Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
23.64Pass@1 Accuracy
6
Apr 6, 2026
12Pass@1 Rate
6
Apr 6, 2026
96.8Accuracy
6
Apr 3, 2026
83.9Accuracy
6
Apr 2, 2026
43.5Top-1 Accuracy
6
Apr 2, 2026
90Accuracy
6
Apr 2, 2026
80Accuracy
6
Apr 1, 2026
83Accg
6
Mar 27, 2026
82.8Math500 Accuracy
6
Mar 27, 2026
77.54Pass@1
6
Mar 24, 2026
53.33Pass@1 Accuracy
6
Mar 24, 2026
92.89Exact Match Accuracy
6
Mar 23, 2026
56.34Acc@8
6
Mar 20, 2026
60Acc@8
6
Mar 20, 2026
30.83Acc@8
6
Mar 20, 2026
34.17Accuracy@8
6
Mar 20, 2026
35.1Avg@32
6
Mar 19, 2026
63Compositional Accuracy
6
Mar 18, 2026
0.47Score
6
Mar 13, 2026
62.5Mean Accuracy
6
Mar 13, 2026
81.65Accuracy
6
Mar 10, 2026
76.3Accuracy
6
Mar 6, 2026
39.2Accuracy
6
Mar 6, 2026
57.5Accuracy
6
Mar 6, 2026
85.5Accuracy (MATH-500)
6
Mar 6, 2026