Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference on VBench 50 prompts
Loading...
139
Ours Wins
One-Forcing
27.72
56.61
85.5
114.39
May 22, 2026
Ours Wins
Baseline Wins
Total Comparisons
Win Rate
Updated 9d ago
Evaluation Results
Method
Method
Links
Ours Wins
Baseline Wins
Total Comparisons
Win Rate
One-Forcing
Baseline=ASD, Baseline...
2026.05
139
11
150
92.7
One-Forcing
Baseline=Self Forcing...
2026.05
130
17
147
88.4
One-Forcing
Baseline=Self Forcing...
2026.05
32
118
150
21.3
Feedback
Search any
task
Search any
task