AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 18 October 2026

Does Nutrient.io keep a simple table formatted correctly?

Nutrient.io failed to keep the simple table intact in the default Build API run. The output kept all values, row count, and row order, but merged the method and turnaround headers and cells.

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.

Simple table — structure retainedFailEvidence
What we sent
InputDocument (PDF)
Input PDF: page 1 table and later prose pages
Open the PDF ↗
What the tool returned
Markdown
  <th>Determination</th>
  <th>Method Turnaround</th>
  <th>Charge per sample</th>

Markdown output: one table with merged method and turnaround cells

Copied from Output file (Markdown), lines 22–24

Open the Markdown file ↗
Markdown
 </tr>
 <tr>
  <td>Total suspended solids</td>
  <td>KAL-M04 2 days</td>
  <td>£18.40</td>
 </tr>
 <tr>
  <td>Chloride</td>
  <td>KAL-M11 3 days</td>
  <td>£21.75</td>
 </tr>
 <tr>
  <td>Ammoniacal nitrogen</td>
  <td>KAL-M12 4 days</td>
  <td>£26.50</td>
 </tr>
 <tr>
  <td>Total oxidised nitrogen</td>
  <td>KAL-M13 5 days</td>
  <td>£29.20</td>
 </tr>
 <tr>
  <td>Orthophosphate</td>
  <td>KAL-M15 6 days</td>
  <td>£31.60</td>
 </tr>
 <tr>
  <td>Dissolved organic carbon</td>
  <td>KAL-M22 7 days</td>
  <td>£44.05</td>
 </tr>
 <tr>
  <td>Metals suite, eleven elements</td>
  <td>KAL-M31 8 days</td>
  <td>£96.80</td>
 </tr>
 <tr>
  <td>Particle size distribution</td>
  <td>KAL-M47 10 days</td>
  <td>£58.35</td>
 </tr>

Copied from Output file (Markdown), lines 25–65

JSON
{
  "status_code": 200,
  "headers": {
    "date": "Wed, 09 Sep 2026 08:52:08 GMT",
    "content-type": "text/markdown",
    "content-length": "9225",
    "content-disposition": "attachment; filename=\"result.md\"",
    "server": "Cowboy",
    "x-pspdfkit-remaining-credits": "45",
    "x-pspdfkit-request-cost": "1",
    "x-request-id": "GNObBeJvIyP70CUAAPSh"
  },
  "content_type": "text/markdown",
  "body_bytes": 9225,
  "delivery": "raw markdown body (content-type text/markdown)",
  "markdown_chars": 9210,
  "zip_members": null,
  "asset_names": null
}

HTTP capture: request details and successful Markdown response

Copied from Captured file (JSON), response

Open the whole JSON file ↗
Expected vs. Found
✗Expected: The table stays a table, with the right headers, rows, columns, and values.Found: All values, row order, and row count stayed correct, but the output merged the method and turnaround into one header and one cell per row.
Supporting proof
Proof 1Screenshot
Comparison frame: source table beside returned Markdown
Open original ↗
Proof 2Screenshot
Run card: default pipeline settings and output size
Open original ↗
Why this result

On the default Build API pipeline, it is a fail, not a pass: the table structure was not intact because method and turnaround were merged into one column, even though values, row count, and row order stayed correct.

Also observed in this test case

Rows preserved. All eight rows and all 32 values were preserved, with row order unchanged.

Other API kept columns. A separate Data Extraction API run returned all four columns and correct headers.

Tested by Chandresh Bisht · evidence dated 9 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
Nutrient.io
Build or version
not exposed (DWS Build API, unversioned /build endpoint)
Plan or tier
free tier
Surface
API
Set up before the run
A small PDF with one clear table; convert the whole file to Markdown in one default pass, without per-tool tuning or cropping pages.
Pipeline
Build API default pipeline, output.type=markdown, no actions, single pass
Tested
9 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
5 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/nutrient-io/a-simple-clearly-formatted-table · 0 pass · 1 fail · coverage 1/1 · graded 2026-10-18

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 · 92 KB
Output file (Markdown) ↗text/markdown · 9 KB
Captured file (JSON) ↗application/json · 1 KB
Proof 1 · Screenshot ↗image/png · 207 KB
Proof 2 · Screenshot ↗image/png · 49 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)2f2a8244eb2e45042de1c4652eeebc8b14c579f55c5a1a8b73e7b21e051e5ee7
Output file (Markdown)2b0e594eddce9f71cf332327d5d610462ac210b68bc2bc4d06fde9512255659e
Captured file (JSON)d9ed99984d1ceabbb4dee856890bee8361aa11f9aab2223b01e3d7e3327b706d
Proof 1 · Screenshot6cb75d3e18a51afbc6687a401c92abfc48ee1c8d78a58fef2d402534d305d8f3
Proof 2 · Screenshotdd320d5d584a917d8c9faddc1fb1c778cea40bf22786d2c585229041237375b0