Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-image preference evaluation on MM-RewardBench T2I 2
Loading...
78.9
Accuracy
Gemini 3.1 Pro
53.004
59.727
66.45
73.173
May 8, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Gemini 3.1 Pro
ARR=true
2026.05
78.9
Gemini 3.1 Pro
ARR=false
2026.05
75.1
GPT-5
ARR=true
2026.05
74.7
GPT-5
ARR=false
2026.05
70.5
UnifiedReward-Thinking
2026.05
66
Qwen3-VL-8B
ARR=true
2026.05
62.7
HPSv3
2026.05
60.2
UnifiedReward
2026.05
59.8
PickScore
2026.05
58.6
Qwen3-VL-8B
ARR=false
2026.05
57.6
ImageReward
2026.05
54
Feedback
Search any
task
Search any
task