| Baidu IDL v3 | 90.91% | 90.91% | 90.91% |
| NVTextSpotter | 81.82% | 100.00% | 90.00% |
| Alibaba-PAI | 81.82% | 90.00% | 85.71% |
| Baidu VIS | 81.82% | 81.82% | 81.82% |
| Baidu VIS v2 | 81.82% | 81.82% | 81.82% |
| Tencent Youtu | 72.73% | 80.00% | 76.19% |
| Baidu VIS v2+ | 72.73% | 80.00% | 76.19% |
| SRC-B-MachineLearningLab | 63.64% | 87.50% | 73.68% |
| FOTS | 54.55% | 100.00% | 70.59% |
| Sensetime V1 | 63.64% | 77.78% | 70.00% |
| CPN (multi-scale) | 63.64% | 77.78% | 70.00% |
| Baidu IDL | 54.55% | 85.71% | 66.67% |
| gts-swint-cocoonly-s4-3_1 | 63.64% | 63.64% | 63.64% |
| Smile | 54.55% | 66.67% | 60.00% |
| Sogou_MM | 36.36% | 66.67% | 47.06% |
| e2e-mlt + bug fix | 45.45% | 38.46% | 41.67% |
| SRC-B-MachineLearningLab | 27.27% | 37.50% | 31.58% |
| Megvii-Image++ | 18.18% | 66.67% | 28.57% |
| e2e-mlt | 27.27% | 27.27% | 27.27% |
| Yunos_Robot1.0 | 9.09% | 50.00% | 15.38% |
| HoText_v1 | 9.09% | 14.29% | 11.11% |
| M_FOTS_Orig | 9.09% | 12.50% | 10.53% |
 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% |
| TextProposals + DictNet | 0.00% | 0.00% | 0.00% |
| SRC-B-TextProcessingLab | 0.00% | 0.00% | 0.00% |
| Char-level PTSD on SynthText | 0.00% | 0.00% | 0.00% |