| Baidu VIS v2+ | 100.00% | 91.67% | 95.65% |
| Baidu IDL v3 | 90.91% | 90.91% | 90.91% |
| Baidu VIS | 90.91% | 90.91% | 90.91% |
| SRC-B-MachineLearningLab | 90.91% | 90.91% | 90.91% |
| Baidu VIS v2 | 90.91% | 90.91% | 90.91% |
| Alibaba-PAI | 90.91% | 90.91% | 90.91% |
| Sogou_MM | 81.82% | 100.00% | 90.00% |
| gts-swint-cocoonly-s4-3_1 | 90.91% | 83.33% | 86.96% |
| Tencent Youtu | 81.82% | 90.00% | 85.71% |
| CPN (multi-scale) | 90.91% | 76.92% | 83.33% |
| Smile | 81.82% | 81.82% | 81.82% |
| e2e-mlt + bug fix | 81.82% | 75.00% | 78.26% |
| NVTextSpotter | 81.82% | 75.00% | 78.26% |
| Yunos_Robot1.0 | 63.64% | 100.00% | 77.78% |
| FOTS | 63.64% | 87.50% | 73.68% |
| SRC-B-MachineLearningLab | 72.73% | 72.73% | 72.73% |
| e2e-mlt | 72.73% | 72.73% | 72.73% |
| Sensetime V1 | 72.73% | 66.67% | 69.57% |
| Megvii-Image++ | 63.64% | 70.00% | 66.67% |
| Baidu IDL | 63.64% | 63.64% | 63.64% |
| HoText_v1 | 63.64% | 63.64% | 63.64% |
| Char-level PTSD on SynthText | 45.45% | 50.00% | 47.62% |
 Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 36.36% | 57.14% | 44.44% |
| M_FOTS_Orig | 45.45% | 38.46% | 41.67% |
| Deep2Text-MO | 27.27% | 50.00% | 35.29% |
| TextProposals + DictNet | 27.27% | 42.86% | 33.33% |
| SRC-B-TextProcessingLab | 27.27% | 33.33% | 30.00% |
| Baseline OpenCV3.0 + Tesseract | 9.09% | 50.00% | 15.38% |
| Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |
| Beam search CUNI (decoding for TextSpotter - spell checked) | 0.00% | 0.00% | 0.00% |