Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
89.9Pass@1 (Avg@32)
14
Feb 26, 2026
28.3Pass@1 (Avg@32)
14
Feb 26, 2026
32.2Pass@1 Accuracy
14
Feb 26, 2026
77.6HMMT Accuracy
14
Feb 26, 2026
55.2Accuracy
14
Feb 26, 2026
39.7M1 Score @ t1
14
Feb 26, 2026
77Accuracy
14
Feb 26, 2026
76.2Accuracy
14
Feb 26, 2026
82.1Accuracy (MathVista Reasoning)
13
Jul 9, 2026
81Accuracy
13
Jul 7, 2026
34.2AIME 2024 Score
13
Jun 30, 2026
37.5ACC
13
Jun 23, 2026
17.26Avg@8 Score
13
Jun 17, 2026
3.33Avg@8
13
Jun 17, 2026
5Avg@8
13
Jun 17, 2026
29.06Avg@8
13
Jun 17, 2026
46.53Avg@8
13
Jun 17, 2026
17.22Avg@8
13
Jun 17, 2026
12.22Average Score @8
13
Jun 17, 2026
2.92Avg@8
13
Jun 17, 2026
31.12Avg@8
13
Jun 17, 2026
17.26Avg@8
13
Jun 17, 2026
11.76Avg@8
13
Jun 17, 2026
3.33Avg@8
13
Jun 17, 2026
5Avg@8
13
Jun 17, 2026