| image-captioning-on-coco | DALL-E | – | CIDEr: 20.2 |
| image-captioning-on-coco | Flamingo (3B; 4-shot) | – | CIDEr: 85 |
| image-captioning-on-coco | Flamingo (80B; 4-shot) | – | CIDEr: 103 |
| image-captioning-on-coco | Parti | – | CIDEr: 83.9 |
| image-captioning-on-coco | RA-CM3 (2.7B) | – | CIDEr: 89.1 |
| image-captioning-on-coco | Vanilla CM3 | – | CIDEr: 71.9 |
| image-captioning-on-coco | X-LXMERT | – | CIDEr: 55.8 |
| image-captioning-on-coco | minDALL-E | – | CIDEr: 48 |
| image-captioning-on-coco | ruDALL-E-XL | – | CIDEr: 38.7 |
| text-to-image-generation-on-coco | DALL-E (12B) | – | FID: 28 |
| text-to-image-generation-on-coco | RA-CM3 (2.7B) | – | FID: 15.7 |
| text-to-image-generation-on-coco | Stable Diffusion | – | FID: 12.63 |
| text-to-image-generation-on-coco | Vanilla CM3 | – | FID: 29.5 |