Multi-modal Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
82.3Accuracy
98
Jun 8, 2026
86.4Accuracy
84
May 26, 2026
62.4Accuracy
38
Apr 13, 2026
81Accuracy
21
Jun 4, 2026
72.7Accuracy
17
Apr 28, 2026
70.7Accuracy
17
May 6, 2026
44.7String Match Accuracy
12
Jul 8, 2026
43Accuracy
12
Feb 26, 2026
65.9Accuracy
12
Feb 26, 2026
70.3Accuracy
12
Feb 26, 2026
87.1Accuracy
12
Feb 26, 2026
0.694Accuracy
12
Feb 26, 2026
61.9Accuracy
10
Jul 7, 2026
75Accuracy
9
Apr 13, 2026
85.28F1 Score
5
Feb 26, 2026
0.645Accuracy
4
Feb 26, 2026
0.857Accuracy
4
Feb 26, 2026
83.2Overall Score
4
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026