List your company

Image-Text Retrieval on COCO & Flickr30k Retrieval (test)

69.44Mean Recall (Zero-shot)TuneCLIP
42.327249.366156.40563.4439Jan 14, 2026

Evaluation results

MethodLinks
TuneCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=9.272026.0169.44
BaselineBase Model=SigLIP ViT-B/16, WCT. (hrs)=N/A2026.0169.32
TuneCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=8.622026.0164.12
OpenCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=5.462026.0157.81
BaselineBase Model=OpenAI ViT-B/16, WCT. (hrs)=N/A2026.0157.46
FastCLIPBase Model=OpenAI ViT-B/16, WCT. (hrs)=4.212026.0151.88
OpenCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=7.552026.0151.54
FastCLIPBase Model=SigLIP ViT-B/16, WCT. (hrs)=4.282026.0143.37