Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
52.1Accuracy
6
May 13, 2026
54.44Accuracy
6
May 12, 2026
1.2Acceptance Length
6
May 12, 2026
4.5Acceptance Length
6
May 12, 2026
4.9Acceptance Length
6
May 12, 2026
2.9Acceptance Length
6
May 12, 2026
56.2IAA
6
May 12, 2026
56.7P@4 Accuracy
6
May 12, 2026
73.3P@4
6
May 12, 2026
94.5Pass@4
6
May 12, 2026
89.1AMC23 Score
6
May 11, 2026
56.46Pass@1 Score
6
May 11, 2026
30Accuracy
6
May 8, 2026
82.8Accuracy
6
May 8, 2026
94.6Accuracy (GSM8K)
6
May 8, 2026
95.2Accuracy
6
May 8, 2026
71.5Hit Score (HS)
6
May 8, 2026
36.2pass@16
6
May 8, 2026
38.6Pass@1
6
May 8, 2026
77.2Pass@1
6
May 8, 2026
92.1Accuracy avg@32
6
May 8, 2026
100Coverage
6
May 7, 2026
82.67Accuracy (2 hops)
6
May 6, 2026
36.4EM Accuracy
6
May 4, 2026
63.1EM (%)
6
May 4, 2026