Can LlamaParse answer about a document fact that is not in the schema?
LlamaParse offered no place to ask about a fact printed on the receipt that the extraction schema left out. Neither the Parse result screen and its menu nor the Extract results panel has a question or chat box, and Chat cannot start until an index exists.
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.
Answer outside the schema, attributedFailEvidence
We parsed the receipt once and looked for a question control on the result screen and its More actions menu, then ran Extract once with a two-field schema and looked again. We also tried to reach Chat through a folder and an index. No question was accepted.
{ "type": "object", "properties": { "receipt_number": { "type": "string", "description": "The receipt's identifying number, labelled 'RECEIPT NO'" }, "loyalty_membership_number": { "type": "string", "description": "The customer's loyalty program membership number, if the document mentions one." } }, "required": ["receipt_number", "loyalty_membership_number"] }
The tool's response has no text to quote: it is what the evidence under Proofs shows.
| ✗ | Expected: It keeps the two apart: it says the fact is not in the extracted data, or answers and says the answer came from the document.Found: No question could be put. The parse result's menu holds only Download, Run Extract, Diagnostics and Report issue, the Extract panel has no question box, and Chat needs an index first. |
The test needed a way to ask about the technician, a fact on the receipt but not in the schema. It is a Fail, not a blocked run: parse and extraction both succeeded on the Free plan, and the product has no place to put the question.
Plan refusal. Creating a folder under Files and creating an index, even from the product's own sample documents, were both refused on the Free plan with a message asking for a Starter, Pro or Enterprise plan.
Technician read correctly. The parsed Markdown of the receipt includes the technician's name from its header row, so the fact asked about was read off the page correctly.
Empty field flagged. The extraction results flagged the second field, loyalty membership number, as empty and below the 90% confidence line: the product marks a field it could not fill, but only for schema fields.
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 | Querying → | |
| Scenario | The answer was never in the schema → | |
| 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.