Advanced Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
12.8Accuracy
18
Apr 8, 2026
46.3Pass@1 Accuracy
15
Feb 26, 2026
41.2Pass@1 Accuracy
15
Feb 26, 2026
85.5Accuracy
6
Feb 26, 2026
19.9AIME 25 Accuracy
6
Feb 26, 2026
22.2Recovery Rate
3
Apr 6, 2026
10.8Recovery Rate
3
Apr 6, 2026