Video-to-Audio Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.52FAD
95
Jun 15, 2026
0.97FD_VGG
32
Jun 12, 2026
0Fréchet Distance (FD)
10
Apr 3, 2026
72Temporal Control Score
9
Feb 26, 2026
701.21FVD
8
Jun 29, 2026
3.23FD (VGG)
8
Feb 26, 2026
1.8FD (VGG)
8
Feb 26, 2026
4.3Overall Score
8
Feb 26, 2026
4.82Alignment
8
Feb 26, 2026
62.37Inception Score
8
Feb 26, 2026
0FD
7
Apr 3, 2026
0FD
7
Apr 3, 2026
52CLAP
7
Mar 4, 2026
474.56FDPaSST
7
Feb 26, 2026
0FD (VGG)
6
Mar 23, 2026
5.32FAD
4
Mar 27, 2026
1.76KLD
4
Feb 26, 2026
3.7Audio Quality
4
Feb 26, 2026
1.98KLD
3
Feb 26, 2026
2.47KL Divergence
3
Feb 26, 2026
10.77FAD
2
May 18, 2026
23.94Accuracy
2
Feb 26, 2026
71.36Audio Quality
1
Jul 1, 2026
—
—Primary metric
0
Feb 26, 2026