Fine-grained multi-page document understanding subset used here for OCR precision rows imported from Papers With Code.
Precision is the reported evaluation metric for Fox English OCR subset. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.
Higher is better
Muted rows were not state of the art when published — an earlier or same-year result already scored better.
| Rank | Model | Trust | Score | Year | Links | Fix |
|---|---|---|---|---|---|---|
| 01 | deepseek-ocr-small-100-vision-tokens | verified | 98.5 | 2025 | Source ↗ | Looks wrong? |