Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85.6Avg@8
6
Feb 26, 2026
73Pass@1
6
Feb 26, 2026
26.2Pass@10
6
Feb 26, 2026
18.33Pass@10
6
Feb 26, 2026
84.78Pass@10
6
Feb 26, 2026
96.62Pass@10
6
Feb 26, 2026
36.67Pass@20
6
Feb 26, 2026
0.233Pass@20
6
Feb 26, 2026
88.4Pass@20
6
Feb 26, 2026
0.973Pass@20
6
Feb 26, 2026
15AIME24 Score
6
Feb 26, 2026
73.8NL-to-Format
6
Feb 26, 2026
94.7Accuracy
6
Feb 26, 2026
54.2Majority Score
6
Feb 26, 2026
28.7Maj Score
6
Feb 26, 2026
30.8Maj Score
6
Feb 26, 2026
73Maj
6
Feb 26, 2026
88.8Maj Score
6
Feb 26, 2026
17,474Length
6
Feb 26, 2026
76.3Accuracy
6
Feb 26, 2026
38.9Acc@16
6
Feb 27, 2026
94.4MATH Score
6
Feb 26, 2026
42.8Average Diffusion Steps
6
Feb 26, 2026
38.1Avg Diffusion Steps
6
Feb 26, 2026
100Pass@16
6
Feb 26, 2026