| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MS COCO Karpathy (test) | PaLI | CIDEr149.1 | 682 | 2d ago | |
| MS COCO (test) | VinVLbase | CIDEr140.4 | 117 | 3d ago | |
| COCO | Method [48] | CIDEr154.9 | 116 | 3d ago | |
| Flickr30K | LION-12B | CIDEr Score87.12 | 111 | 3d ago | |
| Flickr30k (test) | Blended | CIDEr98.3 | 103 | 3d ago | |
| NoCaps | PALI-17B | CIDEr127 | 101 | 3d ago | |
| TextCaps | PaLI-3 | CIDEr164.3 | 96 | 3d ago | |
| nocaps (val) | GIT2 | CIDEr (Overall)126.9 | 93 | 2d ago | |
| Flickr30K (Karpathy split) | InstructBLIP | CIDEr123.1 | 76 | 2d ago | |
| COCO (Karpathy split) | mPLUG | CIDEr155.1 | 74 | 2d ago | |
| NoCaps (test) | CogVLM | CIDEr (overall)126.4 | 61 | 3d ago | |
| MS-COCO | OFA | CIDEr154.9 | 61 | 2d ago | |
| MS COCO (Karpathy) | VinVL_large | CIDEr-D140.9 | 56 | 3d ago | |
| Flickr30k | InstructBLIP | CIDEr84.5 | 55 | 3d ago | |
| COCO Caption | SimVLM | CIDEr143.3 | 55 | 3d ago | |
| TextCaps (val) | PaLI-X | CIDEr163.7 | 51 | 2d ago | |
| TextCaps (test) | PaLI-3 | CIDEr164.3 | 50 | 2d ago | |
| MS-COCO online (test) | GRIT | BLEU-4 (c5)42.5 | 49 | 3d ago | |
| COCO 2014 (test) | MM1-30B | CIDEr125.3 | 44 | 3d ago | |
| MS-COCO 2014 (test) | OFA | BLEU-478.7 | 43 | 3d ago | |
| COCO (test) | GIT2 | CIDEr149.8 | 43 | 2d ago | |
| NoCaps | BLIP | CIDEr (in-domain)111.3 | 36 | 2d ago | |
| Conceptual Captions (test) | VisualGPT (Our SRAU) | CIDEr40.9 | 34 | 3d ago | |
| COCO | GIT2 (5.1B) | CIDEr152.7 | 31 | 3d ago | |
| MSCOCO (test) | OFA | CIDEr149.6 | 29 | 3d ago |