Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Evaluation on Human study blinded triplet comparison
Loading...
1.5
Consistency Rank
Clean
1.4512
1.7806
2.11
2.4394
Jul 1, 2026
Consistency Rank
Plausibility Rank
Best Percentage
Worst Percentage
Updated 22d ago
Evaluation Results
Method
Method
Links
Consistency Rank
Plausibility Rank
Best Percentage
Worst Percentage
Clean
2026.07
1.5
1.57
59.5
10
I2VGuard
2026.07
1.77
1.74
33.5
10.9
Anti-Prompt
2026.07
2.72
2.69
7
79.1
Feedback
Search any
task
Search any
task