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

Can Reducto convert an ordinary digital text document into clean Markdown without missing, garbling, or inventing text?

Reducto failed this ordinary text document test: the output kept the body text, but it joined the page-1 running header to the next line and created a sentence the source does not contain. The other six page breaks kept furniture in separate blocks, and the complete seven-page PDF was sent on the default parse pipeline.

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.

Ordinary digital text — complete and unchangedFailEvidence
What we sent

We sent the complete seven-page briefing note to Reducto’s hosted parse API in one request, without configuration overrides.

InputDocument (PDF)
Source PDF with seven plain-text pages and running headers
Open the PDF ↗
What the tool returned

Returned Markdown with the page-1 header welded into body text

Copied from Output file (Markdown), lines 31–36

Markdown
Page 1 of 7

Braithe Estuary Partnership
have shown so far.

Briefing note BEP/BN/2026/04
Open the Markdown file ↗

Raw parse response with parsed document data and no override

Copied from Output file (JSON), result · an excerpt

JSON
{
  "type": "full",
  "chunks": [
    {
      "content": "Braithe Estuary Partnership\n\nBriefing note BEP/BN/2026/04\n\n# Sediment recharge at Kellow Sands: the 2025/26 placement\n\nPrepared by the technical secretariat for the Partnership Board · 12 February 2026\n\n## Background\n\nThe Partnership has pl … [19,016 characters in the file]",
      "embed": "Braithe Estuary Partnership\n\nBriefing note BEP/BN/2026/04\n\n# Sediment recharge at Kellow Sands: the 2025/26 placement\n\nPrepared by the technical secretariat for the Partnership Board · 12 February 2026\n\n## Background\n\nThe Partnership has pl … [19,016 characters in the file]",
      "enriched": null,
      "enrichment_success": false,
      "blocks": [
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}",
        "{… 8 fields in the file}"
      ]
    }
  ],
  "ocr": null,
  "custom": null
}

Excerpt ends here. Open the source for the complete output.

Open the whole JSON file ↗
Expected vs. Found
✗Expected: All text is present and unchanged — nothing is missing, garbled, or inventedFound: The body text stays present, but the page-1 header joins the next line, producing a sentence the source does not contain.
Supporting proof
Proof 1Screenshot
Run card with success, timing, plan, pipeline, and sent file
Open original ↗
Proof 2Screenshot
Page 1 comparison: source and output match except the welded break
Open original ↗
Proof 3Screenshot
Source-versus-Markdown crop of the page-1 break with Markdown output on right
Open original ↗
Proof 4Screenshot
Page 2 comparison: source and output match, with furniture separated cleanly
Open original ↗
Proof 5Screenshot
Page 3 comparison: source and output match, with separate page furniture
Open original ↗
Proof 6Screenshot
Page 4 comparison: source and output match, including the water-quality figure
Open original ↗
Proof 7Screenshot
Page 5 comparison: source and output match, including the valuation figure
Open original ↗
Proof 8Screenshot
Page 6 comparison: source and output match, with furniture separated cleanly
Open original ↗
Proof 9Screenshot
Page 7 comparison: source and output match through the closing line
Open original ↗
Cited values2 values from this file
job_id
b71ad6f9-2cfd-44ee-b830-8b3544d4a339
usage
{ "num_pages": 7, "credits": 7, "credit_breakdown": { "page": 7 }, "page_billing_breakdown": { "1": ["page"], "2": ["page"], "3": ["page"], "4": ["page"], "5": ["page"], "6": ["page"], "7": ["page"] }, "non_empty_cell_count": null }
Why this result

The complete seven-page PDF was processed on the default parse pipeline, and the output kept the body text but welded the page-1 running header onto the next line. That adds a sentence the source does not contain, so the text is not unchanged.

Also observed in this test case

Header kept. It kept the document identifier from the running header.

Other breaks. At the other six page breaks, headers and footers stayed in separate blocks.

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
Reducto
Build or version
Not exposed by the hosted product
Plan or tier
Standard self-serve plan
Surface
API
Set up before the run
A short plain-paragraph PDF had to be processed as the complete file, in one default parse pass with no per-tool tuning.
Pipeline
default parse pipeline; no configuration overrides · POST https://platform.reducto.ai/parse · 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
21 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/reducto/an-ordinary-digital-text-document · 0 pass · 1 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.

Input · Document (PDF) ↗application/pdf · 103 KB
Output file (JSON) ↗application/json · 116 KB
Output file (Markdown) ↗text/markdown; charset=utf-8 · 19 KB
Proof 1 · Screenshot ↗image/png · 100 KB
Proof 2 · Screenshot ↗image/png · 613 KB
Proof 3 · Screenshot ↗image/png · 68 KB
Proof 4 · Screenshot ↗image/png · 629 KB
Proof 5 · Screenshot ↗image/png · 584 KB
Proof 6 · Screenshot ↗image/png · 659 KB
Proof 7 · Screenshot ↗image/png · 625 KB
Proof 8 · Screenshot ↗image/png · 579 KB
Proof 9 · Screenshot ↗image/png · 392 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)291669466fefcdd19a890091f82c0fba09f8ddce2882ef5755c52d8abe28ffa1
Output file (JSON)a6d21b63ff8c8c0d389f36750a68ffce44fbd8d6767047a644f20604859b8f00
Output file (Markdown)04ee3f1069c800f426f0d0f4c00586c9e29cb33e45ee375124a565f91785f25b
Proof 1 · Screenshot8dc108fec7eb2f60867ce9b09ce5ccd31a3e4c4882ce9081a183fa7fda78b261
Proof 2 · Screenshot9d15f5dfe2f646d93157706249913de8784f6ba0d671843abe8b76901ffe2124
Proof 3 · Screenshot47025c76e06ad043ba4e0a9c29e7e290eeee9205974390c8b6230f7bc7f6b25b
Proof 4 · Screenshot9fa92ed2e0eede7b7765064752eaa6ae3ea1ba792ef62a8197c58aad9f1c7025
Proof 5 · Screenshotbed8e029bdc16895aaa43ed9a0674167169ec8435386efd5408d9b0fe6601344
Proof 6 · Screenshot1221b7b5dec36cef4aaaf8babcdfd586f45df308900990258ac13167088c7c9f
Proof 7 · Screenshot0b267a4c13b11a574b8e05a4747405f99c06921d6990bf3e85fdfff62f6b50f7
Proof 8 · Screenshot45ee2c1d60471cf9749a65cf7f0955be9b04c2d8eabddfcabb9b316e734d077c
Proof 9 · Screenshotfc709819133f670e70571f57473ac64ec7de5e048792496a70d1102ebda93f19