Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.81Accuracy (Acc)
352
Jun 25, 2026
96.67Accuracy
338
Mar 23, 2026
85.2Accuracy
337
Jun 30, 2026
84Accuracy
317
Jul 9, 2026
94Accuracy
298
Jul 1, 2026
96.67Accuracy
294
Jul 7, 2026
74.8Pass@1 Accuracy
289
May 22, 2026
83.3AIME Accuracy
288
Mar 5, 2026
0.955Accuracy
280
Jun 8, 2026
98.5Accuracy
279
Jul 2, 2026
96Pass@1 Rate
274
Jun 25, 2026
84.1Accuracy
266
Jul 9, 2026
76.71Accuracy
254
Jun 11, 2026
85Accuracy
252
May 19, 2026
93Accuracy
251
Jul 8, 2026
13.4Speed Up (x)
246
Mar 20, 2026
93.2Accuracy
245
Jun 26, 2026
83.33Pass@1 Accuracy
243
Jun 12, 2026
97.9Accuracy
241
Jul 1, 2026
97.3pass@1
239
Mar 24, 2026
63.2Accuracy
228
Apr 21, 2026
95Accuracy
227
Feb 26, 2026
100Accuracy (ACC)
224
Jun 9, 2026
97.5Accuracy
221
Mar 18, 2026
95.38GSM8K Accuracy (%)
220
Jun 17, 2026