Multimodal Mathematical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.878Accuracy
124
Jun 9, 2026
77.1Overall Accuracy
114
Jun 30, 2026
62.4Average Score
70
Jun 11, 2026
68Accuracy
56
Apr 10, 2026
60.3Accuracy
47
Mar 31, 2026
75.2Accuracy
46
May 20, 2026
65.9Accuracy
45
Jul 7, 2026
69.2Accuracy (DynaMath)
45
Jun 5, 2026
38.1CoT Error
38
Apr 21, 2026
74.2Accuracy
34
Mar 31, 2026
81.2Accuracy
33
Apr 3, 2026
64.9Accuracy (ALL)
33
Mar 31, 2026
66.4DynaMath Score
31
May 11, 2026
61.5Pass@1 Accuracy
31
May 22, 2026
68.8Accuracy (ALL)
28
Jun 30, 2026
70.94T-Dominant Score
26
Feb 26, 2026
63Score
23
Mar 31, 2026
90.2Macro Score
22
May 19, 2026
67.5Accuracy
18
Jun 9, 2026
26.1CoT Error
18
Apr 21, 2026
39.6CoT Error
18
Apr 21, 2026
28.8CoT Error
18
Apr 21, 2026
40.5CoT Error
18
Apr 21, 2026
36.5CoT Error
18
Apr 21, 2026
79.5Accuracy
18
May 6, 2026