Does Docling process a scanned page inside a mixed PDF instead of skipping it?
Docling included the scanned worksheet's text and values in the Markdown output instead of skipping the page. The worksheet stayed in its original position between the surrounding pages.
1 of 1 test case passed
Every test case in this scenario has a result.
The test case
Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.
Mixed pages — scanned page not skippedPassEvidence
We converted the complete three-page equipment service report to Markdown in one pass using Docling's library.
## Equipment service report CLIENT Braithe Estuary Partnership Estuary House, Vardenne Quay Braithe BR3 4LN | Job reference | KAL-ESR-4471 | |------------------|--------------------------------| | Date of visit | 29 January 2026 | | Engineer | R. Tarbert | | Instrument | Kestrel 400 turbidity analyser | | Location | Vardenne Quay pumping station | | Service interval | Twelve months | ## Reported fault Intermittent baseline noise on channel 2, reported by the Partnership on 21 January. The analyser had been running without attention since the annual service in January 2025. ## Work carried out The flow cell was removed, stripped and cleaned, and the pump tubing set replaced. The optical window was found to be lightly fouled on the inner face; it was cleaned rather than replaced, and should be inspected again at the next visit. The analyser was recalibrated against the two-point standards and left running on channel 2 for an hour before the site was handed back. The completed worksheet is bound in as page 2 of this report. ## Kirkhollow Analytical Laboratories Ltd Service worksheet Job reference Instrument serial Engineer Date KAL-ESR-4471 GK-2214-77 R. Tarbert 29·January 2026 ## CHECKS AND READINGS Flow cell condition on arrival Flow cell pressure after service Zero drift over 30 minutes Span recovery against standard Lamp hours at service Result Fouled, inner face 2.4 bar 0.003 mg/l 99.4 per cent 8,140 Pass ## Calibration certificate SR-4471/2 Analyser left in service on channel 2. Optical window to be inspected at the next visit. TIME ON SITE Arrived Left Chargeable time Next service due 29 January 2026, 09:15 29 January 2026, 13:40 4 hours 25 minutes January 2027 ## RECEIVED BY Name Position Date M. Cairney Duty operator, Vardenne Quay 29 January 2026 <!-- image --> Engineer's signature FIELD SERVICE ## Parts fitted | Part | Code | Quantity | |-------------------------|---------|------------| | Pump tubing set | PT-114 | 1 | | Flow cell O-ring, 12 mm | OR-0912 | 2 | | Inlet filter, 40 micron | IF-4004 | 1 | ## Declaration The work described in this report was carried out to the standard set out in the service agreement. The analyser was left in service and calibrated. The next annual service falls due in January 2027. | Engineer | R. Tarbert | |---------------|------------------| | Countersigned | Dr A. J. Prosser | | Report issued | 2 February 2026 |
Returned Markdown: scanned-page text included between the digital pages
Copied from Output file (Markdown), lines 1–23, 25–63, 65–99, 101–116
Open the Markdown file ↗| ✓ | Expected: Include the scanned page's text in the output alongside the digital pages, without skipping it.Found: The scanned page's full text appears between the content from pages 1 and 3; nothing from that page is skipped. |
The default whole-document conversion recovered the image-only middle page in the right position with every value correct. This meets the requirement to preserve scanned text alongside digital text.
Worksheet label–value layout. In the scanned worksheet's job details and checks, labels appear in groups followed by their values. Readers must pair them by position; no content is lost.
Minor text artefacts. The worksheet date contains a stray dot between the day and month. Its date and result labels join the job reference and flow-cell condition, respectively.
Repeated headers and footers. The digital pages' repeated company header, job reference and page numbers are absent from the Markdown.
Configuration and setup
How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.
How this scenario is graded
How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.
Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.
- Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
- Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
- Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.
Where this sits in the benchmark
This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.
| Level | Name | Scope |
|---|---|---|
| Benchmark | Converting a complex PDF into clean Markdown with an open-source library → | 12 scenarios · 10 tools |
| Capability | Scanned Document OCR → | |
| Scenario | A document mixing digital and scanned pages → | |
| Tool | Docling → |
Global scenario definition → · Global capability definition → · Docling product page →
History of this result
What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.
Act on this result
Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.
You run the same kind of test against your own setup and get the same behaviour.
Agree →Yours behaves differently. Tell us what you got, with a screenshot if you have one.
Disagree →Something here is wrong — a reference value, a transcription, a grade.
Report an issue →Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.
Vendor notice →The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.
Verify the proof files
These files support this result. Open a file to inspect the original evidence.
File fingerprints (SHA-256)
A fingerprint identifies the exact file used for this result.