| gts-swint-cocoonly-s4-3_1 | 85.71% | 100.00% | 92.31% |
| Baidu VIS | 71.43% | 100.00% | 83.33% |
| Baidu VIS v2 | 71.43% | 100.00% | 83.33% |
| Alibaba-PAI | 71.43% | 100.00% | 83.33% |
| HoText_v1 | 71.43% | 83.33% | 76.92% |
| SRC-B-MachineLearningLab | 71.43% | 83.33% | 76.92% |
| NVTextSpotter | 71.43% | 83.33% | 76.92% |
| CPN (multi-scale) | 71.43% | 83.33% | 76.92% |
| Baidu IDL | 57.14% | 100.00% | 72.73% |
| Sensetime V1 | 57.14% | 100.00% | 72.73% |
| FOTS | 57.14% | 100.00% | 72.73% |
| Smile | 57.14% | 100.00% | 72.73% |
| Tencent Youtu | 57.14% | 100.00% | 72.73% |
| Sogou_MM | 71.43% | 71.43% | 71.43% |
| SRC-B-MachineLearningLab | 57.14% | 80.00% | 66.67% |
| Baidu VIS v2+ | 57.14% | 80.00% | 66.67% |
| DIY FOTS | 57.14% | 66.67% | 61.54% |
| Yunos_Robot1.0 | 42.86% | 75.00% | 54.55% |
| Baidu IDL v3 | 42.86% | 60.00% | 50.00% |
| e2e-mlt | 42.86% | 60.00% | 50.00% |
| e2e-mlt + bug fix | 42.86% | 60.00% | 50.00% |
| Megvii-Image++ | 28.57% | 100.00% | 44.44% |
| TextProposals + DictNet | 28.57% | 100.00% | 44.44% |
 Stradvision-2 | 28.57% | 50.00% | 36.36% |
| M_FOTS_Orig | 28.57% | 33.33% | 30.77% |
| HUST_MCLAB | 14.29% | 100.00% | 25.00% |
| SRC-B-TextProcessingLab | 14.29% | 50.00% | 22.22% |
| NJU Text (Version3) | 14.29% | 33.33% | 20.00% |
| StradVision_v1 | 14.29% | 11.11% | 12.50% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 0.00% | 0.00% | 0.00% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |
| Deep2Text-MO | 0.00% | 0.00% | 0.00% |
| Baseline OpenCV3.0 + Tesseract | 0.00% | 0.00% | 0.00% |
| Char-level PTSD on SynthText | 0.00% | 0.00% | 0.00% |