| scene-text-recognition-on-coco-text | CLIP4STR-L | #1 | 1:1 Accuracy: 81.9 |
| scene-text-recognition-on-coco-text | CLIP4STR-B | #4 | 1:1 Accuracy: 81.1 |
| scene-text-recognition-on-cute80 | CLIP4STR-L (DataComp-1B) | #1 | Accuracy: 99.7 |
| scene-text-recognition-on-cute80 | CLIP4STR-B | #6 | Accuracy: 99.3 |
| scene-text-recognition-on-cute80 | CLIP4STR-L | #8 | Accuracy: 99.0 |
| scene-text-recognition-on-host | CLIP4STR-L | #1 | 1:1 Accuracy: 82.7 |
| scene-text-recognition-on-host | CLIP4STR-B | #2 | 1:1 Accuracy: 79.8 |
| scene-text-recognition-on-ic19-art | CLIP4STR-L (DataComp-1B) | #1 | Accuracy (%): 86.4 |
| scene-text-recognition-on-ic19-art | CLIP4STR-L | #2 | Accuracy (%): 85.9 |
| scene-text-recognition-on-ic19-art | CLIP4STR-B | #3 | Accuracy (%): 85.8 |
| scene-text-recognition-on-icdar2015-1-811-images | CLIP4STR-L (DataComp-1B, RBU 6.5M) | #1 | Accuracy: 91.9 |
| scene-text-recognition-on-iiit5k | CLIP4STR-L (DataComp-1B) | #1 | Accuracy: 99.6 |
| scene-text-recognition-on-iiit5k | CLIP4STR-L | #3 | Accuracy: 99.5 |
| scene-text-recognition-on-iiit5k | CLIP4STR-B (DataComp-1B) | #4 | Accuracy: 99.5 |
| scene-text-recognition-on-iiit5k | CLIP4STR-B | #10 | Accuracy: 99.2 |
| scene-text-recognition-on-uber-text | CLIP4STR-L (DataComp-1B) | #1 | Accuracy (%): 92.2 |
| scene-text-recognition-on-uber-text | CLIP4STR-B | #4 | Accuracy (%): 86.8 |
| scene-text-recognition-on-wost | CLIP4STR-H (DFN-5B) | #1 | 1:1 Accuracy: 90.9 |
| scene-text-recognition-on-wost | CLIP4STR-L (DataComp-1B) | #2 | 1:1 Accuracy: 90.6 |
| scene-text-recognition-on-wost | CLIP4STR-L | #3 | 1:1 Accuracy: 88.8 |
| scene-text-recognition-on-wost | CLIP4STR-B | #4 | 1:1 Accuracy: 87.0 |
| scene-text-recognition-on-icdar2013 | CLIP4STR-L (DataComp-1B) | #3 | Accuracy: 99.0 |
| scene-text-recognition-on-icdar2013 | CLIP4STR-L | #5 | Accuracy: 98.5 |
| scene-text-recognition-on-icdar2013 | CLIP4STR-B | #10 | Accuracy: 98.3 |
| scene-text-recognition-on-svt | CLIP4STR-H (DFN-5B) | #3 | Accuracy: 99.1 |
| scene-text-recognition-on-svt | CLIP4STR-L (DataComp-1B) | #8 | Accuracy: 98.6 |
| scene-text-recognition-on-svt | CLIP4STR-L | #9 | Accuracy: 98.5 |
| scene-text-recognition-on-svt | CLIP4STR-B | #12 | Accuracy: 98.3 |
| scene-text-recognition-on-icdar2015 | CLIP4STR-L (DataComp-1B) | #4 | Accuracy: 91.4 |
| scene-text-recognition-on-icdar2015 | CLIP4STR-L | #6 | Accuracy: 90.8 |
| scene-text-recognition-on-icdar2015 | CLIP4STR-B | #8 | Accuracy: 90.6 |
| scene-text-recognition-on-svtp | CLIP4STR-L (DataComp-1B) | #5 | Accuracy: 98.1 |
| scene-text-recognition-on-svtp | CLIP4STR-L | #6 | Accuracy: 97.4 |
| scene-text-recognition-on-svtp | CLIP4STR-B | #7 | Accuracy: 97.2 |