AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 16 November 2026

Does Upstage AI turn styled headings into nested Markdown heading levels?

Upstage AI returned every heading of the three-page procedure at a single Markdown level, so the source's three heading sizes collapsed into one and no nesting survived. Three headings, including Refrigerated storage, came back as plain lines with no heading marker.

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.

Styled headings — hierarchy preservedFailEvidence
What we sent

We sent the complete three-page PDF to Upstage's document conversion endpoint in one request, with every setting left at its default; nothing was typed.

InputDocument (PDF)
Input PDF: a three-page lab procedure with styled section headings and subheadings
Open the PDF ↗
What the tool returned

Copied from Output file (Markdown), lines 3–37

Markdown
# Sample Reception and Handling
Procedure KAL-SP-06 · Revision 4 · Effective 1 March 2026

# Scope

This procedure covers the receipt, identification, storage and disposal of samples submitted to the laboratory for
chemical analysis. It applies to everything received at the Braithe Road reception, including samples delivered
by courier and samples brought in by clients. It does not cover samples taken by our own field staff, which are
dealt with in KAL-SP-11.

# Reception

Samples are received at reception between 08:00 and 17:30 on weekdays and between 09:00 and 12:00 on
Saturdays. Outside those hours clients who hold a key may use the refrigerated drop box at the rear entrance.

# Chain of custody

Every delivery arrives with a completed submission form. Reception staff check that the form is signed, that the
number of containers matches the number listed on it, and that each container carries a legible client reference.
The form is signed and timed on receipt and the top copy is returned to the person making the delivery.

# Condition on arrival

Reception staff record the condition of each container on the submission form before it leaves the reception
bench. Anything recorded there that falls outside the limits below goes to the duty chemist before the sample is
booked in.

# Temperature

Chilled samples. Where the submission form specifies chilled transport, the temperature of the transport box is
measured and written on the form. A box above 8 degrees is accepted, marked, and referred to the duty chemist,
who decides whether the analysis can still be reported. A box above 15 degrees is not accepted for
microbiological work at all.

# Container integrity

Copied from Output file (Markdown), lines 42–55

Markdown
# Storage

Refrigerated storage

Samples for chemical analysis are held at 4 degrees in the reception cold room and are racked by the day of
receipt, not by client. Racks are cleared every Friday afternoon.

# Frozen storage

Samples that require frozen storage are held at minus 20 degrees in the chest freezer in room 4. Nothing goes
into the freezer without a completed freezer label, and nothing is stacked above the load line marked inside the
cabinet.

Retention and disposal

Copied from Output file (Markdown), lines 83–85

Markdown
Identification and booking in

# The laboratory number

Returned Markdown: every heading at one level, three source headings as plain text

Open the Markdown file ↗
Expected vs. Found
✗Expected: Headings come back as Markdown headings with their levels and nesting kept, not as plain or bold text.Found: The source's 26 headings use three sizes (16, 13, 12 point); every returned heading is one '#' level, and three headings, such as Refrigerated storage, are plain lines.
Supporting proof
Proof 1Screenshot
Page 1 side by side: three source heading sizes against one returned heading level
Open original ↗
Proof 2Screenshot
Run details card: default pipeline, the complete three-page PDF in one request, completed
Open original ↗
Why this result

The test required headings to become Markdown headings with their nesting kept. The source sets headings at three sizes above the body text; the returned Markdown uses one heading level for all of them, and three headings carry no marker at all, so both parts of the requirement fail.

Also observed in this test case

Body-size title made a heading. The title line "Sample Reception and Handling", set at body size in the source, came back as a top-level heading.

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
Upstage AI
Build or version
document-parse-260630 (API 2.0)
Plan or tier
free tier
Surface
API
Set up before the run
The input was a three-page laboratory procedure PDF with headings set at three styled sizes over normal body text. The complete PDF was converted to Markdown in one pass with Upstage's default settings and no options tuned.
Endpoint mode
synchronous endpoint
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
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/upstage-ai/a-document-with-styled-headings-and-subheadings · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-16

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 · 43 KB
Output file (Markdown) ↗text/markdown · 7 KB
Proof 1 · Screenshot ↗image/png · 560 KB
Proof 2 · Screenshot ↗image/png · 71 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)1d53151023b44fca82503e6e748e2a1bed0b2374f54d2dc2d10279009401f34d
Output file (Markdown)66d7b22c4ebc8d3856f42234cda09b8ca898605a6092c402f27c686d5e9689ae
Proof 1 · Screenshotc7b63dd77cb6ceec955cc000a2080c94eed17b5db24a4c9830026528c22285ad
Proof 2 · Screenshot9d62667540c6a1bda48e58ecec3c23fdf2b3740218f57c2d7e7a10084e745675