| Baidu IDL v3 | 100.00% | 100.00% | 100.00% |
| SRC-B-MachineLearningLab | 87.50% | 100.00% | 93.33% |
| Baidu VIS | 87.50% | 100.00% | 93.33% |
| FOTS | 87.50% | 100.00% | 93.33% |
| SRC-B-MachineLearningLab | 87.50% | 100.00% | 93.33% |
| Baidu VIS v2 | 87.50% | 100.00% | 93.33% |
| Smile | 87.50% | 100.00% | 93.33% |
| Tencent Youtu | 87.50% | 100.00% | 93.33% |
| Baidu VIS v2+ | 87.50% | 100.00% | 93.33% |
| Alibaba-PAI | 87.50% | 100.00% | 93.33% |
| gts-swint-cocoonly-s4-3_1 | 87.50% | 100.00% | 93.33% |
| CPN (multi-scale) | 87.50% | 100.00% | 93.33% |
| Sogou_MM | 87.50% | 87.50% | 87.50% |
| HUST_MCLAB | 75.00% | 100.00% | 85.71% |
| Sensetime V1 | 75.00% | 100.00% | 85.71% |
| HoText_v1 | 75.00% | 85.71% | 80.00% |
| NVTextSpotter | 75.00% | 85.71% | 80.00% |
| Baidu IDL | 75.00% | 75.00% | 75.00% |
| e2e-mlt + bug fix | 75.00% | 75.00% | 75.00% |
 Stradvision-2 | 50.00% | 100.00% | 66.67% |
| e2e-mlt | 62.50% | 71.43% | 66.67% |
| TextProposals + DictNet | 37.50% | 100.00% | 54.55% |
| Megvii-Image++ | 37.50% | 60.00% | 46.15% |
| StradVision_v1 | 50.00% | 40.00% | 44.44% |
| DIY FOTS | 37.50% | 37.50% | 37.50% |
| SRC-B-TextProcessingLab | 25.00% | 66.67% | 36.36% |
| Yunos_Robot1.0 | 25.00% | 66.67% | 36.36% |
| NJU Text (Version3) | 25.00% | 50.00% | 33.33% |
| M_FOTS_Orig | 25.00% | 28.57% | 26.67% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 12.50% | 100.00% | 22.22% |
| Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 12.50% | 50.00% | 20.00% |
| Baseline OpenCV3.0 + Tesseract | 12.50% | 50.00% | 20.00% |
| Deep2Text-MO | 12.50% | 33.33% | 18.18% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Char-level PTSD on SynthText | 0.00% | 0.00% | 0.00% |