Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-Image Generation on MSCOCO (CLIP-T, CLIP-I)
Loading...
0.697
CLIP-I (Image-Text Alignment)
DreamLLM
0.64812
0.66081
0.6735
0.68619
Mar 6, 2026
CLIP-I (Image-Text Alignment)
CLIP-T (Text-Image Alignment)
Updated 1mo ago
Evaluation Results
Method
Method
Links
CLIP-I (Image-Text Alignment)
CLIP-T (Text-Image Alignment)
DreamLLM
Model Type=Visual LLM,...
2026.03
0.697
0.238
NExT-GPT‡
Model Type=Any-to-Any,...
2026.03
0.691
0.225
Omni-Diffusion
Model Type=Any-to-Any,...
2026.03
0.667
0.235
Emu‡
Model Type=Visual LLM,...
2026.03
0.656
0.286
AnyGPT
Model Type=Any-to-Any,...
2026.03
0.65
-
Feedback
Search any
task
Search any
task