Does Upstage AI keep ordinary digital text complete and unchanged?
Upstage AI did not keep ordinary digital text unchanged. At one page break, it joined a running header to a continuation of the body text; the other five breaks stayed clean.
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
granted in 2021. This note records what was placed, what it cost, and what the winter surveys Page 1 of 7 Braithe Estuary Partnership have shown so far.
Markdown output: the converted document and its page-break text
Copied from Output file (Markdown), lines 50–55
Open the Markdown file ↗{ "id": 16, "page": 2, "category": "header", "content": { "html": "<header id='16' style='font-size:16px'>Braithe Estuary Partnership<br>have shown so far.</header>", "markdown": "Braithe Estuary Partnership\nhave shown so far.", "text": "" }, "coordinates": [ { "x": 0.1159, "y": 0.0608 }, { "x": 0.2981, "y": 0.0608 }, { "x": 0.2981, "y": 0.0872 }, { "x": 0.1159, "y": 0.0872 } ] }
API response: converted text and classified document elements
Copied from Output file (JSON), elements 17
Open the whole JSON file ↗| ✗ | Expected: All text present and unchanged, with nothing missing, garbled or invented.Found: No words were missing or invented, but the page-two header and a body continuation formed a paragraph absent from the source. |
The text had to remain complete and unchanged. Although all seven pages were processed, the product placed a body continuation inside a running header, altering the text. The failure is in the conversion, not an incomplete request.
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 | Upstage AI → |
Global scenario definition → · Global capability definition → · Upstage AI 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.