Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Image Preference Prediction on Cross-domain Aggregate
Loading...
77
Average Accuracy
DyCoRM
54.12
60.06
66
71.94
May 25, 2026
Average Accuracy
Updated 8d ago
Evaluation Results
Method
Method
Links
Average Accuracy
DyCoRM
Model Category=Reward...
2026.05
77
HPSV3
Model Category=Reward...
2026.05
76.1
HPSV2
Model Category=Reward...
2026.05
70.8
MPS
Model Category=Reward...
2026.05
70.4
HPS
Model Category=Reward...
2026.05
66.8
PICKSCORE
Model Category=Reward...
2026.05
65.7
IMAGEREWARD
Model Category=Reward...
2026.05
64.5
GPT-5 (25-08-07)
Model Category=General...
2026.05
62.9
AESTHETIC SCORE PREDICTOR
Model Category=Reward...
2026.05
62.3
GEMINI-3.0-PRO
Model Category=General...
2026.05
61.5
GPT-4O (24-11-20)
Model Category=General...
2026.05
60.7
INTERNVL3.5-14B
Model Category=General...
2026.05
57.6
CLIPSCORE
Model Category=Reward...
2026.05
57.3
QWEN3VL-8B
Model Category=General...
2026.05
56.9
INTERNVL3.5-8B
Model Category=General...
2026.05
55.8
LLAVA-ONEVISION-1.5-7B
Model Category=General...
2026.05
55.5
QWEN3VL-4B
Model Category=General...
2026.05
55
Feedback
Search any
task
Search any
task