| GOCR Offline | 82.42% | 74.51% | 89.03% | 65 | 10 | 3 | 3020 | 13 | 203 | 385 |
| GOCR | 81.16% | 74.51% | 88.46% | 65 | 10 | 3 | 3020 | 13 | 246 | 385 |
| LOGO | 64.60% | 69.68% | 76.54% | 53 | 12 | 13 | 2504 | 22 | 296 | 892 |
| SVRepV2(Kuaishou-MMU) | 62.43% | 78.93% | 57.10% | 50 | 14 | 14 | 2461 | 18 | 327 | 939 |
| TA-VTT | 60.65% | 72.77% | 64.23% | 45 | 16 | 17 | 2290 | 19 | 217 | 1109 |
| TransVTSpotter | 60.01% | 71.35% | 67.62% | 48 | 20 | 10 | 2502 | 44 | 451 | 872 |
| h&h_lab | 55.00% | 74.29% | 46.91% | 50 | 10 | 18 | 2336 | 10 | 456 | 1072 |
| TransDETR | 52.14% | 71.77% | 71.96% | 42 | 15 | 21 | 2228 | 3 | 446 | 1187 |
| GoMatching++ | 51.52% | 79.12% | 71.16% | 49 | 3 | 26 | 2131 | 6 | 370 | 1281 |
| Semantic-Aware Video Text Detection | 51.40% | 72.90% | 59.24% | 39 | 12 | 27 | 1927 | 18 | 170 | 1473 |
| GoMatching | 51.14% | 79.42% | 69.10% | 48 | 2 | 28 | 2084 | 9 | 336 | 1325 |
| HIK_OCR | 47.69% | 77.28% | 60.07% | 38 | 9 | 31 | 1721 | 24 | 91 | 1673 |
 AJOU | 40.43% | 71.87% | 53.70% | 33 | 19 | 26 | 1972 | 50 | 590 | 1396 |
| SRC-B-TextProcessingLab | 37.39% | 74.94% | 42.66% | 28 | 14 | 36 | 1564 | 11 | 286 | 1843 |
| Megvii-Image++ | 33.70% | 69.51% | 48.59% | 13 | 43 | 22 | 1563 | 25 | 411 | 1830 |
| VideoTextSCM | 32.39% | 78.72% | 55.73% | 42 | 4 | 32 | 1832 | 50 | 725 | 1536 |
| USTB_TexVideo II-2 | 23.32% | 82.32% | 33.21% | 6 | 29 | 43 | 1076 | 63 | 279 | 2279 |
| USTB_TexVideo | 17.67% | 82.57% | 29.43% | 11 | 25 | 42 | 1129 | 58 | 525 | 2231 |
| USTB_TexVideo II-1 | 5.65% | 79.83% | 29.98% | 12 | 24 | 42 | 1104 | 71 | 911 | 2243 |
| RTST Lucas-Kanade-2 (RealTimeSceneText_LucasKanade_v2) | -106.03% | 62.42% | 0.95% | 0 | 6 | 72 | 28 | 93 | 3652 | 3297 |
| StradVision-1 | -2.34% | 78.79% | 21.01% | 4 | 21 | 53 | 582 | 40 | 662 | 2796 |