Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
93Pass@1 Accuracy
9
Apr 28, 2026
94.1Pass@1 Accuracy
9
Apr 28, 2026
90.4Random Baseline
9
Apr 24, 2026
33.21Accuracy (maj@2)
9
Apr 23, 2026
64.52Accuracy (maj@2)
9
Apr 23, 2026
36.46Accuracy
9
Apr 21, 2026
81.58Accuracy
9
Apr 21, 2026
95.9Exact Match Accuracy
9
Apr 20, 2026
83.2Accuracy
9
Apr 16, 2026
92.6Accuracy (GSM8K)
9
Apr 16, 2026
96.8FRS
9
Jun 9, 2026
98.9FRS
9
Apr 15, 2026
60.8Avg@4 Score
9
Apr 14, 2026
91.1Avg@4 Score
9
Apr 14, 2026
30.4Avg@32
9
Apr 14, 2026
45.1Average Score (Avg@32)
9
Apr 14, 2026
46.1Accuracy
9
Apr 14, 2026
23Accuracy
9
Apr 14, 2026
58.6Accuracy
9
Apr 14, 2026
93.1GSM8K Score
9
Apr 8, 2026
3.33Score
9
Apr 8, 2026
0.94Average Accuracy
9
Mar 25, 2026
0.94Average Accuracy
9
Mar 25, 2026
44Pass@1
9
Mar 24, 2026
21.9Pass@1 Accuracy
9
Mar 23, 2026