| visual-reasoning-on-winoground | CLIP (ViT-L/14) | – | Text Score: 30.25Image Score: 8.0 |
| visual-reasoning-on-winoground | LDM-CLIP (SelfEval) | – | Text Score: 22.75Image Score: 7.25 |
| visual-reasoning-on-winoground | LDM-T5 (SelfEval) | – | Text Score: 29.00Image Score: 13.50 |
| visual-reasoning-on-winoground | OCLIP (ViT-H/14) | – | Text Score: 30.75Image Score: 12.75 |
| visual-reasoning-on-winoground | PDM-CLIP (SelfEval) | – | Text Score: 17.00Image Score: 14.00 |
| visual-reasoning-on-winoground | PDM-T5 (SelfEval) | – | Text Score: 28.25Image Score: 12.00 |