Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
97.77pass@K
12
Apr 13, 2026
66.67Score
12
Apr 8, 2026
90.39Pass@1 Accuracy
12
Apr 8, 2026
63.3Acc
12
Apr 7, 2026
96.6Accuracy
12
Apr 7, 2026
88.8Accuracy
12
Apr 7, 2026
88.32Accuracy (GSM8K)
12
Apr 7, 2026
87.92Accuracy (GSM8K)
12
Apr 7, 2026
75.04Mean Value (MV)
12
Apr 3, 2026
96.31Top-1 Accuracy
12
Mar 31, 2026
10.93Top-1 Accuracy
12
Mar 31, 2026
35.93Top-1 Accuracy
12
Mar 31, 2026
71.09Top-1 Accuracy
12
Mar 31, 2026
9.6Training Time (hours)
12
Mar 27, 2026
93.2Math500 Score
12
Mar 27, 2026
79.53Accuracy
12
Mar 24, 2026
93.21Accuracy
12
Mar 24, 2026
44.6Accuracy
12
Mar 20, 2026
79.15Accuracy (%)
12
Mar 20, 2026
64Accuracy
12
Mar 19, 2026
86.8Accuracy
12
Mar 19, 2026
2,555Average Acceptance Length τ
12
Mar 20, 2026
40.81Avg@8
12
Mar 10, 2026
39.33Accuracy
12
Mar 9, 2026
54.33Accuracy
12
Mar 9, 2026