Upstage AI in Converting a complex PDF into clean Markdown with a hosted API
Scenario-level performance from current published Results.
6 of 12 scenarios published
Where Upstage AI failed
2 of 5 graded scenarios. Open a Result to see the conversation and the evidence.
A document with a data chart
Upstage AI failed this PDF-chart scenario: the page-3 chart was not preserved as an image with its title. The Markdown shows a placeholder image, 'Chart Type: bar', and a wrong value table; the surrounding prose and page-2 Figure 1 caption remain.
View Result →An ordinary digital text document
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.
View Result →How Upstage AI performed
Open a capability to explore its scenarios. Each row reports the test set in its published Result.
Figures & Charts1 fail1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A document with a data chart | 0 Pass1 Fail0 Not gradable 1 of 1 test case failedWhat happenedUpstage AI failed this PDF-chart scenario: the page-3 chart was not preserved as an image with its title. The Markdown shows a placeholder image, 'Chart Type: bar', and a wrong value table; the surrounding prose and page-2 Figure 1 caption remain. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| A document with figures and captions | No published result | ||
Heading & Section Structure1 pass1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| Footnotes at the bottom of the page | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedUpstage AI kept footnotes out of the body flow and attached them to their references in this test. The source PDF’s thirteen notes all appear in the Markdown, set as separate blocks after the relevant page body. Each note keeps its leading number, and the matching reference digit remains in the body text. One reference digit has a space before it. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| A document with styled headings and subheadings | No published result | ||
Scanned Document OCR2 pass
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A cleanly scanned document | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedUpstage AI recovered the text from the scanned page. The page had no text layer, and the Markdown returned every printed block correctly; the closing words were styled as a heading and the results came back as a pipe table. | 1/1 assessed1/1 gradablePublished test set | View Result → |
| A document mixing digital and scanned pages | 1 Pass0 Fail0 Not gradable 1 of 1 test case passedWhat happenedUpstage AI processed the scanned page inside the mixed PDF instead of skipping it. The scanned worksheet appears in place between the two digital pages, and the service reports all three pages processed with OCR on; the scanned page also returns the most elements, with only small spacing and punctuation changes. | 1/1 assessed1/1 gradablePublished test set | View Result → |
Table Extraction1 different test set1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A table that continues across a page break | Different test setPublished Result available, but not included in this comparison. | View Result → | |
| A simple, clearly formatted table | No published result | ||
Text Fidelity1 fail
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| An ordinary digital text document | 0 Pass1 Fail0 Not gradable 1 of 1 test case failedWhat happenedUpstage 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. | 1/1 assessed1/1 gradablePublished test set | View Result → |
Code Extraction1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A document containing a code block | No published result | ||
Equations & Mathematical Notation1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A document containing mathematical equations | No published result | ||
Reading Order & Layout1 no Result yet
Capability in this benchmark →
| Scenario | Published outcomes | Test coverage | Result |
|---|---|---|---|
| A page laid out in multiple columns | No published result | ||
Reading these Results
Published evidence and test coverage answer different questions.
Which scenarios have a Result?
A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.
What does each Result cover?
Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.
Out of 12 scenarios
The summary counts each of the 12 scenarios once. A scenario fails when any of its published test cases failed. “No published Result yet” means nothing is public for that scenario; it does not say whether Upstage AI was tested on it.