Scenario in benchmark · Version 1
A cleanly scanned document
A document is scanned and image-only, so its visible text must be recovered without relying on a text layer.
How the tools performed
Every in-scope tool is visible. Outcomes come from current published Results for this scenario and benchmark version.
No published results for this scenario yet.
No published result does not tell you whether a tool has been tested. Test coverage is shown only for comparable published Results.
| Tool | Published outcomes | Test coverage | Result |
|---|---|---|---|
| No published result · alphabetical | |||
| doc2mark | — | — | No published result |
| Docling | — | — | No published result |
| GPT-5.6 terra | — | — | No published result |
| LiteParse | — | — | No published result |
| Marker | — | — | No published result |
| MarkItDown | — | — | No published result |
| MinerU | — | — | No published result |
| olmOCR | — | — | No published result |
| PaddleOCR-VL | — | — | No published result |
| PyMuPDF4LLM | — | — | No published result |
Assessed = Pass + Fail + Not gradable. Gradable = Pass + Fail. Both use the published Result’s pinned-test denominator. — means not publicly available.
Test design
- Pinned test cases
- 1
- Disclosure
- 1 public · 0 withheld
- Capabilities exercised here
- Scanned Document OCR
What this scenario evaluates
- Whether the visible text from the scanned page is recovered accurately.
- Whether the page is not silently skipped or treated as empty because no text layer exists.
- Whether the output stays faithful to the visible content without inventing text.
- Whether scanned pages are handled as real input, not hidden by omission.
Exact wording, inputs, fixture state, expected output and detailed grading remain at the test-case level and may be withheld while the benchmark version is active. The scenario and its evaluation intent are public.
How the results are graded
- Pass: the test-case expectations hold.
- Fail: an expectation demonstrably does not hold.
- Not gradable: the evidence cannot establish the outcome.
Version 1 uses test-case expectations; no scenario rubric is pinned.
Benchmark methodology →