Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
66.5P@1
20
May 22, 2026
30.59P@1
20
May 22, 2026
80.8P@1
20
May 22, 2026
90.82Pass@1
20
May 22, 2026
66.67Pass@1
20
May 22, 2026
6.97Average Acceptance Length (τ)
20
May 15, 2026
0.378Test Accuracy (%)
20
May 13, 2026
49.7Accuracy
20
May 13, 2026
56.2Accuracy
20
May 13, 2026
76.1Accuracy
20
May 13, 2026
95.6Accuracy
20
May 12, 2026
60Accuracy
20
May 12, 2026
20.5Accuracy (Acc)
20
May 12, 2026
41.7Accuracy
20
May 12, 2026
71.3Accuracy
20
May 12, 2026
77.9Accuracy
20
May 12, 2026
17.5Avg@4
20
May 12, 2026
72.9Avg@8 (e_m)
20
May 14, 2026
59.5Avg@32
20
May 8, 2026
95.1Avg@32
20
May 8, 2026
52.3Average Score (@32)
20
May 8, 2026
55.8Avg@4
20
May 8, 2026
34.38Average Score @64
20
Apr 21, 2026
73.8Accuracy (%)
20
Apr 16, 2026
98.5Accuracy (%)
20
Apr 16, 2026