Video Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
65.3Accuracy (All)
12
Apr 1, 2026
71.2Accuracy
12
Feb 26, 2026
0.793Avg Score
12
Feb 26, 2026
46.76Average Score
12
Mar 17, 2026
76.1Accuracy
12
Feb 26, 2026
0.665Action Accuracy
12
Feb 26, 2026
44.35Model-as-Judge Score
12
Feb 26, 2026
81MC Q&A Accuracy
12
Feb 26, 2026
57.8Object Relations Acc
12
Feb 26, 2026
3.07CI
12
Feb 26, 2026
63.75c-F1
12
Feb 26, 2026
47.32Accuracy (World)
12
Feb 26, 2026
49.4Accuracy
12
Mar 5, 2026
63.36Binary Accuracy
12
Feb 26, 2026
95.43Accuracy
12
Feb 26, 2026
68.2Action Acc
12
Feb 26, 2026
36.7p@1
11
Jul 7, 2026
40.3P@1
11
Jul 7, 2026
67.9p@1
11
Jul 7, 2026
67.7P@1
11
Jul 7, 2026
52.5Average Accuracy
11
Jul 2, 2026
45.68Strict Acc (Desc.)
11
Jun 24, 2026
90.6Accuracy (%)
11
Jun 16, 2026
86.9Accuracy
11
Jun 16, 2026
85.5Accuracy
11
Mar 6, 2026