AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 12 October 2026

Does LlamaParse leave out an item in a set that is not a valid record?

LlamaParse left out the invoice’s Total row carrying 1,982.00 rather than treating it as an item. It returned five items, preserving all five genuine rows.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

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.

Total row is not a memberPassEvidence
What we sent

We uploaded the invoice to the LlamaCloud Extract screen and ran one extraction.

InputDocument (PDF)
Input PDF: five invoice items followed by a look-alike Total row
Open the PDF ↗
Extraction schema
line_items array of {description, quantity, unit_price, amount}
What the tool returned
JSON
"status": "COMPLETED",
"error_message": null,
"extract_result": {
  "line_items": [
    {
      "description": "Retail Shelving Unit - Steel, 5-Tier",
      "quantity": "6",
      "unit_price": "84.00",
      "amount": "504.00"
    },
    {
      "description": "Checkout Counter - Laminate Top",
      "quantity": "2",
      "unit_price": "310.00",
      "amount": "620.00"
    },
    {
      "description": "Security Tag Deactivator - Handheld",
      "quantity": "4",
      "unit_price": "45.50",
      "amount": "182.00"
    },
    {
      "description": "Price Label Printer - Thermal",
      "quantity": "3",
      "unit_price": "162.00",
      "amount": "486.00"
    },
    {
      "description": "Shopping Basket - 20L, Set of 10",
      "quantity": "5",
      "unit_price": "38.00",
      "amount": "190.00"
    }
  ]

Extraction result: five genuine invoice items with the Total row excluded

Copied from Output file (JSON), lines 7–41

Open the JSON file ↗
Expected vs. Found
✓Expected: The five genuine invoice items, with none added or omitted and the Total row excluded.Found: It returned five items for five genuine invoice rows, with none omitted; the Total row carrying 1,982.00 was excluded.
Supporting proof
Proof 1Screenshot
Web app screenshot: five extracted invoice rows beside the source document
Open original ↗
Why this result

Membership mattered as well as count: no genuine invoice item was dropped and the total was excluded. No instruction told it to skip totals. This result covers agentic extraction in the web app.

Also observed in this test case

Citations for each value. For each of the five returned invoice items, citations locate the description, quantity, unit price and amount within marked areas on page 1.

Tested by Rugved Nichite · evidence dated 12 October 2026

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.

Software that produced the output
LlamaParse
Build or version
LlamaCloud web app (build v9bc3d1a1); Extract, Agentic tier
Plan or tier
Free plan (20,000 credits)
Surface
Web app
Set up before the run
The invoice had to include a clearly labelled Total row shaped like its genuine item rows. The task was to extract genuine items with descriptions, quantities, unit prices and amounts.
Schema wording
neutral
Tested
12 October 2026 · Rugved Nichite

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

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.

from the publication record
29 October 2026First publishedStructured Document Extraction v1
30 October 2026Taken down
The page left the site; nothing was deleted.
20 November 2026Republished

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/structured-document-extraction/results/llamaparse/the-set-contains-a-non-record · 1 pass · 0 fail · coverage 1/1 · graded 2026-10-12

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.

Input · Document (PDF) ↗application/pdf · 55 KB
Output file (JSON) ↗text/plain; charset=utf-8 · 16 KB
Proof 1 · Screenshot ↗image/png · 147 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)791590c9d422110ebebf3c1e434eebac20aff3c6728024693becc870818c26d8
Output file (JSON)e8bb5d8666e4a09f139c7b454c599fc2cc9b24d737e9e86a786cd4a2cdca5500
Proof 1 · Screenshot702337427656888f987c1a78e4031f5bba38c6022ba30e7da8f6675570b90e99