Does LlamaParse keep corrected data moving downstream?
LlamaParse failed to keep the corrected value moving downstream in this case. The delivered JSON and the results panel both still showed RHS-70234, and the same four extracted values were visible; the correction was not shown as applied on this surface, so the case only covers what the delivery paths returned.
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 counts this row.
Correction survives the delivery pathFailEvidence
{ "data": { "receipt_number": "RHS-70234", "subtotal": "$85.00", "tax": "$5.10", "total_due": "$90.10" }, … }
Downloaded JSON with original extracted receipt number and totals
Copied from Output file (JSON), lines 2–7
Open the JSON file ↗| ✗ | Expected: The delivery path should carry the corrected value downstream.Found: It did not: both the delivered JSON and the results panel still showed RHS-70234, the original value, instead of the corrected one. |
The tool’s response is printed above, under What the tool returned. Show this screenshot
Open original ↗It was required to carry the corrected value downstream, but both readout paths still returned RHS-70234 instead. The correction was not shown as applied on this surface, so this case measures what the delivery paths carried.
Only the two read delivery paths are covered here; no webhook or destination-sync payload was observed.
The correction was not shown as applied on this surface, so the case covers what the delivery paths returned.
It shows the results panel, but not the download action or any later state.
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 row says which 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 row 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.