Mathematical Problem Solving
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82Accuracy
12
Jun 11, 2026
28.9Accuracy
12
Jun 11, 2026
85Peak Accuracy
12
May 27, 2026
59.3Peak Accuracy
12
May 27, 2026
39.7Peak Accuracy
12
May 27, 2026
91Peak Accuracy
12
May 27, 2026
28.6Peak Accuracy
12
May 27, 2026
40.2Peak Accuracy
12
May 27, 2026
31.67Pass@1
12
May 22, 2026
42.19Pass@1
12
May 22, 2026
86.7Accuracy
12
Apr 29, 2026
86.52Average Accuracy
12
Apr 21, 2026
96.39AMC Accuracy
12
Apr 21, 2026
38.33Accuracy
12
Apr 15, 2026
95Pass@1
12
Apr 1, 2026
57.7Exact Match Accuracy
12
Feb 26, 2026
72.8Exact Match Accuracy
12
Feb 26, 2026
56.3Exact Match Accuracy
12
Feb 26, 2026
76Exact Match Accuracy
12
Feb 26, 2026
63.1F1 Score
12
Feb 26, 2026
39.5Exact Match Acc
12
Feb 26, 2026
98.15Accuracy
11
Jun 30, 2026
91.8MATH500 Score
11
Feb 26, 2026
84.4Ac (alpha=0.10)
10
May 15, 2026
49.1Pass@8 Accuracy
10
Feb 26, 2026