AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 30 October 2026

Can LlamaParse turn a clean scan into accurate text?

LlamaParse recovered every printed word of the image-only certificate correctly, including the station code VQ1, all five mg/l readings, the four method codes and the dates. The six-row results block came back as a table, and the only addition was a line standing in for the handwritten signature.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
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 recoveredPassEvidence
What we sent

We uploaded the complete one-page scanned PDF to LlamaParse's v2 parse endpoint at its documented default tier, with no tuning.

InputDocument (PDF)
Input PDF: the one-page scanned certificate of analysis, with no text layer
Open the PDF ↗
What the tool returned
Markdown
## Kirkhollow Analytical Laboratories Ltd

Braithe Road, Vardenne BR7 2HD
01632 960118 · 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 you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.

<table>
    <tr>
        <td>Sampling point</td>
<td>Vardenne Channel, station VQ1</td>
    </tr>
<tr>
        <td>Date and time of sampling</td>
<td>27 January 2026, 09:40</td>
    </tr>
<tr>
        <td>Total suspended solids</td>
<td>41.6 mg/l (method KAL-M04)</td>
    </tr>
<tr>
        <td>Chloride</td>
<td>18,200 mg/l (method KAL-M11)</td>
    </tr>
<tr>
        <td>Ammoniacal nitrogen</td>
<td>0.42 mg/l (method KAL-M12)</td>
    </tr>
<tr>
        <td>Dissolved organic carbon</td>
<td>5.9 mg/l (method KAL-M22)</td>
    </tr>
</table>

The suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow 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

