| scene-text-recognition-on-icdar-2003 | ViTSTR | #9 | Accuracy: 94.3 |
| scene-text-recognition-on-icdar2013-857-images | ViTSTR-Base + RandAugment (extra data) | #18 | Accuracy: 93.2 |
| scene-text-recognition-on-icdar2015-1-811-images | ViTSTR-Base + RandAugment (extra data) | #19 | Accuracy: 78.5 |
| scene-text-recognition-on-icdar2015 | ViTSTR | #31 | Accuracy: 72.6 |
| scene-text-recognition-on-icdar2013 | ViTSTR | #37 | Accuracy: 92.4 |
| scene-text-recognition-on-svtp | ViTSTR-Base + RandAugment (extra data) | #39 | Accuracy: 81.8 |
| scene-text-recognition-on-cute80 | ViTSTR-Base + RandAugment (extra data) | #45 | Accuracy: 81.3 |
| scene-text-recognition-on-iiit5k | ViTSTR-Base + RandAugment (extra data) | #46 | Accuracy: 88.4 |
| scene-text-recognition-on-svt | ViTSTR | #51 | Accuracy: 87.7 |