| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Flickr30K | EVA-CLIP-E | R@194.9 | 559 | 8d ago | |
| Flickr30k (test) | BLIP-2 | Recall@189.7 | 525 | 1d ago | |
| Flickr30K 1K (test) | ERNIE-ViL 2.0 | R@193.3 | 432 | 1mo ago | |
| MSCOCO 5K (test) | MAP | R@160.9 | 312 | 1mo ago | |
| MS-COCO 5K (test) | BLIP-2 ViT-g | R@168.3 | 244 | 2mo ago | |
| MS-COCO | L2RM-SGRAF | R@165.7 | 187 | 21d ago | |
| COCO | EVA-CLIP-8B | Recall@170.2 | 156 | 12d ago | |
| MSCOCO | BLIP | R@164.3 | 142 | 8d ago | |
| MSCOCO 1K (test) | AltCLIP | R@16,390 | 118 | 2mo ago | |
| CUHK-PEDES (test) | CADA-L | Recall@178.37 | 114 | 1mo ago | |
| DCI | Qwen3-VL-Embedding | R@179.7 | 106 | 7d ago | |
| Flickr30K-CN | R2D2 | R@184.4 | 105 | 23d ago | |
| MS-COCO (test) | K-LITE | R@12,208 | 82 | 1mo ago | |
| RSITMD (test) | GeoRSCLIP-FT | R@125.04 | 77 | 2mo ago | |
| Flickr30k (val) | FreqAdapter | R@177.6 | 70 | 22d ago | |
| Flickr30k (1K) | ALIGN | R@184.9 | 63 | 1mo ago | |
| MIRFlickr | mAP@5097 | 62 | 1d ago | ||
| NUS-WIDE | mAP@5091.6 | 62 | 1d ago | ||
| COCO 5K (test) | R@164.3 | 53 | 2d ago | ||
| ShareGPT4V | LamRA | R@197.9 | 52 | 8d ago | |
| MSCOCO (val) | ITO | R@138.97 | 51 | 3mo ago | |
| MS-COCO 1K | CRCL | R@165.1 | 51 | 2mo ago | |
| MSCOCO (5K) | AMoE | R@153.98 | 51 | 26d ago | |
| RSICD (test) | GeoRSCLIP-FT | R@115.59 | 50 | 2mo ago | |
| COCO-CN | M2-Encoder | R@178.7 | 49 | 3mo ago |