Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
74Average Accuracy
6
May 1, 2026
86.2Accuracy (pass@1/mean@32)
6
May 1, 2026
71.2Pass@1 Score (mean@32)
6
May 1, 2026
65.6Pass@1/Mean@32
6
May 1, 2026
45.5Accuracy
6
May 1, 2026
66.8Accuracy
6
Apr 30, 2026
37.4Accuracy
6
Apr 30, 2026
86.8Accuracy
6
Apr 30, 2026
84.1Accuracy
6
Apr 30, 2026
91.3Accuracy
6
Apr 30, 2026
96.04Algebra Accuracy
6
Apr 28, 2026
94TFR
6
Apr 27, 2026
13Best-of-16 Delta
6
Apr 24, 2026
95.6Accuracy
6
Apr 23, 2026
31.41Accuracy
6
Apr 21, 2026
81.2Accuracy
6
Apr 21, 2026
76.65Accuracy
6
Apr 21, 2026
27Accuracy
6
Apr 21, 2026
78.2Accuracy
6
Apr 21, 2026
69.2Reasoning Performance
6
Apr 21, 2026
93.4Reasoning Performance
6
Apr 21, 2026
82.34Accuracy
6
Apr 21, 2026
37.3Score
6
Apr 21, 2026
78.47Score
6
Apr 21, 2026
92.2Accuracy
6
Apr 21, 2026