Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93.8Accuracy (%)
12
Mar 9, 2026
79.6Pass@1 Rate
12
Mar 5, 2026
69Pass@1 Rate
12
Mar 5, 2026
88.34Accuracy (%)
12
Mar 4, 2026
37Accuracy
12
Mar 4, 2026
53Accuracy
12
Mar 4, 2026
89Accuracy
12
Mar 4, 2026
71.4Pass@1
12
Mar 4, 2026
74Acc@16
12
Feb 27, 2026
40.5Acc@16
12
Feb 27, 2026
26Acc@16
12
Feb 27, 2026
76.25Mean@8
12
Feb 26, 2026
97.33Verifiability Score
12
Feb 26, 2026
97.82Verifiability Score
12
Feb 26, 2026
71.11Reusability Score
12
Feb 26, 2026
94.68Reusability Score
12
Feb 26, 2026
62Pass@1
12
May 27, 2026
88.15MATH-500 Score
12
Feb 26, 2026
0.597Pass@1 Accuracy
12
Feb 26, 2026
67.4Accuracy
12
Feb 26, 2026
96Accuracy
12
Feb 26, 2026
51.94Pass@1
12
Feb 26, 2026
31.76Pass@1 Success Rate
12
Feb 26, 2026
85.92Pass@1
12
Feb 26, 2026
0.388Pass@1
12
Feb 26, 2026