Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
96.96Accuracy (AddSub)
18
Mar 4, 2026
31.6Pass@1
18
Feb 26, 2026
27.3Pass@1
18
Feb 26, 2026
66.4Pass@1
18
Feb 26, 2026
74.4Pass@1
18
Feb 26, 2026
15.4Pass@1
18
Feb 26, 2026
34.4Pass@1
18
Feb 26, 2026
1Speed
18
Feb 26, 2026
92.2Accuracy
18
Feb 26, 2026
94.1Accuracy
18
Feb 26, 2026
93.5Accuracy
18
Feb 26, 2026
65.8Accuracy
18
Feb 26, 2026
56.8Mean@16
18
Feb 26, 2026
24.4Mean Score @16
18
Feb 26, 2026
53.36Average Score
18
Feb 26, 2026
20.21Average@16
18
Feb 27, 2026
75.32Pass@1
18
Feb 26, 2026
90.6MATH500 Score
18
Feb 26, 2026
42.4Pass@1
18
Feb 26, 2026
58.6Pass@1
18
Feb 26, 2026
13Pass@1
18
Feb 26, 2026
41.3Accuracy
18
Feb 26, 2026
56.9Accuracy
18
Feb 26, 2026
59.69Accuracy (Avg@32)
18
Feb 26, 2026
72.19Accuracy (avg@32)
18
Feb 26, 2026