Does Landing AI read a page laid out in multiple columns in the right order?
Landing AI returned the two-column bulletin's text down each column in turn, without mixing lines from the two columns. On pages 1 and 2, where a sentence runs from the left column into the right, its two halves came back joined with nothing in between, and each page's sections followed in left-column order, then right-column order.
1 of 1 test case passed
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.
Two-column page — natural reading orderPassEvidence
We sent the complete three-page PDF to Landing AI's parse API in one request, with no model or options set.
Copied from Output file (Markdown), lines 62–65
cannot manage a stile. The coach leaves the Assembly Rooms at half past nine and is back by six. The cost,
Copied from Output file (Markdown), lines 190–193
deciding whether to dredge the bar, and the papers of the argument are worth reading. The board's engineer
Copied from Output file (JSON), structure · an excerpt
{ "type": "document", "children": [ { "type": "page", "grounding": { "page": 1, "range": { "start": 0, "end": 4176 }, "box": { "xmin": 0.0, "ymin": 0.0, "xmax": 1.0, "ymax": 1.0 } }, "status": "ok", "children": [ { "type": "text", "id": "text-0", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 2 items in the file]" }, { "type": "marginalia", "id": "marginalia-0", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "text", "id": "text-1", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "text", "id": "text-2", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 9 items in the file]" }, { "type": "text", "id": "text-3", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 6 items in the file]" }, { "type": "text", "id": "text-4", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 13 items in the file]" }, { "type": "text", "id": "text-5", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 7 items in the file]" }, { "type": "text", "id": "text-6", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 7 items in the file]" }, { "type": "text", "id": "text-7", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 4 items in the file]" }, { "type": "text", "id": "text-8", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 10 items in the file]" }, { "type": "text", "id": "text-9", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 9 items in the file]" }, { "type": "text", "id": "text-10", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 8 items in the file]" }, { "type": "text", "id": "text-11", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 9 items in the file]" }, { "type": "marginalia", "id": "marginalia-1", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "marginalia", "id": "marginalia-2", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" } ] }, { "type": "page", "grounding": { "page": 2, "range": { "start": 4197, "end": 8750 }, "box": { "xmin": 0.0, "ymin": 0.0, "xmax": 1.0, "ymax": 1.0 } }, "status": "ok", "children": [ { "type": "text", "id": "text-12", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "text", "id": "text-13", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 7 items in the file]" }, { "type": "text", "id": "text-14", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 11 items in the file]" }, { "type": "text", "id": "text-15", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 6 items in the file]" }, { "type": "text", "id": "text-16", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 5 items in the file]" }, { "type": "text", "id": "text-17", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 9 items in the file]" }, { "type": "text", "id": "text-18", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 5 items in the file]" }, { "type": "text", "id": "text-19", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 3 items in the file]" }, { "type": "text", "id": "text-20", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 7 items in the file]" }, { "type": "text", "id": "text-21", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 6 items in the file]" }, { "type": "text", "id": "text-22", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 10 items in the file]" }, { "type": "text", "id": "text-23", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 10 items in the file]" }, { "type": "text", "id": "text-24", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 4 items in the file]" }, { "type": "text", "id": "text-25", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 8 items in the file]" }, { "type": "text", "id": "text-26", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "marginalia", "id": "marginalia-3", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "marginalia", "id": "marginalia-4", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" } ] }, { "type": "page", "grounding": { "page": 3, "range": { "start": 8771, "end": 12374 }, "box": { "xmin": 0.0, "ymin": 0.0, "xmax": 1.0, "ymax": 1.0 } }, "status": "ok", "children": [ { "type": "text", "id": "text-27", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "text", "id": "text-28", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 3 items in the file]" }, { "type": "text", "id": "text-29", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 10 items in the file]" }, { "type": "text", "id": "text-30", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 8 items in the file]" }, { "type": "text", "id": "text-31", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 10 items in the file]" }, { "type": "text", "id": "text-32", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 6 items in the file]" }, { "type": "text", "id": "text-33", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 8 items in the file]" }, { "type": "text", "id": "text-34", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "text", "id": "text-35", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 4 items in the file]" }, { "type": "text", "id": "text-36", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 9 items in the file]" }, { "type": "text", "id": "text-37", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 5 items in the file]" }, { "type": "text", "id": "text-38", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 6 items in the file]" }, { "type": "text", "id": "text-39", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 4 items in the file]" }, { "type": "marginalia", "id": "marginalia-5", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" }, { "type": "marginalia", "id": "marginalia-6", "grounding": "{… 3 fields in the file}", "atomic_grounding": "[… 1 items in the file]" } ] } ] }
Excerpt ends here. Open the source for the complete output.
Returned Markdown: each page's left column followed by its right column
Open the Markdown file ↗Returned JSON: the full parse response with the Markdown and the page structure
Open the whole JSON file ↗| ✓ | Expected: Text comes back in natural reading order, down each column in turn, without mixing lines from the two columns.Found: Each page came back left column, then right column. Sentences split across columns on pages 1 and 2 joined up, and the header and footer stayed out of the text. |
- metadata
- { "job_id": "parse-01m22mzj8e9t0f3bbd2w4rby0n", "model_version": "dpt-3-pro-20260710", "page_count": 3, "output_markdown_chars": 12421, "range_units": "unicode_codepoints", "openapi_spec": "https://api.ade.landing.ai/openapi.json", "failed_pages": [], "duration_ms": 11136, "billing": { "service_tier": "priority", "total_credits": 9.3 } }
The text had to come down each column in turn. The sentences running from the left column into the right on pages 1 and 2 are where a wrong order would show, and both came back joined. Page 3's break falls between sentences, so it does not decide the result.
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 | Reading Order & Layout → | |
| Scenario | A page laid out in multiple columns → | |
| Tool | Landing AI → |
Global scenario definition → · Global capability definition → · Landing 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.