Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
44.8Average Score
10
May 28, 2026
59.17Average Score (avg@4)
10
May 27, 2026
53.2Accuracy
10
May 26, 2026
98.89Pass@1
10
May 26, 2026
63.2Accuracy
10
May 26, 2026
65.8Accuracy
10
May 26, 2026
58.3Best AIME25 Score
10
May 25, 2026
37.4Ar Score
10
May 22, 2026
54.79Accuracy
10
May 21, 2026
100AR (%)
10
May 21, 2026
7.7Pass@1 Accuracy
10
May 21, 2026
65.5Mean@8 Score
10
May 19, 2026
60.1Mean Score @8
10
May 19, 2026
95.3Mean@8
10
May 19, 2026
59.2Mean@8
10
May 19, 2026
61.2AIME25 Accuracy
10
May 14, 2026
63.2Pass Rate
10
May 13, 2026
32.8Accuracy
10
May 12, 2026
81.5Accuracy
10
May 12, 2026
59.07Accuracy
10
May 11, 2026
237.5TPR (s)
10
May 11, 2026
75.2Accuracy
10
May 8, 2026
32.64Pass@4
10
May 7, 2026
42.6Pass@4 Score
10
May 7, 2026
49.03Pass@4
10
May 7, 2026