Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Video on VBench (Efficiency and Perceptual Metrics)
Loading...
23.96
Throughput
VideoMLA
0.4872
6.5811
12.675
18.7689
May 28, 2026
Throughput
Latency
CLIP-T
CLIP-F
HPSv3
Updated 5d ago
Evaluation Results
Method
Method
Links
Throughput
Latency
CLIP-T
CLIP-F
HPSv3
VideoMLA
Model Category=Chunk-w...
2026.05
23.96
3.38
0.3278
0.9686
9.74
LongSANA
Model Category=Chunk-w...
2026.05
19.35
4.48
0.2978
0.9887
7.54
Self-Forcing
Model Category=Chunk-w...
2026.05
18.06
4.19
0.3036
0.9689
9.86
NOVA
Model Category=Frame-w...
2026.05
2.26
14.63
0.2764
0.9673
2.95
Pyramid Flow
Model Category=Frame-w...
2026.05
1.39
87.32
0.2888
0.9795
8.02
Feedback
Search any
task
Search any
task