Multimodal Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.01Score
17
Jun 5, 2026
72.15Accuracy
17
Mar 31, 2026
78.2Overall Accuracy (ALL)
17
Mar 4, 2026
65Accuracy
17
May 28, 2026
76.4MathVista Score
16
Jun 19, 2026
79.5Mean@5
16
Mar 31, 2026
57Accuracy
16
Mar 4, 2026
73.8Pass@1 Accuracy
15
Apr 14, 2026
85.1GPS Score
15
Feb 26, 2026
47.2Pass@1 Accuracy
14
Apr 14, 2026
60.5Accuracy
14
Feb 26, 2026
77.26Accuracy (All)
13
Jun 17, 2026
37.7Accuracy
13
Jun 9, 2026
61.5Accuracy
13
Jun 9, 2026
54.11Accuracy
12
May 20, 2026
47.37Accuracy
12
May 20, 2026
51.2Accuracy
12
Apr 28, 2026
31.2Score
12
Feb 27, 2026
63.16Pass@1 Accuracy
12
Feb 26, 2026
76.39Pass@1 Accuracy
11
Feb 26, 2026
66.8Average Score
9
Mar 4, 2026
36.33WeMath-S Score
8
May 13, 2026
21.05Alg Score
8
Feb 26, 2026
66.45Accuracy
6
Jun 17, 2026
87.47Overall Macro Score
6
May 19, 2026