Mathematical Problem Solving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.6Pass@8
10
Feb 26, 2026
88.2Pass@8
10
Feb 26, 2026
31.7pass@8
10
Feb 26, 2026
55.5pass@8
10
Feb 26, 2026
86.5Score
9
Jul 2, 2026
24.5Score
9
Jul 2, 2026
100Score
9
Jul 2, 2026
651Total Problems
9
Jul 1, 2026
81.94Avg@8
9
Jun 4, 2026
73.33Avg@8
9
Jun 4, 2026
84.17Avg@8 Score
9
Jun 4, 2026
96.09Accuracy
9
May 15, 2026
7.4Pass@1
9
Apr 10, 2026
8.9Pass@1
9
Apr 10, 2026
66.3Pass@1 Acc
9
Mar 4, 2026
85.4Pass@1 Acc
9
Jun 16, 2026
0.916Score
9
Feb 26, 2026
59.4Accuracy (Exact Match)
8
May 18, 2026
64Accuracy
8
May 11, 2026
17.11Accuracy
8
Apr 30, 2026
19.37Accuracy
8
Apr 30, 2026
47.83Accuracy (MATH 500)
8
Apr 30, 2026
59.32Accuracy (AMC 83)
8
Apr 30, 2026
8Accuracy
8
Apr 30, 2026
97Normalized Score
8
Apr 23, 2026