Multimodal Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.8ACC
19
Feb 26, 2026
58.76Accuracy
19
May 22, 2026
74.5GPT-4 Score
19
Feb 26, 2026
71.86Overall Score
18
Jun 8, 2026
88.41Accuracy
18
Jun 23, 2026
65.2Score
18
May 19, 2026
47.6Pass@1
18
Jul 2, 2026
70.64Pass@1
18
Feb 26, 2026
0.857Score
18
Jun 9, 2026
73.8Accuracy
17
Jun 30, 2026
76.9Accuracy
17
Jun 30, 2026
61.5Accuracy
17
Jun 30, 2026
43.47Pass@1
17
May 13, 2026
52.35Pass@1
17
May 13, 2026
67.84Pass@1
17
May 13, 2026
51Pass@1
17
May 13, 2026
69.5Pass@1
17
May 13, 2026
62.23Pass@1
17
May 13, 2026
52.6Score
17
Mar 18, 2026
57.6Mean@1 Accuracy
17
Feb 26, 2026
0.491METEOR
17
Feb 26, 2026
52.9METEOR
17
Feb 26, 2026
41.7METEOR
17
Feb 26, 2026
0.415METEOR
17
Feb 26, 2026
62.2Accuracy
16
Jul 3, 2026