Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
42.68MATH Score
18
Feb 26, 2026
86Accuracy
18
Feb 26, 2026
24.8College Math
18
Feb 26, 2026
65.8Pass@1
18
Feb 26, 2026
72.44Accuracy
18
May 12, 2026
67.35Overall Performance Rate
18
Mar 24, 2026
39.7m1@t1
18
Feb 26, 2026
91.9Pass@1
18
Apr 14, 2026
50Accuracy
17
Jul 8, 2026
53.33Accuracy
17
Jul 8, 2026
94.31Accuracy
17
Jul 8, 2026
88.4Accuracy
17
Jul 8, 2026
58.7Precision@1
17
Jul 3, 2026
70.3P@1
17
Jul 3, 2026
94Algebra Accuracy
17
May 27, 2026
8.03Average Acceptance Length (τ)
17
Jul 7, 2026
40AIME24 Accuracy
17
May 19, 2026
47.33Accuracy (LG-GSM8K)
17
May 11, 2026
57.5Pass@1
17
May 11, 2026
57F1 Score
17
Apr 21, 2026
22.9Accuracy (8K)
17
Apr 21, 2026
38.97Accuracy
17
Jun 23, 2026
68.8Accuracy
17
Mar 25, 2026
13,040Length
17
Mar 10, 2026
2,246Solution Length
17
Mar 10, 2026