Text-to-Image Retrieval on IIW
99.7ScoreFineViT/14
Evaluation Results
| Method | Links | |
|---|---|---|
| FineViT/14Params=0.86B, Zero-shot=true2026.03 | 99.7 | |
| FixCLIP-L/14Params=0.3B, Zero-shot=true2026.03 | 98.2 | |
| LongCLIP-L/14Params=0.3B, Zero-shot=true2026.03 | 96.1 | |
| SigLIP2-so400m/14Params=0.4B, Zero-shot=true2026.03 | 95.6 | |
| LongCLIPModel=LongCLIP2025.09 | 95 | |
| SigLIPModel=SigLIP2025.09 | 94.5 | |
| DreamLIPModel=DreamLIP2025.09 | 93 | |
| LSSModel=LSS2025.09 | 92 | |
| SigLIP-so400m/14Params=0.4B, Zero-shot=true2026.03 | 91.8 | |
| NegCLIPModel=NegCLIP2025.09 | 91 | |
| CE-CLIPModel=CE-CLIP2025.09 | 85.3 | |
| CLIPModel=CLIP2025.09 | 85 | |
| DCIP1Model=DCIP12025.09 | 75.3 | |
| DACLLMModel=DACLLM2025.09 | 71.8 |