Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.2Accuracy
4
Feb 26, 2026
0.922Accuracy
4
Feb 26, 2026
14.48Accuracy
4
Feb 26, 2026
99.01Accuracy
4
Feb 26, 2026
94.6Solve Rate
4
Feb 26, 2026
96.1Solve Rate
4
Feb 26, 2026
51.3Pass@1
4
Feb 27, 2026
89.01Accuracy
4
Feb 26, 2026
20Pass@1
4
Feb 26, 2026
26.7pass@1
4
Feb 26, 2026
33.3Pass@1
4
Feb 26, 2026
66.8AUROC
3
Jul 9, 2026
37.32Exact Match (EM)
3
Jul 3, 2026
64.22Exact Match (EM)
3
Jul 3, 2026
94.1Accuracy
3
Jun 30, 2026
35.7Pass@1
3
Jun 30, 2026
55.1Pass@1
3
Jun 30, 2026
59.6Pass@1
3
Jun 25, 2026
26.9Pass@1
3
Jun 25, 2026
89.2Pass@1
3
Jun 25, 2026
0.59Distinct-4
3
Jun 25, 2026
90.07Accuracy
3
Jun 24, 2026
0.48Drift |δ|
3
Jun 23, 2026
70.56Mathematics Score
3
Jun 19, 2026
0.742Accuracy
3
Jun 18, 2026