signature: Dr A. J. Prosser

Dr A. J. Prosser
Laboratory Manager

Registered in England 2214887 · Results relate only to the samples as received

Returned Markdown: the certificate's text, with the results block as a table

Copied from Output file (Markdown), lines 1–60

Open the Markdown file ↗
Key momentslines 1–54
Output file (JSON)
Raw API response: the same Markdown with the job record
Cited values2 values from this file
markdown_full
## Kirkhollow Analytical Laboratories Ltd Braithe Road, Vardenne BR7 2HD 01632 960118 · 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 you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received. <table> <tr> <td>Sampling point</td> <td>Vardenne Channel, station VQ1</td> </tr> <tr> <td>Date and time of sampling</td> <td>27 January 2026, 09:40</td> </tr> <tr> <td>Total suspended solids</td> <td>41.6 mg/l (method KAL-M04)</td> </tr> <tr> <td>Chloride</td> <td>18,200 mg/l (method KAL-M11)</td> </tr> <tr> <td>Ammoniacal nitrogen</td> <td>0.42 mg/l (method KAL-M12)</td> </tr> <tr> <td>Dissolved organic carbon</td> <td>5.9 mg/l (method KAL-M22)</td> </tr> </table> The suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow 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 signature: Dr A. J. Prosser Dr A. J. Prosser Laboratory Manager Registered in England 2214887 · Results relate only to the samples as received
job
{ "user_metadata": null, "id": "pjb-nznlkop4yh3lv7d7d5o6tynyb0kp", "created_at": "2026-09-10T13:26:26.807772Z", "updated_at": "2026-09-10T13:26:45.579169Z", "project_id": "f2cfef38-e7e3-4955-be62-16148c6f1b96", "status": "COMPLETED", "error_message": null, "name": "certificate_of_analysis_KAL-11938.pdf", "tier": "agentic", "usage": { "credits": 10 } }
Show the whole file (5 KB)
JSON
{
  "job": {
    "user_metadata": null,
    "id": "pjb-nznlkop4yh3lv7d7d5o6tynyb0kp",
    "created_at": "2026-09-10T13:26:26.807772Z",
    "updated_at": "2026-09-10T13:26:45.579169Z",
    "project_id": "f2cfef38-e7e3-4955-be62-16148c6f1b96",
    "status": "COMPLETED",
    "error_message": null,
    "name": "certificate_of_analysis_KAL-11938.pdf",
    "tier": "agentic",
    "usage": {
      "credits": 10.0
    }
  },
  "result_content_metadata": null,
  "text": null,
  "markdown": {
    "pages": [
      {
        "page_number": 1,
        "markdown": "## Kirkhollow Analytical Laboratories Ltd\n\nBraithe Road, Vardenne BR7 2HD\n01632 960118 \u00b7 reception@kirkhollow-labs.example\n\n---\n\nMs R. Sandiman\nBraithe Estuary Partnership\nEstuary House, Vardenne Quay\nBraithe BR3 4LN\n\n**Our reference**: KAL-11938/26\n**Date of report**: 4 February 2026\n\n## Certificate of analysis\n\nDear Ms Sandiman\n\nThank you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.\n\n<table>\n    <tr>\n        <td>Sampling point</td>\n        <td>Vardenne Channel, station VQ1</td>\n    </tr>\n    <tr>\n        <td>Date and time of sampling</td>\n        <td>27 January 2026, 09:40</td>\n    </tr>\n    <tr>\n        <td>Total suspended solids</td>\n        <td>41.6 mg/l (method KAL-M04)</td>\n    </tr>\n    <tr>\n        <td>Chloride</td>\n        <td>18,200 mg/l (method KAL-M11)</td>\n    </tr>\n    <tr>\n        <td>Ammoniacal nitrogen</td>\n        <td>0.42 mg/l (method KAL-M12)</td>\n    </tr>\n    <tr>\n        <td>Dissolved organic carbon</td>\n        <td>5.9 mg/l (method KAL-M22)</td>\n    </tr>\n</table>\n\nThe suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow Sands, and the result is consistent with that.\n\nThe remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to keep them.\n\nYours sincerely\n\nsignature: Dr A. J. Prosser\n\nDr A. J. Prosser\nLaboratory Manager",
        "footer": "Registered in England 2214887 \u00b7 Results relate only to the samples as received",
        "success": true
      }
    ]
  },
  "items": null,
  "metadata": {
    "pages": [
      {
        "page_number": 1,
        "confidence": 0.917,
        "original_orientation_angle": 0,
        "cost_optimized": false,
        "triggered_auto_mode": false
      }
    ],
    "document": {}
  },
  "forms": null,
  "markdown_full": "## Kirkhollow Analytical Laboratories Ltd\n\nBraithe Road, Vardenne BR7 2HD\n01632 960118 \u00b7 reception@kirkhollow-labs.example\n\n----\n\nMs R. Sandiman\nBraithe Estuary Partnership\nEstuary House, Vardenne Quay\nBraithe BR3 4LN\n\n**Our reference**: KAL-11938/26\n**Date of report**: 4 February 2026\n\n## Certificate of analysis\n\nDear Ms Sandiman\n\nThank you for the four water samples delivered to this laboratory on 28 January 2026. They were booked in as batch KAL-11938 and analysed by the methods shown. The results below relate only to the samples as received.\n\n<table>\n    <tr>\n        <td>Sampling point</td>\n<td>Vardenne Channel, station VQ1</td>\n    </tr>\n<tr>\n        <td>Date and time of sampling</td>\n<td>27 January 2026, 09:40</td>\n    </tr>\n<tr>\n        <td>Total suspended solids</td>\n<td>41.6 mg/l (method KAL-M04)</td>\n    </tr>\n<tr>\n        <td>Chloride</td>\n<td>18,200 mg/l (method KAL-M11)</td>\n    </tr>\n<tr>\n        <td>Ammoniacal nitrogen</td>\n<td>0.42 mg/l (method KAL-M12)</td>\n    </tr>\n<tr>\n        <td>Dissolved organic carbon</td>\n<td>5.9 mg/l (method KAL-M22)</td>\n    </tr>\n</table>\n\nThe suspended solids figure is higher than those reported for this station in December and January, which were both below 30 mg/l. The samples were taken on the ebb, two days after the last placement at Kellow Sands, and the result is consistent with that.\n\nThe remaining samples will be held until 4 March 2026 and destroyed after that date unless you ask us to keep them.\n\nYours sincerely\n\nsignature: Dr A. J. Prosser\n\nDr A. J. Prosser\nLaboratory Manager\n\nRegistered in England 2214887 \u00b7 Results relate only to the samples as received\n",
  "text_full": null,
  "images_content_metadata": {
    "total_count": 0,
    "images": []
  },
  "job_metadata": {
    "state_transitions": {
      "pending_at": "2026-09-10T13:26:26.801472Z",
      "throttled_at": "2026-09-10T13:26:27.027887Z",
      "running_at": "2026-09-10T13:26:27.249934Z",
      "completed_at": "2026-09-10T13:26:45.581431Z",
      "failed_at": null,
      "cancelled_at": null
    },
    "quarantine": null,
    "pdf-pages": 1,
    "pdf-real-pages": 1,
    "pdf-rawTextLength": 1511,
    "pdf-mdLength": 1638,
    "pdf-time": 8747,
    "pdf-ocrTime": 0,
    "pdf-image-convertTime": 0,
    "pdf-pdfToHTMLTime": 0,
    "pdf-llmTime": 7050,
    "pdf-inputTokens": 19422,
    "pdf-outputTokens": 735,
    "pdf-image-ocr-count": 0,
    "pdf-image-ocr-failed-count": 0,
    "pdf-image-ocr-success-count": 14,
    "pdf-image-ocr-empty-count": 2,
    "pdf-image-ocr-hadText-count": 12,
    "pdf-image-ocr-pixels": 16243202,
    "pdf-multimodal-time": 0,
    "pdf-multimodal-pdf2Image": 0,
    "pdf-high-res-ocr": 1
  },
  "raw_parameters": null,
  "debug": null
}
Open the JSON file ↗
Expected vs. Found
✓Expected: The visible text on the scanned page is recovered accurately.Found: Every printed word is present and correct, including VQ1, the five mg/l readings, 18,200 with its separator and all three dates; one line was added for the signature.
Supporting proof
Proof 1Screenshot
Comparison sheet: the scanned page beside the complete returned Markdown
Open original ↗
Why this result

