32.7Accuracy
105
May 26, 2026
6,749Average Tokens
104
Jun 24, 2026
97.5Accuracy
104
Jun 24, 2026
94.6Accuracy
104
Jun 19, 2026
52.9pass@1 Accuracy
104
Apr 29, 2026
96.7pass@1
102
Feb 26, 2026
95.7Accuracy
99
May 26, 2026
96Accuracy
98
Jun 12, 2026
6.92Tau ($ au$)
97
Mar 4, 2026