Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
92.97Pass@1
57
May 4, 2026
95.83Pass@4 Accuracy
54
Apr 29, 2026
99.59Accuracy
54
Apr 23, 2026
83.3Accuracy
52
Jul 7, 2026
87.5Pass@1
51
Apr 30, 2026
96.7Accuracy
49
Apr 23, 2026
42.6Accuracy
45
Jun 9, 2026
95Accuracy
45
Jun 18, 2026
83.9Average Accuracy
45
Feb 26, 2026
70.3Accuracy
44
Apr 8, 2026
95.2Pass@1
42
Jun 30, 2026
96.8Pass@4
39
Apr 29, 2026
95Accuracy
39
May 18, 2026
97.6Accuracy
38
May 18, 2026
65.6Average Rate @16
38
May 28, 2026
0.627Accuracy
37
Feb 26, 2026
55.4Accuracy
36
May 12, 2026
80Accuracy
36
Apr 21, 2026
90Accuracy
36
Apr 21, 2026
99.2Accuracy
36
Apr 21, 2026
73.3Pass@1 Score
36
Mar 16, 2026
90.7Accuracy
36
Feb 26, 2026
75Accuracy
36
Feb 26, 2026
71.8Math-500
34
Jun 11, 2026
66.7Pass@1
33
Mar 16, 2026