Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.712AUROC
16
Apr 13, 2026
57.64Accuracy
16
Apr 10, 2026
58.33Accuracy
16
Apr 10, 2026
71.66Accuracy
16
Apr 10, 2026
89.16Accuracy
16
Apr 8, 2026
59.85Accuracy
16
Apr 8, 2026
31.67Accuracy
16
Apr 8, 2026
44Accuracy
16
Apr 8, 2026
46Random Score
16
Apr 7, 2026
23.3Accuracy
16
Apr 16, 2026
83.33Solved Rate (%)
16
Mar 26, 2026
13.9Average Accuracy (32 samples)
16
Mar 25, 2026
15.4Accuracy @32 samples
16
Mar 25, 2026
16.4Accuracy
16
Mar 25, 2026
100Accuracy
16
Mar 24, 2026
85.2Average Success Rate @32
16
Jun 17, 2026
48.38AIME25 Score
16
Apr 14, 2026
37Algebra Accuracy
16
Mar 18, 2026
32.8Avg@32 Score
16
Apr 28, 2026
108.5Retention Rate
16
Mar 10, 2026
76.8Accuracy@16
16
Jun 23, 2026
74Accuracy (Without Verifier)
16
Mar 4, 2026
48.01Pass@1
16
Feb 26, 2026
40.65Pass@1
16
Feb 26, 2026
26.84Pass@1
16
Feb 26, 2026