AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 20 November 2026

Can LiteParse convert a cleanly scanned document into Markdown?

LiteParse recognised every word of the cleanly scanned page but did not return its text accurately: in five body sentences short words were moved onto separate lines, and five lines gained heading markers where the page has none, two of them in the middle of a sentence. The six result values and their method codes came through exactly.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

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.

Clean scan — text recoveredFailEvidence
What we sent

We converted the complete one-page scanned PDF with LiteParse 2.14.7 in Python, using the default setup with the output format set to Markdown. Nothing was typed.

InputDocument (PDF)
Input PDF: the one-page scanned laboratory report, an image with no text layer
Open the PDF ↗
What the tool returned

Copied from Output file (Markdown), lines 5–9, 17–27, 29–35, 37–43, 53–59

Markdownthe whole file · cited lines 5–9, 17–27, 29–35, 37–43 and 53–59 marked
# Kirkhollow Analytical Laboratories Ltd

Braithe Road, Vardenne BR7 2HD

### 01632960118 reception@kirkhollow-labs.example

Ms R. Sandiman Braithe Estuary Partnership

## Estuary House, Vardenne Quay

Braithe BR3 4LN

Our reference: KAL-11938/26 Date of report: 4 February 2026

Certificate of analysis

Dear Ms Sandiman Thank for the four water samples delivered to this laboratory 28 January 2026. They booked

you on were

in batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples

as

received.

as

Sampling point Vardenne Channel, station VQ1 Date and time of sampling 27 January 2026, 09:40

| Total suspended solids | 41.6 mg/l (method KAL-M04) |
|---|---|
| Chloride | 18,200 mg/l (method KAL-M11) |
| Ammoniacal nitrogen | 0.42 mg/l (method KAL-M12) |
| Dissolved organic carbon | 5.9 mg/l (method KAL-M22) |

The suspended solids figure is higher than those reported for this station in December and January, which

# both below 30 mg/l. The samples were taken the ebb, two days after the last placement at Kellow

were on

### Sands, and the result is consistent with that.

The remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to

keep them.

Yours sincerely

Dr A. J. Prosser

### Laboratory Manager

+

Registered England 2214887 Results relate only to the samples as received

in

Returned Markdown: every word of the page, with short words displaced and extra headings

Open the Markdown file ↗
Expected vs. Found
✗Expected: The text visible on the scanned page comes back accurately.Found: In five body sentences short words sat on lines of their own, and five lines carried heading markers where the page has no heading, two inside a sentence.
Supporting proof
Proof 1Screenshot
Run screenshot: the call, its stage timings and the returned Markdown beside the scanned page
Open original ↗
Why this result

It is a Fail: the page had to come back as accurate text. Every word was recognised, but displaced short words break five body sentences and five lines carry heading markers where the page has none. The product's own text recognition ran, so the shortfall is in what it returned.

Also observed in this test case

Result rows returned as table. Four of the six result values, total suspended solids, chloride, ammoniacal nitrogen and dissolved organic carbon, were returned with their method codes as a Markdown table.

Letterhead contact line altered. The letterhead's contact line came back without the phone number's internal space and the separator dot after it, and was marked as a level-3 heading.

Tested by Vamshidhar Rao Thumula · evidence dated 28 October 2026

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.

Software that produced the output
LiteParse
Build or version
LiteParse 2.14.7
Surface
SDK / library
Set up before the run
The input was a cleanly scanned one-page laboratory report: an image with no text layer, holding ordinary letter text and six result values. The complete PDF was converted to Markdown in one pass with the library's default settings.
Output format
markdown
Tested
28 October 2026 · Vamshidhar Rao Thumula

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

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.

from the publication record
20 November 2026First publishedConverting a complex PDF into clean Markdown with an open-source library v1

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/pdf-to-markdown-open-source/results/liteparse/a-cleanly-scanned-document · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-20

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.

Input · Document (PDF) ↗application/pdf · 747 KB
Output file (Markdown) ↗text/markdown; charset=utf-8 · 1 KB
Proof 1 · Screenshot ↗image/png · 929 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)a459554d58b9480b19bb3a63598c500b961c3ad377492d18ff227bb439e1f68c
Output file (Markdown)95f35e7ba7f53f1bd8e889363e7f5cf65125a496edee3a37cc71866e31627fb1
Proof 1 · Screenshot21abe89fdda8040ff88b42c681b759e5b70e335cc3f92741da9cf6c902d69583