Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.2Accuracy
151
Jul 7, 2026
758Accuracy
147
May 26, 2026
89.16Accuracy (Acc)
146
May 28, 2026
81.42Accuracy
146
Jul 7, 2026
96.02Accuracy
144
May 13, 2026
100Accuracy
143
Mar 6, 2026
55.96Pass@1
138
Feb 26, 2026
70.9Accuracy
137
Mar 24, 2026
46.1Accuracy
136
Jun 9, 2026
78.5Accuracy
135
Jun 23, 2026
94.8Accuracy (pass@1)
134
Jun 30, 2026
68.8Accuracy
134
Jun 18, 2026
88.2Accuracy (ACC)
133
Feb 26, 2026
84Accuracy
130
Jun 2, 2026
80.1Accuracy
124
Jun 23, 2026
96.23Accuracy
124
Jun 11, 2026
97.04EM
123
Mar 5, 2026
85.9Accuracy
121
May 1, 2026
75Accuracy (ACC)
119
Jun 17, 2026
79.5Pass@1 Accuracy
119
May 13, 2026
35.9AIME 2024 Score
119
Jun 4, 2026
97.6Accuracy
119
Feb 26, 2026
86.7Accuracy
119
May 11, 2026
95.1Accuracy
118
Jun 2, 2026
76.25Pass@1 Accuracy
117
Jun 19, 2026