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

Can LlamaParse correct a returned field value?

LlamaParse offered no way to correct a returned field. No edit control was found in the Results view, JSON view, History menu or Details drawer, and the saved receipt number stayed RHS-70234.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
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.

Corrected value reaches the stored recordFailEvidence
What we sent

In LlamaParse, we tried to change the returned receipt number from RHS-70234 to RHS-99999.

InputDocument (PDF)
Input PDF: the service receipt used for the correction attempt
Open the PDF ↗
What the tool returned
JSON
"extract_result": {
  "receipt_number": "RHS-70234",
  "subtotal": "$85.00",
  "tax": "$5.10",
  "total_due": "$90.10"
},
"extract_metadata": {
  "field_metadata": {
    "document_metadata": {
      "receipt_number": {
        "citation": [
          {
            "page": 1,
            "matching_text": "RHS-70234",
            "bounding_boxes": [
              {
                "x": 366.623660902977,
                "y": 182.13455400466918,
                "w": 40.38487688541412,
                "h": 7.228088979721069
              }
            ],
            "page_dimensions": {
              "width": 594.96,
              "height": 841.92
            }
          }
        ],
        "confidence": 0.9399183641652863,
        "extraction_confidence": 0.9399183641652863
      },
      "subtotal": {
        "citation": [
          {
            "page": 1,
            "matching_text": "subtotal",
            "bounding_boxes": [
              {
                "x": 521.0869697856904,
                "y": 259.22286203384397,
                "w": 23.806994662284854,
                "h": 8.80667492866516
              }
            ],
            "page_dimensions": {
              "width": 594.96,
              "height": 841.92
            }
          }
        ],
        "confidence": 0.8374902131908023,
        "extraction_confidence": 0.8374902131908023
      },
      "tax": {
        "citation": [
          {
            "page": 1,
            "matching_text": "$5.10",
            "bounding_boxes": [
              {
                "x": 525.297205324173,
                "y": 277.9029379463196,
                "w": 19.596759123802187,
                "h": 8.80672511100769
              }
            ],
            "page_dimensions": {
              "width": 594.96,
              "height": 841.92
            }
          }
        ],
        "confidence": 0.8039167539738895,
        "extraction_confidence": 0.8039167539738895
      },
      "total_due": {
        "citation": [
          {
            "page": 1,
            "matching_text": "$90.10",
            "bounding_boxes": [
              {
                "x": 512.6664632463455,
                "y": 304.2129379463196,
                "w": 31.964370346069337,
                "h": 10.385311059951782
              }
            ],
            "page_dimensions": {
              "width": 594.96,
              "height": 841.92
            }
          }
        ],
        "confidence": 0.8801188752802118,
        "extraction_confidence": 0.8801188752802118
      }
    },
    "page_metadata": null,
    "row_metadata": null
  },
  "parse_job_id": "pjb-w8erd92hps9gq5240vai6v86v81d",
  "parse_tier": "agentic"

Extraction output: the original receipt number after the correction attempts

Copied from Output file (JSON), lines 9–111

Open the JSON file ↗
Expected vs. Found
✗Expected: The stored record must save the corrected field value without changing any other field.Found: The saved receipt number remained RHS-70234, not the intended RHS-99999; subtotal stayed $85.00, tax $5.10 and total due $90.10.
Supporting proof
Proof 1Screenshot
Results screenshot: the receipt number displayed as plain text without an input box
Open original ↗
Proof 2Screenshot
JSON screenshot: the read-only result with copy and download controls
Open original ↗
Proof 3Screenshot
History screenshot: the job menu without an edit action
Open original ↗
Proof 4Screenshot
Details screenshot: job information and a button to open the extraction, with no editing control
Open original ↗
Why this result

Saving a correction was required, so the absence of an edit control is a failure, not an untested action. This applies to the Free plan’s web extraction screens.

Also observed in this test case

Confidence highlighting. The subtotal, tax and total due fields were shaded amber below the 90% confidence threshold. The shading indicated confidence, not an editable input.

Tested by Rugved Nichite · evidence dated 13 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 v09046f5c); Extract, Agentic tier
Plan or tier
Free plan (20,000 credits)
Surface
Web app
Set up before the run
A service receipt and a schema for receipt number, subtotal, tax and total due were required. The task was to attempt changing the correctly extracted receipt number to RHS-99999 and read it back.
Extraction schema
4 fields · receipt_number, subtotal, tax, total_due · string type
Tested
13 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.

LevelNameScope
BenchmarkStructured Document Extraction →19 scenarios · 10 tools
CapabilityReview and Correction →
ScenarioCorrect a field value →
ToolLlamaParse →

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
13 November 2026First publishedStructured Document Extraction v1

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/correct-a-field-value · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-12

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 · 54 KB
Output file (JSON) ↗text/plain; charset=utf-8 · 3 KB
Proof 1 · Screenshot ↗image/png · 141 KB
Proof 2 · Screenshot ↗image/png · 129 KB
Proof 3 · Screenshot ↗image/png · 147 KB
Proof 4 · Screenshot ↗image/png · 153 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)a96bbe1c5b22336e7b54169baf72b85e45eabf1312cd293a1821017b52fa85f7
Output file (JSON)159f9a4952e06b0d923040fb332f8e614f8cbbae8dde0442b54fc1403e232b0c
Proof 1 · Screenshot99702117b7fcd16e294b2cbed2dca15736b41639ee5c34eff9dabc313816363d
Proof 2 · Screenshot43e2b75721a108f649c99ab966c29345fce43c944505b24efc70603eecbe762e
Proof 3 · Screenshot44436a2b848025a377fe5c2b620db28377345a25b4eaa140623576dfcbe3c57b
Proof 4 · Screenshot790a2dd38fa046937b2cc449846e33fc609a4a524614237a1be2ebd2c7f46394