Does LlamaParse keep corrected data moving downstream?
LlamaParse did not carry the corrected receipt_number RHS-99999 downstream on the Extract screen. On the Free plan, the agentic four-field setup stayed read-only, and the downloaded JSON and opened export still showed receipt_number RHS-70234 with subtotal, tax, and total_due.
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.
Correction survives the delivery pathFailEvidence
{ "data": { "receipt_number": "RHS-70234", "subtotal": "$85.00", "tax": "$5.10", "total_due": "$90.10" }, "extract_metadata": {
Downloaded JSON export with citations for the four extracted fields
Copied from Output file (JSON), lines 1–8
Open the JSON file ↗| ✗ | Expected: The delivery path carries the corrected receipt number.Found: The exported JSON and results panel still show receipt_number RHS-70234, and the panel offers no edit control; RHS-99999 does not appear. |
The delivery path had to carry the corrected receipt number, but the results panel and downloaded JSON still showed the original number and offered no edit control. That leaves the required correction absent, so the case fails.
Export completeness. The downloaded JSON carries all four extracted values and per-field citations.
Read-only flags. Three money fields sit below 90%, while receipt number is above it; the panel still offers no edit control.
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 | Review and Correction → | |
| Scenario | Corrected data goes downstream → | |
| 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.