| Alibaba-PAI | 92.31% | 100.00% | 96.00% |
| gts-swint-cocoonly-s4-3_1 | 92.31% | 92.31% | 92.31% |
| SRC-B-MachineLearningLab | 84.62% | 100.00% | 91.67% |
| CPN (multi-scale) | 84.62% | 100.00% | 91.67% |
| Sensetime V1 | 84.62% | 91.67% | 88.00% |
| Baidu VIS v2 | 84.62% | 91.67% | 88.00% |
| Baidu VIS v2+ | 84.62% | 91.67% | 88.00% |
| Tencent Youtu | 84.62% | 84.62% | 84.62% |
| Baidu IDL v3 | 76.92% | 90.91% | 83.33% |
| FOTS | 76.92% | 90.91% | 83.33% |
| HoText_v1 | 76.92% | 90.91% | 83.33% |
| Smile | 76.92% | 90.91% | 83.33% |
| HUST_MCLAB | 69.23% | 100.00% | 81.82% |
| SRC-B-MachineLearningLab | 84.62% | 78.57% | 81.48% |
| Baidu VIS | 76.92% | 83.33% | 80.00% |
| Sogou_MM | 76.92% | 83.33% | 80.00% |
| Baidu IDL | 76.92% | 76.92% | 76.92% |
| DIY FOTS | 69.23% | 69.23% | 69.23% |
| NVTextSpotter | 69.23% | 69.23% | 69.23% |
| Megvii-Image++ | 61.54% | 72.73% | 66.67% |
| e2e-mlt + bug fix | 61.54% | 61.54% | 61.54% |
 Stradvision-2 | 46.15% | 85.71% | 60.00% |
| e2e-mlt | 53.85% | 58.33% | 56.00% |
| TextProposals + DictNet | 38.46% | 100.00% | 55.56% |
| M_FOTS_Orig | 53.85% | 53.85% | 53.85% |
| SRC-B-TextProcessingLab | 38.46% | 71.43% | 50.00% |
| Yunos_Robot1.0 | 38.46% | 62.50% | 47.62% |
| NJU Text (Version3) | 38.46% | 55.56% | 45.45% |
| StradVision_v1 | 53.85% | 33.33% | 41.18% |
| Char-level PTSD on SynthText | 23.08% | 42.86% | 30.00% |
| Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 15.38% | 40.00% | 22.22% |
| Deep2Text-MO | 7.69% | 25.00% | 11.76% |
| 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% |