benchmark with DeepSeek-OCR included
#29
by
jzhang533
- opened
OCR is definitely a hot topic in the community recently, and it's heating up even more after DeepSeek-OCR joined the field.
PaddleOCR-VL team has evaluated and included DeepSeek-OCR (Gundam-M setting) in OmniDocBench v1.5 benchmark. We hope this helps the community better understand diverse OCR approaches and contributes to advancing the field.
The HTML format version of the above benchmark image, recognized by PaddleOCR-VL.
| Model Type | Methods | Parameters | Overall↑ | TextEdit↓ | FormulaCDM↑ | TableTEDS↑ | TableTEDS-S↑ | Reading OrderEdit↓ |
| Pipeline Tools | Marker-1.8.2 [45] | - | 71.30 | 0.206 | 76.66 | 57.88 | 71.17 | 0.250 |
| Mineru2-pipeline [14] | - | 75.51 | 0.209 | 76.55 | 70.90 | 79.11 | 0.225 | |
| PP-StructureV3 [10] | - | 86.73 | 0.073 | 85.79 | 81.68 | 89.48 | 0.073 | |
| General VLMs | GPT-4o [7] | - | 75.02 | 0.217 | 79.70 | 67.07 | 76.09 | 0.148 |
| InternVL3-76B [46] | 76B | 80.33 | 0.131 | 83.42 | 70.64 | 77.74 | 0.113 | |
| InternVL3.5-241B [47] | 241B | 82.67 | 0.142 | 87.23 | 75.00 | 81.28 | 0.125 | |
| Qwen2.5-VL-72B [24] | 72B | 87.02 | 0.094 | 88.27 | 82.15 | 86.22 | 0.102 | |
| Gemini-2.5 Pro [48] | - | 88.03 | 0.075 | 85.82 | 85.71 | 90.29 | 0.097 | |
| Specialized VLMs | Dolphin [3] | 322M | 74.67 | 0.125 | 67.85 | 68.70 | 77.77 | 0.124 |
| OCRFlux-3B [49] | 3B | 74.82 | 0.193 | 68.03 | 75.75 | 80.23 | 0.202 | |
| Mistral OCR [50] | - | 78.83 | 0.164 | 82.84 | 70.03 | 78.04 | 0.144 | |
| POINTS-Reader [4] | 3B | 80.98 | 0.134 | 79.20 | 77.13 | 81.66 | 0.145 | |
| olmOCR-7B [12] | 7B | 81.79 | 0.096 | 86.04 | 68.92 | 74.77 | 0.121 | |
| MinerU2-VLM [14] | 0.9B | 85.56 | 0.078 | 80.95 | 83.54 | 87.66 | 0.086 | |
| Nanonets-OCR-s [51] | 3B | 85.59 | 0.093 | 85.90 | 80.14 | 85.57 | 0.108 | |
| DeepSeek-OCR-Gundam-M | 3B | 86.46 | 0.081 | 89.45 | 78.02 | 81.55 | 0.093 | |
| MonkeyOCR-pro-1.2B [1] | 1.9B | 86.96 | 0.084 | 85.02 | 84.24 | 89.02 | 0.130 | |
| MonkeyOCR-3B [1] | 3.7B | 87.13 | 0.075 | 87.45 | 81.39 | 85.92 | 0.129 | |
| dots.ocr [52] | 3B | 88.41 | 0.048 | 83.22 | 86.78 | 90.62 | 0.053 | |
| MonkeyOCR-pro-3B [1] | 3.7B | 88.85 | 0.075 | 87.25 | 86.78 | 90.63 | 0.128 | |
| MinerU2.5 [2] | 1.2B | 90.67 | 0.047 | 88.46 | 88.22 | 92.38 | 0.044 | |
| PaddleOCR-VL | 0.9B | 92.56 | 0.035 | 91.43 | 89.76 | 93.52 | 0.043 |