| Paper | Code | Edit Distance | ModelName | ReleaseDate |
|---|---|---|---|---|
| DeepSeek-OCR: Contexts Optical Compression | ✓ Link | 0.123 | DeepSeek-OCR (Gundam-M) | 2025-10-21 |
| dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model | ✓ Link | 0.125 | dots.ocr | 2025-12-02 |
| Qwen3-VL Technical Report | ✓ Link | 0.143 | Qwen3-VL-235B-A22B-Instruct | 2025-11-26 |
| PaddleOCR 3.0 Technical Report | ✓ Link | 0.145 | PP-StructureV3 | 2025-07-08 |
| LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR | 0.146 | LightOnOCR-2-1B | 2026-01-20 | |
| MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe | ✓ Link | 0.175 | MiniCPM-V 4.5 | 2025-09-16 |
| Qwen2.5-VL Technical Report | ✓ Link | 0.226 | Qwen2.5-VL-72B | 2025-02-19 |