Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.48pass@4 Accuracy
2
Feb 26, 2026
59.39Pass@4 Accuracy
2
Feb 26, 2026
93.83pass@4 Accuracy
2
Feb 26, 2026
81.74Avg@16
2
Feb 26, 2026
21.46Avg@16
2
Feb 26, 2026
23.54Avg@32
2
Feb 26, 2026
65.21Avg@32
2
Feb 26, 2026
50.63Avg@32
2
Feb 26, 2026
90.4Accuracy
2
Feb 26, 2026
91.6Accuracy
2
Feb 26, 2026
90Accuracy
2
Feb 26, 2026
47.19CA
2
Feb 26, 2026
0.65Overall Score
2
Feb 26, 2026
11.81ECE
2
Feb 26, 2026
21P1 Score
1
Jul 2, 2026
7P1 Score
1
Jul 2, 2026
93.5Algebra Accuracy
1
Jul 1, 2026
6Effect (pp)
1
Jun 23, 2026
54CR (%)
1
Jun 4, 2026
59Completion Rate
1
Jun 4, 2026
40Score
1
May 28, 2026
85.9Score (SC)
1
May 28, 2026
91SC
1
May 28, 2026
51.7Error Rate
1
May 28, 2026
28.3Error Rate (%)
1
May 28, 2026