Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
95.2Accuracy
9
Feb 26, 2026
59.8Accuracy
9
Feb 26, 2026
70.2Acc@16
9
Feb 26, 2026
66.7DBS
9
Feb 26, 2026
91.4MATH Score
9
Feb 26, 2026
86.5Pass@1 Accuracy
9
Feb 26, 2026
63.26Pass@8
9
Feb 26, 2026
93Pass@8
9
Feb 26, 2026
92.5Pass@8
9
Feb 26, 2026
63.33Pass@8
9
Feb 26, 2026
27.92Avg Recall@8
9
Feb 26, 2026
61.25AIME 25 Avg@8 Accuracy
9
Feb 26, 2026
66.25Avg@8 Accuracy
9
Feb 26, 2026
88.42Pass@1
9
Feb 26, 2026
95.72Pass@1
9
Feb 26, 2026
91Average Score
9
Feb 26, 2026
0.84Average Score
9
Feb 26, 2026
49.71Pass@4
9
Feb 26, 2026
90.52Accuracy
9
Feb 26, 2026
38.4Accuracy @ t1
9
Feb 26, 2026
79.3Acceptance Rate
9
Feb 26, 2026
75Pass@1
9
Feb 26, 2026
49.6Accuracy
8
Jul 9, 2026
1.25Perplexity (PPL)
8
Jul 3, 2026
17Accuracy
8
Jul 3, 2026