| Baidu IDL v3 | 88.89% | 100.00% | 94.12% |
| Baidu VIS | 88.89% | 88.89% | 88.89% |
| Baidu VIS v2 | 88.89% | 88.89% | 88.89% |
| e2e-mlt + bug fix | 88.89% | 88.89% | 88.89% |
| NVTextSpotter | 88.89% | 88.89% | 88.89% |
| Tencent Youtu | 77.78% | 87.50% | 82.35% |
| Sogou_MM | 77.78% | 87.50% | 82.35% |
| Alibaba-PAI | 77.78% | 87.50% | 82.35% |
| Baidu IDL | 77.78% | 77.78% | 77.78% |
| Sensetime V1 | 77.78% | 77.78% | 77.78% |
| FOTS | 77.78% | 77.78% | 77.78% |
| CPN (multi-scale) | 77.78% | 77.78% | 77.78% |
| SRC-B-MachineLearningLab | 66.67% | 85.71% | 75.00% |
| HoText_v1 | 66.67% | 85.71% | 75.00% |
| Baidu VIS v2+ | 66.67% | 85.71% | 75.00% |
| SRC-B-MachineLearningLab | 66.67% | 75.00% | 70.59% |
| gts-swint-cocoonly-s4-3_1 | 66.67% | 75.00% | 70.59% |
| e2e-mlt | 66.67% | 60.00% | 63.16% |
| Smile | 55.56% | 55.56% | 55.56% |
| Yunos_Robot1.0 | 44.44% | 66.67% | 53.33% |
| M_FOTS_Orig | 55.56% | 45.45% | 50.00% |
| Megvii-Image++ | 44.44% | 40.00% | 42.11% |
| SRC-B-TextProcessingLab | 33.33% | 50.00% | 40.00% |
| TextProposals + DictNet | 22.22% | 50.00% | 30.77% |
 Baseline OpenCV3.0 + Tesseract | 11.11% | 50.00% | 18.18% |
| Deep2Text-MO | 11.11% | 12.50% | 11.76% |
| 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% |
| Char-level PTSD on SynthText | 0.00% | 0.00% | 0.00% |