AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 13 October 2026

Does Upstage AI preserve figures in place with their captions?

Upstage AI retained the figure’s caption but not the image itself. A placeholder occupied the right position, but it did not link to an image.

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.

Figure with caption — preserved in placeFailEvidence
What we sent

We sent the complete 4-page PDF once to Upstage’s Document Parse API.

InputDocument (PDF)
Input PDF: the transect figure and its caption on page 2
Open the PDF ↗
What the tool returned

Returned Markdown: a placeholder and caption where the figure belongs

Copied from Output file (Markdown), lines 60–66

Markdown
rather than taken from photography, and because it is the line against which the advisers have asked that
marsh extent be reported.

![image](/image/placeholder)
T1 N Kellow Sands T2 Thrimby Point T3 T4

Figure 1. Survey transects at Kellow Sands and Thrimby Point. Sampling stations are shown as filled circles and the 1998 saltmarsh
Open the Markdown file ↗

API response: the figure’s image reference has no source

Copied from Captured file (JSON), elements 18

JSON
{
  "id": 17,
  "page": 2,
  "category": "figure",
  "content": {
    "html": "<figure id='17'><img style='font-size:14px' alt=\"T1 N Kellow Sands T2 Thrimby Point T3 T4\" data-coord=\"top-left:(222,599); bottom-right:(1017,988)\" /></figure>",
    "markdown": "![image](/image/placeholder)\nT1 N Kellow Sands T2 Thrimby Point T3 T4",
    "text": ""
  },
  "coordinates": [
    {
      "x": 0.179,
      "y": 0.3417
    },
    {
      "x": 0.82,
      "y": 0.3417
    },
    {
      "x": 0.82,
      "y": 0.5637
    },
    {
      "x": 0.179,
      "y": 0.5637
    }
  ]
}
Open the whole JSON file ↗
Expected vs. Found
✗Expected: Preserve the image, embedded or through a working reference, in its original position with its caption.Found: The placeholder and caption were correctly positioned, but the reference led nowhere and no image data was returned.
Supporting proof
Proof 1Screenshot
Side-by-side comparison: the source figure and caption beside the placeholder output
Open original ↗
Proof 2Screenshot
Run details: successful conversion reporting zero assets
Open original ↗
Cited values2 values from this file
model
document-parse-260630
ocr
false
Why this result

The default pipeline produced no surviving image. A correctly placed placeholder and caption did not meet the requirement to preserve the figure itself.

Also observed in this test case

Figure labels as text. The survey-transect figure’s printed labels were returned as one line of text after the placeholder.

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 complete survey PDF, including the transect figure and its normal-text caption, had to be converted to Markdown in one pass without tool-specific tuning.
Endpoint
synchronous
Base64 encoding
unset
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
18 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-figures-and-captions · 0 pass · 1 fail · coverage 1/1 · graded 2026-10-13

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 · 301 KB
Output file (Markdown) ↗text/markdown · 6 KB
Captured file (JSON) ↗application/json · 41 KB
Proof 1 · Screenshot ↗image/png · 183 KB
Proof 2 · Screenshot ↗image/png · 50 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)75b2bcc613580942d7d3222254c0f0d084525c2c6521f55cffa629c49f64c608
Output file (Markdown)4a3c83010d4d7e6f77461a0ad15316548d8590df4f5c8a2b92ed4e7a03ce964f
Captured file (JSON)f6bfeb1ca97eab419fe5c94d0c7cbb1e23691ed145fdb95e90eba20647b318f1
Proof 1 · Screenshot66d486b9fcfda1086779ed2f685fb7fb91da88a506c306350fbef9a1c9813983
Proof 2 · Screenshotfc3de70b5720aad1e005a87cae6796782e1e1d2d7ea8f4530e1e05454a083add