Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
45.96Pass@1
9
Jul 1, 2026
86.93Pass@1
9
Jul 1, 2026
6.17Pass@1 Rate
9
Jul 1, 2026
75.74Pass@1
9
Jul 1, 2026
40.25Pass@1
9
Jul 1, 2026
90.1Accuracy
9
Jun 30, 2026
84.2Accuracy
9
Jun 30, 2026
99.2Accuracy
9
Jun 30, 2026
93.3Accuracy
9
Jun 30, 2026
83.6Accuracy
9
Jun 30, 2026
81.5Accuracy
9
Jun 30, 2026
97.7Pass@32
9
Jun 30, 2026
83.55Accuracy
9
Jun 24, 2026
71.5Accuracy
9
Jun 23, 2026
46.88Pass@1
9
Jun 18, 2026
63.12Pass@1
9
Jun 18, 2026
85.52GSM8K Utility
9
Jun 16, 2026
64.86Aclean
9
Jun 16, 2026
70Accuracy (Clean)
9
Jun 16, 2026
5.46NFE Reduction
9
Jun 12, 2026
8.25NFE Reduction
9
Jun 12, 2026
40.42Avg@8 Score
9
Jun 11, 2026
48.33Average Score (k=8)
9
Jun 11, 2026
42.3Pass@1
9
Jun 5, 2026
15.42AIME24 Accuracy
9
Jun 4, 2026