Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Pairwise human preference on Prolific user study large-scale (test)
Loading...
97.33
Winning Rate
PrefGen
77.9236
82.9618
88
93.0382
Dec 4, 2025
Winning Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Winning Rate
PrefGen
baseline=ViPer
2025.12
97.33
PrefGen
baseline=InstantStyle
2025.12
90.67
PrefGen
baseline=IP-Adapter
2025.12
88.67
PrefGen
baseline=StyleAligned
2025.12
88.67
PrefGen
baseline=EasyRef
2025.12
88
PrefGen
baseline=Bagel
2025.12
78.67
Feedback
Search any
task
Search any
task
