Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Zero-shot Image-Text Retrieval on Flickr30k
Loading...
97.7
Accuracy (Zero-shot)
CLIPS (ViT-L/14)
91.564
93.157
94.75
96.343
Mar 26, 2026
Accuracy (Zero-shot)
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy (Zero-shot)
CLIPS (ViT-L/14)
Backbone=ViT-L/14
2026.03
97.7
BLIP-B
Backbone=ViT-B
2026.03
97.2
C^2LIP
Backbone=ViT-B/16
2026.03
97
SigLIP ViT-L/16-res256
Backbone=ViT-L/16, Inp...
2026.03
96.7
SigLIP2-ViT-B/16
Backbone=ViT-B/16
2026.03
96.5
CLIP-A (ViT-L/14)
Backbone=ViT-L/14
2026.03
95.2
FLAVA
Backbone=ViT-B
2026.03
91.8
Feedback
Search any
task
Search any
task