| Sample Ranking | MOTA | MOTP | IDF1 | Mostly Matched | Partially Matched | Mostly Lost | Matches | Switches | False Positives | Misses |
|---|---|---|---|---|---|---|---|---|---|---|
| GoMatching | 80.48% | 73.20% | 84.05% | 2 | 1 | 0 | 549 | 6 | 9 | 116 |
| LOGO | 78.99% | 67.47% | 84.73% | 2 | 1 | 0 | 553 | 4 | 23 | 114 |
| CoText(Kuaishou_MMU) | 69.00% | 75.20% | 83.70% | 2 | 1 | 0 | 548 | 3 | 85 | 120 |
| TransDETR | 67.66% | 73.45% | 63.60% | 0 | 3 | 0 | 466 | 5 | 12 | 200 |
| GOCR | 65.28% | 70.30% | 73.56% | 2 | 1 | 0 | 538 | 7 | 100 | 126 |
| GOCR Offline | 63.19% | 70.83% | 75.92% | 1 | 2 | 0 | 512 | 4 | 88 | 155 |
| CoText | 62.59% | 73.75% | 75.27% | 0 | 3 | 0 | 433 | 7 | 13 | 231 |
| h&h_lab | 53.65% | 79.30% | 70.18% | 0 | 3 | 0 | 366 | 0 | 6 | 305 |
| SRC-B-TextProcessingLab | 32.94% | 70.33% | 51.30% | 0 | 3 | 0 | 237 | 0 | 16 | 434 |
| HIK_OCR | 32.49% | 79.00% | 49.02% | 0 | 2 | 1 | 234 | 1 | 16 | 436 |
| Megvii-Image++ | 31.89% | 73.00% | 40.31% | 0 | 3 | 0 | 221 | 4 | 7 | 446 |
 Deep2Text I (Video) | 25.78% | 70.38% | 33.40% | 0 | 3 | 0 | 227 | 6 | 54 | 438 |
| USTB_TexVideo | 22.80% | 71.39% | 23.71% | 0 | 3 | 0 | 199 | 12 | 46 | 460 |
| Stradvision-1 | 19.67% | 76.70% | 23.58% | 0 | 3 | 0 | 178 | 21 | 46 | 472 |
| USTB_TexVideo II-2 | 14.01% | 77.51% | 14.67% | 0 | 2 | 1 | 127 | 14 | 33 | 530 |
| USTB_TexVideo II-1 | 1.64% | 70.94% | 22.08% | 0 | 3 | 0 | 151 | 7 | 140 | 513 |
| Baseline-TextSpotter | ||||||||||