Math Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
98.47Relative Overall Score
16
Feb 26, 2026
96.59Relative Overall Score
16
Feb 26, 2026
66.9Macro Avg. Accuracy
15
Apr 30, 2026
72.2Average Score
15
Apr 30, 2026
79.2Avg@12 Score
15
Apr 30, 2026
90.4MDR
15
Apr 15, 2026
0.65Pass@1
15
Feb 26, 2026
30.8Accuracy (MATH 500)
14
May 28, 2026
52.7Exact Match (EM)
14
May 1, 2026
98.4Pass@8
14
Apr 15, 2026
72Pass@8
14
Apr 15, 2026
66.7Pass@8
14
Apr 15, 2026
80Pass@8
14
Apr 15, 2026
86.7Pass@8 Score
14
Apr 15, 2026
40.1Average Accuracy @16
14
Apr 2, 2026
81.8Average Accuracy@16
14
Apr 2, 2026
55.6Pass@1
14
Apr 15, 2026
75.52Performance
14
Feb 26, 2026
78.3Performance
14
Feb 26, 2026
57.54Accuracy (%)
14
Feb 26, 2026
26.04Performance
14
Feb 26, 2026
68.31Performance (%)
14
Feb 26, 2026
48General Score
14
Feb 26, 2026
91Accuracy
14
Feb 26, 2026
72.1AIME 2024 Score
13
May 6, 2026