| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Flickr30K 1K (test) | X2-VLM-large | R@199.1 | 491 | 1mo ago | |
| Flickr30k (test) | BLIP | R@196.6 | 472 | 1d ago | |
| Flickr30k | Qwen-2.5 | R@199 | 451 | 8d ago | |
| MS-COCO 5K (test) | BLIP-2 ViT-g | R@185.4 | 320 | 2mo ago | |
| MS-COCO | L2RM-SGRAF | R@180.5 | 168 | 21d ago | |
| COCO | BLIP2 | R@185.4 | 152 | 9d ago | |
| MSCOCO | BLIP | R@181.9 | 152 | 7d ago | |
| MS-COCO (test) | BLIP | R@180.6 | 127 | 1mo ago | |
| MS-COCO 1K (test) | VSE∞ | R@182 | 121 | 3mo ago | |
| DCI | Qwen3-VL-Embedding | R@177.9 | 100 | 7d ago | |
| Flickr30K-CN | CN-CLIP | R@196.6 | 99 | 3mo ago | |
| MSCOCO (1K test) | ImageBERT | R@185.4 | 96 | 2mo ago | |
| RSITMD (test) | GeoRSCLIP-FT | R@132.3 | 77 | 2mo ago | |
| Flickr30k (val) | FreqAdapter | Recall@190.9 | 70 | 22d ago | |
| MSCOCO 5K (test) | BEIT-3 | R@184.8 | 68 | 1mo ago | |
| NUS-WIDE | mAP@5091.1 | 62 | 1d ago | ||
| MIRFlickr | mAP@5097.1 | 62 | 1d ago | ||
| Flickr30K 1K Karpathy (test) | Florence-Huge | R@197.2 | 59 | 3mo ago | |
| COCO 5K (test) | R@181.9 | 57 | 2d ago | ||
| MSCOCO (val) | ITO | R@158.14 | 51 | 3mo ago | |
| CC152K | L2RM-SGRAF | R@143 | 48 | 3mo ago | |
| COCO-CN | ObjEmbed | R@187.4 | 48 | 3mo ago | |
| RSITMD | RemoteCLIP | Rank1 | 47 | 1mo ago | |
| MS-COCO 5K | SoftMask++ | R@10.723 | 46 | 3mo ago | |
| DOCCI | Gemini Embedding 2 | R@191.3 | 45 | 7d ago |