The test needed the visible text of an image-only page recovered accurately. Read against the page, every printed word is present and correct; the one added line describes the handwritten signature and changes no printed text.

Also observed in this test case

Signature line added. The output adds a line describing the handwritten signature, text the page does not print.

Results block as a table. The six-row results block came back as an HTML table rather than plain lines.

Tested by Chandresh Bisht · evidence dated 10 September 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
LlamaParse
Build or version
Parse API v2, tier agentic, version latest (build not exposed)
Plan or tier
free tier
Surface
API
Set up before the run
A one-page image-only certificate of analysis with ordinary printed text and no text layer, sent whole to the product's default pipeline in one pass with no tuning.
Pipeline
documented default, single pass, no tuning
Tested
10 September 2026 · Chandresh Bisht

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
17 November 2026First publishedConverting a complex PDF into clean Markdown with a hosted API 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-apis/results/llamaparse/a-cleanly-scanned-document · 1 pass · 0 fail · coverage 1/1 · graded 2026-10-30

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.

Proof 1 · Screenshot ↗image/png · 1.2 MB
Input · Document (PDF) ↗application/pdf · 747 KB
Output file (Markdown) ↗text/markdown; charset=utf-8 · 2 KB
Output file (JSON) ↗application/json · 5 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Proof 1 · Screenshotd82b1e0f5006dddabce1a8a54df457c02dba417eb2a847ef5f8f65b99b3e1c9d
Input · Document (PDF)a459554d58b9480b19bb3a63598c500b961c3ad377492d18ff227bb439e1f68c
Output file (Markdown)a227fa27416df2a3e0a9644ae9fb60fd5b68edce21ab2aec437f77a959379f37
Output file (JSON)84e4dd0085b97ff2a19c1a9b7c3372f1c206eba678459a6e95a4a2b7334d55da
Can LlamaParse turn a clean scan into accurate text? — LlamaParse | AI Demos Research