Scanned Document OCR
Whether image-only pages are turned into accurate text instead of being skipped or left unread.
2 scenarios · 0 current published Results · 0 tools with published Results
How the tools performed
Explore current published Results across this capability’s scenarios. Open a scenario to compare its tools, or a Result to inspect the evidence.
No published Results are available for this capability in this benchmark.
Publication availability does not describe testing status.
Scenarios in this capability
| Participating tool | A cleanly scanned document → | A document mixing digital and scanned pages → |
|---|---|---|
| doc2mark | No published result across these scenarios | |
| Docling | No published result across these scenarios | |
| GPT-5.6 terra | No published result across these scenarios | |
| LiteParse | No published result across these scenarios | |
| Marker | No published result across these scenarios | |
| MarkItDown | No published result across these scenarios | |
| MinerU | No published result across these scenarios | |
| olmOCR | No published result across these scenarios | |
| PaddleOCR-VL | No published result across these scenarios | |
| PyMuPDF4LLM | No published result across these scenarios | |
Reading the comparison
Publication availability and test coverage describe different things.
Publication is not testing progress
“No published result” says only that there is no current public Result. It does not indicate whether a tool has been tested, passed, failed or is applicable.
Read each Result’s test set
Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Each fraction uses the pinned tests in that same published Result.
Choose the view you need
A scenario compares tools on one situation. A tool page follows one tool across this benchmark. A Result explains the outcome and shows the evidence.