Does Nutrient.io preserve code blocks when converting PDFs to Markdown?
Nutrient.io did not preserve the code block in its default PDF-to-Markdown conversion. It returned the Python snippet as a table without a code fence or its original indentation.
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.
Code block — fenced, structure intactFailEvidence
<table> <tr> <th>from tarnbeck.stations import Export, reload_window</th> </tr> <tr> <th>def reload_after_reset(station, reset_at):</th> </tr> <tr> <th>export = Export.open(station)</th> </tr> <tr> <th>window = reload_window(reset_at, margin_minutes=45)</th> </tr> <tr> <th>for block in export.blocks(window):</th> </tr> <tr>
Returned Markdown: Python snippet rendered as a table without code fences
Copied from Output file (Markdown), lines 67–83
Open the Markdown file ↗{ "status_code": 200, "headers": { "date": "Wed, 09 Sep 2026 08:53:19 GMT", "content-type": "text/markdown", "content-length": "6340", "content-disposition": "attachment; filename=\"result.md\"", "server": "Cowboy", "x-pspdfkit-remaining-credits": "38", "x-pspdfkit-request-cost": "1", "x-request-id": "GNObFoUaysppv0UAAIMB" }, "content_type": "text/markdown", "body_bytes": 6340, "delivery": "raw markdown body (content-type text/markdown)", "markdown_chars": 6332, "zip_members": null, "asset_names": null }
API exchange: default conversion request and Markdown response
Copied from Captured file (JSON), response
Open the whole JSON file ↗| ✗ | Expected: Code appears as a preformatted or fenced block, with line breaks and indentation intact.Found: The Markdown contained no code fences. The Python snippet appeared as a table with one source line per row and its indentation flattened. |
The code needed to remain preformatted with its line structure and indentation intact. The complete PDF was converted successfully using the default path, but the returned snippet lost its block formatting and indentation, so the failure was in the output rather than the conversion setup.
Alternative conversion. A separate Data Extraction API conversion using understand mode fenced the Python snippet, but ran its lines together on one line.
Code text preserved. The returned code preserved the characters of each source line, even though its block structure was lost.
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 | Code Extraction → | |
| Scenario | A document containing a code block → | |
| Tool | Nutrient.io → |
Global scenario definition → · Global capability definition → · Nutrient.io 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.