Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.729Accuracy
42
Mar 30, 2026
85.79Accuracy
40
May 28, 2026
81.39Accuracy
40
May 28, 2026
92.65Accuracy (%)
40
May 28, 2026
70.46Mean@8 Accuracy
40
May 19, 2026
83Accuracy
40
May 19, 2026
51.79Accuracy
38
Jun 9, 2026
66.91Accuracy
38
Jun 9, 2026
62.7Accuracy
38
May 28, 2026
68.87Overall Performance
36
May 13, 2026
89.8Pass@1
36
Mar 24, 2026
58.4Accuracy
33
Jun 23, 2026
48.8Accuracy
33
May 22, 2026
69.86Accuracy
33
Jun 18, 2026
95.93Accuracy
31
Jun 30, 2026
90.62Accuracy
30
Jul 1, 2026
0.756Chart Score
30
Feb 26, 2026
81.4Accuracy
29
Jun 30, 2026
81.8Accuracy
29
Jun 23, 2026
75.2Accuracy
29
Feb 26, 2026
57.1MMMU Score
27
May 28, 2026
67.4Accuracy
27
Apr 21, 2026
60.95Mean@8 Accuracy
26
May 12, 2026
51.36Mean@8 Accuracy
26
May 12, 2026
76Accuracy
26
May 19, 2026