Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Image Generation Evaluation on GenAI-Bench (Pearson-r)
Loading...
70.3
Pearson-r
Gemini-2.5-Pro
14.244
28.797
43.35
57.903
Jun 3, 2025
Pearson-r
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pearson-r
Gemini-2.5-Pro
Scale=/
2025.06
70.3
UnifiedReward_Q
Scale=8B
2025.06
62.7
UnifiedReward_L
Scale=7B
2025.06
62.6
Qwen3-VL
Scale=8B
2025.06
61.6
GPT-4o
Scale=/
2025.06
60.9
Minos
Scale=8B
2025.06
60.2
LLaVA-Critic
Scale=72B
2025.06
53.2
LLaVA-OV
Scale=72B
2025.06
51.6
LLaVA-Critic
Scale=7B
2025.06
33
Prometheus-V
Scale=7B
2025.06
18.6
LLaVA-OV
Scale=7B
2025.06
16.4
Feedback
Search any
task
Search any
task