Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
30.43Average@16
42
Jun 9, 2026
73.83Avg@16
42
Jun 9, 2026
70.4Mean Accuracy
42
Jun 11, 2026
93.3Accuracy
42
May 6, 2026
65.4Accuracy
42
Mar 18, 2026
51.77Accuracy (Avg@32)
42
Jun 19, 2026
46.78Avg@16
42
May 22, 2026
79.3Accuracy
42
Jun 30, 2026
73.84Accuracy (maj1@1)
42
Feb 26, 2026
89.1Accuracy
41
Jun 16, 2026
74.8Accuracy
41
May 21, 2026
78.5Accuracy
41
Jun 23, 2026
78.6Math500 Score
41
Apr 27, 2026
65.2Pass@1
41
Jun 2, 2026
79.08EM Accuracy
41
May 15, 2026
68.02Accuracy
41
Jun 16, 2026
96.2Accuracy
41
Feb 26, 2026
87.4Accuracy
41
May 11, 2026
97.6Accuracy
40
Jul 2, 2026
70.6Accuracy (Aggregate)
40
May 21, 2026
100Accuracy
40
May 21, 2026
55.95Attack Accuracy
40
Apr 28, 2026
88.4Accuracy
40
Apr 20, 2026
79Pass@128
40
Apr 14, 2026
99Original Accuracy
40
Apr 10, 2026