Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
26.5Accuracy @4
20
Apr 16, 2026
66.8Pass@4
20
Apr 16, 2026
78.67Accuracy
20
Apr 15, 2026
29.4Accuracy
20
Apr 13, 2026
66.91Pass@1
20
Apr 7, 2026
52.5Overall Score
20
Apr 20, 2026
88.1Average Score
20
Jun 11, 2026
97.8Accuracy
20
Mar 24, 2026
82Accuracy
20
Mar 24, 2026
80Accuracy
20
Mar 24, 2026
80Accuracy
20
Mar 24, 2026
63.1Pass@1
20
Mar 18, 2026
36.7Pass@1
20
Mar 18, 2026
78.8Pass@1
20
Mar 18, 2026
39.2Pass@1
20
Mar 18, 2026
46.1Pass@1
20
Mar 18, 2026
52.3Pass@1
20
Mar 18, 2026
88.7Pass@1
20
Mar 18, 2026
66.8Average Score (Top-32)
20
Jun 9, 2026
73.18Accuracy
20
Mar 5, 2026
38.24Hit Score (HS)
20
Mar 4, 2026
72.8Success Rate
20
Feb 26, 2026
74.4Success Rate
20
Feb 26, 2026
826Trace Count
20
Feb 26, 2026
1,383Trace Count
20
Feb 26, 2026