| Sogou_MM | 72.73% | 88.89% | 80.00% |
| NVTextSpotter | 72.73% | 88.89% | 80.00% |
| gts-swint-cocoonly-s4-3_1 | 72.73% | 88.89% | 80.00% |
| Sensetime V1 | 63.64% | 87.50% | 73.68% |
| FOTS | 63.64% | 87.50% | 73.68% |
| SRC-B-MachineLearningLab | 63.64% | 87.50% | 73.68% |
| Tencent Youtu | 72.73% | 72.73% | 72.73% |
| Baidu VIS | 63.64% | 77.78% | 70.00% |
| HoText_v1 | 63.64% | 77.78% | 70.00% |
| SRC-B-MachineLearningLab | 63.64% | 70.00% | 66.67% |
| Baidu IDL v3 | 63.64% | 70.00% | 66.67% |
| Alibaba-PAI | 63.64% | 70.00% | 66.67% |
| CPN (multi-scale) | 54.55% | 85.71% | 66.67% |
| Baidu VIS v2 | 63.64% | 63.64% | 63.64% |
| e2e-mlt + bug fix | 63.64% | 63.64% | 63.64% |
| Yunos_Robot1.0 | 54.55% | 75.00% | 63.16% |
| e2e-mlt | 63.64% | 53.85% | 58.33% |
| Baidu IDL | 54.55% | 60.00% | 57.14% |
| Baidu VIS v2+ | 54.55% | 54.55% | 54.55% |
| Megvii-Image++ | 36.36% | 44.44% | 40.00% |
| SRC-B-TextProcessingLab | 27.27% | 75.00% | 40.00% |
| Char-level PTSD on SynthText | 27.27% | 37.50% | 31.58% |
 Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 18.18% | 66.67% | 28.57% |
| TextProposals + DictNet | 18.18% | 66.67% | 28.57% |
| M_FOTS_Orig | 27.27% | 30.00% | 28.57% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 9.09% | 100.00% | 16.67% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Deep2Text-MO | 0.00% | 0.00% | 0.00% |
| Baseline OpenCV3.0 + Tesseract | 0.00% | 0.00% | 0.00% |