Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
21Mean@8 Score
18
Jul 7, 2026
13.33Mean Score (8 samples)
18
Jul 7, 2026
84.6Mean@8 Score
18
Jul 7, 2026
39.79Mean@8 Score
18
Jul 7, 2026
18.48BCE
18
Jul 1, 2026
72.5Accuracy
18
Jun 30, 2026
86.2Accuracy
18
Jun 30, 2026
94.39Accuracy
18
Jun 30, 2026
19.7AIME24 Score
18
Jun 24, 2026
88.5Accuracy
18
Jun 23, 2026
54.8Accuracy (ACC)
18
Jun 23, 2026
15.1Accuracy (ACC)
18
Jun 19, 2026
45.92Accuracy
18
Jun 16, 2026
89.4Pass@1 Score
18
Jun 16, 2026
69.22Accuracy (%)
18
Jun 15, 2026
38.13Accuracy (%)
18
Jun 15, 2026
81.6Accuracy (MATH-500)
18
Jun 12, 2026
91.43Accuracy
18
Jun 12, 2026
64.6Accuracy
18
Jun 11, 2026
53.75Average Score @16
18
Jun 9, 2026
36.36Avg@16
18
Jun 9, 2026
82.8Accuracy
18
Jun 9, 2026
52Accuracy
18
Jun 9, 2026
47.3Average Score
18
Jun 9, 2026
65.4Pass@1 Rate
18
Jun 9, 2026