| Baidu VIS v2+ | 100.00% | 100.00% | 100.00% |
| Alibaba-PAI | 100.00% | 93.33% | 96.55% |
| gts-swint-cocoonly-s4-3_1 | 92.86% | 100.00% | 96.30% |
| NVTextSpotter | 92.86% | 92.86% | 92.86% |
| Baidu VIS v2 | 85.71% | 85.71% | 85.71% |
| Smile | 85.71% | 85.71% | 85.71% |
| Tencent Youtu | 78.57% | 91.67% | 84.62% |
| FOTS | 71.43% | 100.00% | 83.33% |
| Sensetime V1 | 78.57% | 84.62% | 81.48% |
| Baidu VIS | 78.57% | 84.62% | 81.48% |
| SRC-B-MachineLearningLab | 78.57% | 84.62% | 81.48% |
| e2e-mlt | 78.57% | 78.57% | 78.57% |
| SRC-B-MachineLearningLab | 78.57% | 73.33% | 75.86% |
| Baidu IDL v3 | 71.43% | 71.43% | 71.43% |
| e2e-mlt + bug fix | 64.29% | 64.29% | 64.29% |
| Sogou_MM | 50.00% | 70.00% | 58.33% |
| TextProposals + DictNet | 42.86% | 85.71% | 57.14% |
| HoText_v1 | 50.00% | 58.33% | 53.85% |
| Yunos_Robot1.0 | 35.71% | 83.33% | 50.00% |
| Baidu IDL | 50.00% | 41.18% | 45.16% |
| M_FOTS_Orig | 42.86% | 40.00% | 41.38% |
| Megvii-Image++ | 28.57% | 40.00% | 33.33% |
| SRC-B-TextProcessingLab | 21.43% | 37.50% | 27.27% |
 Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 7.14% | 25.00% | 11.11% |
| Deep2Text-MO | 7.14% | 25.00% | 11.11% |
| Char-level PTSD on SynthText | 7.14% | 25.00% | 11.11% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |
| Baseline OpenCV3.0 + Tesseract | 0.00% | 0.00% | 0.00% |