| Benchmark | Model | Rank | Results |
|---|---|---|---|
| image-captioning-on-coco-captions | VLKD (ViT-B/16) | – | BLEU-4: 16.7CIDER: 58.3METEOR: 19.7SPICE: 13.4 |
| visual-question-answering-on-ok-vqa | VLKD(ViT-B/16) | – | Accuracy: 10.5 |
| visual-question-answering-on-vqa-v2-test-dev | VLKD | – | Accuracy: 44.5 |
| visual-question-answering-on-vqa-v2-val | VLKD(ViT-B/16) | – | Accuracy: 38.6 |