Does LlamaParse extract the same field across different layouts?
LlamaParse passed this scenario. It returned the correct identifier, subtotal, tax, and total_due values for all three differently laid out documents, and the three outputs matched the values read from the pages while keeping the same four-field schema.
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.
Same field across three layoutsPassEvidence
- properties
- { "identifier_number": { "type": "string", "description": "The receipt or work order number that uniquely identifies this document" }, "subtotal": { "type": "string", "description": "The subtotal amount before tax" }, "tax": { "type": "string", "description": "The tax amount" }, "total_due": { "type": "string", "description": "The total amount due" } }
- required
- ["identifier_number", "subtotal", "tax", "total_due"]
Show the whole file (1 KB)
{ "type": "object", "properties": { "identifier_number": { "type": "string", "description": "The receipt or work order number that uniquely identifies this document" }, "subtotal": { "type": "string", "description": "The subtotal amount before tax" }, "tax": { "type": "string", "description": "The tax amount" }, "total_due": { "type": "string", "description": "The total amount due" } }, "required": ["identifier_number", "subtotal", "tax", "total_due"] }
"extract_result": { "identifier_number": "RHS-70234", "subtotal": "$85.00", "tax": "$5.10", "total_due": "$90.10" },
Output record: document A returned all four values
Copied from Output file 1 (JSON), lines 9–14
Open the JSON file ↗"extract_result": { "identifier_number": "GLR-98213", "subtotal": "$210.00", "tax": "$17.33", "total_due": "$227.33" },
Output record: document B returned all four values
Copied from Output file 2 (JSON), lines 9–14
Open the JSON file ↗"extract_result": { "identifier_number": "SPD-2026-0714", "subtotal": "USD 150.00", "tax": "USD 7.50", "total_due": "USD 157.50" },
Output record: document C returned all four values
Copied from Output file 3 (JSON), lines 9–14
Open the JSON file ↗| ✓ | Expected: The correct value from each document.Found: All three documents returned the right identifier, subtotal, tax, and total values. |
It is a pass because the task required the same four fields across three differently laid out documents, and the returned values matched the reference values on all three while the schema stayed unchanged.
Currency format kept. Each returned amount kept the notation printed on its document, including dollar amounts on A and B and USD amounts on C.
Confidence flags shown. The app marked one field on B and two on C below 90%, while the returned values were still correct.
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 | Structured Document Extraction → | 19 scenarios · 10 tools |
| Capability | Field Extraction → | |
| Scenario | The same field across layouts → | |
| Tool | LlamaParse → |
Global scenario definition → · Global capability definition → · LlamaParse 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.