Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
49.4MATH Accuracy (BoN@8)
4
Apr 14, 2026
60.7PRMScore
4
Apr 14, 2026
0.766AUC
4
Apr 14, 2026
43.8Accuracy
4
Apr 14, 2026
85Pass@1 Rate
4
Apr 10, 2026
19.1Pass@1
4
Apr 10, 2026
77.9Accuracy
4
Apr 10, 2026
92.4GSM8K Accuracy
4
Apr 10, 2026
97.5Accuracy
4
Apr 10, 2026
95.4Accuracy (MATH 500)
4
Apr 10, 2026
96.3Accuracy
4
Apr 10, 2026
57Accuracy (%)
4
Apr 7, 2026
6.25Pass@1
4
Apr 2, 2026
43.6Pass@16 Rate
4
Mar 26, 2026
44.94Average Score
4
Mar 24, 2026
72.3English Score
4
Mar 24, 2026
78.2Compression Accuracy
4
Mar 18, 2026
46Exact Match Accuracy
4
Mar 17, 2026
44.88Accuracy
4
Mar 16, 2026
0.777Hypervolume
4
Mar 12, 2026
35.6Accuracy
4
Mar 11, 2026
37Accuracy
4
Mar 11, 2026
1Success Rate (SR)
4
Mar 10, 2026
2.08Average Score @8
4
Mar 10, 2026
45.01Avg@8 Score (MATH500)
4
Mar 10, 2026