Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Pass@16
6
Feb 26, 2026
83.33Pass@16
6
Feb 26, 2026
33.07Selection Accuracy
6
Feb 26, 2026
63.87Selection Accuracy
6
Feb 26, 2026
51.4Accuracy
6
Feb 26, 2026
56.3Accuracy
6
Feb 26, 2026
0.749Accuracy
6
Feb 26, 2026
0.683Accuracy
6
Feb 26, 2026
86Accuracy
6
Feb 26, 2026
85.81Accuracy
6
Feb 26, 2026
96.4GSM8K Pass@1 Accuracy
6
Feb 26, 2026
79.6Solve Rate
6
Feb 26, 2026
54.71Accuracy
6
Feb 26, 2026
81.92Accuracy
6
Feb 26, 2026
43.06Average Score @8
5
Jul 7, 2026
54.38Avg@32
5
Jul 7, 2026
44.06AIME26 Accuracy
5
Jul 7, 2026
79.68Accuracy
5
Jul 7, 2026
40.6Accuracy
5
Jul 7, 2026
3.35Coherence
5
Jul 2, 2026
73.33Accuracy
5
Jul 1, 2026
42.22Accuracy
5
Jul 1, 2026
46.67Accuracy
5
Jul 1, 2026
87.33Accuracy
5
Jul 1, 2026
76.42Accuracy
5
Jul 1, 2026