Audio-Visual QA
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
84.3Overall Accuracy
11
Jun 2, 2026
163CIDEr
10
Jun 2, 2026
55.56Accuracy
6
Mar 17, 2026
73.78Accuracy
6
Mar 17, 2026
66.57Accuracy
6
Mar 17, 2026
48.25Accuracy
6
Mar 17, 2026