Text-to-Video Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.73Quality Score
209
Jul 7, 2026
84.58Consistency Attribute Score
92
May 15, 2026
0.312CLIP Similarity
85
Feb 26, 2026
81FVD
61
Feb 26, 2026
200.2FVD
59
Mar 27, 2026
0LPIPS
44
Jun 26, 2026
84.26Total Score
41
Jul 2, 2026
40.1PC Score
41
Jul 7, 2026
75.62Text-Video Alignment
34
May 19, 2026
71.7PC Score
28
May 28, 2026
0.32CLIPSIM
28
Feb 26, 2026
0.193CLIPSIM
27
Mar 4, 2026
82.9Latency (s)
26
Mar 4, 2026
212FVD
26
Apr 10, 2026
84.12Overall Score
25
Jun 1, 2026
217.24FVD
25
Feb 26, 2026
83.6Quality Score
23
Jun 5, 2026
60.4Human Score
22
May 12, 2026
28.86SA Score
22
Jul 7, 2026
86.12Quality Score
21
May 14, 2026
0.191CLIPSIM
21
Mar 10, 2026
62.3Imaging Quality (IQ)
21
Mar 10, 2026
58.56Aesthetic Quality
21
Mar 4, 2026
81.4VBench Score (%)
21
Feb 26, 2026
51.27T2V Alignment (Count)
20
Apr 21, 2026