Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-image preference evaluation on HPD v3 (test)
Loading...
78.3
Accuracy
Gemini 3.1 Pro
57.812
63.131
68.45
73.769
May 8, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini 3.1 Pro
ARR=true
2026.05
78.3
HPSv3
2026.05
76.9
Gemini 3.1 Pro
ARR=false
2026.05
76.6
GPT-5
ARR=true
2026.05
76.1
GPT-5
ARR=false
2026.05
72.4
Qwen3-VL-8B
ARR=true
2026.05
70.2
UnifiedReward-Thinking
2026.05
68.1
Qwen3-VL-8B
ARR=false
2026.05
67.2
UnifiedReward
2026.05
66
PickScore
2026.05
65.6
ImageReward
2026.05
58.6
Feedback
Search any
task
Search any
task