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.
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
We sent the complete seven-page briefing note to Reducto’s hosted parse API in one request, without configuration overrides.
Returned Markdown with the page-1 header welded into body text
Copied from Output file (Markdown), lines 31–36
Page 1 of 7 Braithe Estuary Partnership have shown so far. Briefing note BEP/BN/2026/04
Raw parse response with parsed document data and no override
Copied from Output file (JSON), result · an excerpt
{ "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: 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. |
- 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 }
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.
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.
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 a hosted API → | 12 scenarios · 13 tools |
| Capability | Text Fidelity → | |
| Scenario | An ordinary digital text document → | |
| Tool | Reducto → |
Global scenario definition → · Global capability definition → · Reducto 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.