| Baidu VIS | 100.00% | 100.00% | 100.00% |
| SRC-B-MachineLearningLab | 100.00% | 100.00% | 100.00% |
| Baidu VIS v2 | 100.00% | 100.00% | 100.00% |
| e2e-mlt + bug fix | 100.00% | 100.00% | 100.00% |
| gts-swint-cocoonly-s4-3_1 | 100.00% | 100.00% | 100.00% |
| Tencent Youtu | 90.91% | 100.00% | 95.24% |
| NVTextSpotter | 90.91% | 90.91% | 90.91% |
| Baidu VIS v2+ | 81.82% | 90.00% | 85.71% |
| Baidu IDL v3 | 81.82% | 81.82% | 81.82% |
| e2e-mlt | 81.82% | 81.82% | 81.82% |
| CPN (multi-scale) | 81.82% | 75.00% | 78.26% |
| Sensetime V1 | 72.73% | 72.73% | 72.73% |
| Smile | 72.73% | 72.73% | 72.73% |
| Alibaba-PAI | 72.73% | 72.73% | 72.73% |
| FOTS | 54.55% | 100.00% | 70.59% |
| SRC-B-MachineLearningLab | 63.64% | 70.00% | 66.67% |
| Sogou_MM | 63.64% | 70.00% | 66.67% |
| M_FOTS_Orig | 63.64% | 63.64% | 63.64% |
| Baidu IDL | 63.64% | 58.33% | 60.87% |
| HoText_v1 | 54.55% | 66.67% | 60.00% |
| SRC-B-TextProcessingLab | 45.45% | 83.33% | 58.82% |
| TextProposals + DictNet | 27.27% | 100.00% | 42.86% |
| Yunos_Robot1.0 | 27.27% | 75.00% | 40.00% |
 Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 27.27% | 42.86% | 33.33% |
| Megvii-Image++ | 27.27% | 37.50% | 31.58% |
| Char-level PTSD on SynthText | 18.18% | 18.18% | 18.18% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 9.09% | 100.00% | 16.67% |
| Baseline OpenCV3.0 + Tesseract | 9.09% | 20.00% | 12.50% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Deep2Text-MO | 0.00% | 0.00% | 0.00% |