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

Can Docsumo process a document with digital and scanned pages?

Docsumo read the scanned page inside the digital PDF rather than skipping it. It returned all five requested values accurately, including the vehicle registration and delivery recipient found only on the scanned page.

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.

Values on both digital and scanned pagesPassEvidence
What we sent

We configured the extraction fields in Docsumo’s web app and ran extraction on the three-page invoice, which had an image-only delivery note in the middle.

InputDocument (PDF)
Input PDF: three-page invoice with an image-only delivery note between digital pages
Open the PDF ↗
Extraction schema
Invoice Information
{ "name": "invoice_reference", "type": "String", "description": "The invoice reference number printed on the invoice." },
{ "name": "order_reference", "type": "String", "description": "The order reference the invoice relates to." }
Delivery Detail
{ "name": "vehicle_registration", "type": "String", "description": "The registration plate of the delivery vehicle." },
{ "name": "received_by", "type": "String", "description": "The name of the person who received the delivery." }
Summary
{ "name": "total_due", "type": "Number", "description": "The total amount due on the invoice." }
What the tool returned
JSON
  "Invoice Information": {
    "invoice_reference": {
      "value": "HIS-4402",
      "position": [1432, 162, 1510, 180],
      "confidence": 1,
      "review_required": false
    },
    "order_reference": {
      "value": "FWT-PO-2291",
      "position": [518, 651, 673, 669],
      "confidence": 1,
      "review_required": false
    }
  },
  "Delivery Detail": {
    "vehicle_registration": {
      "value": "LR19 KVM",
      "position": [1409, 2827, 1519, 2851],
      "confidence": 1,
      "review_required": false
    },
    "received_by": {
      "value": "J. Whitlock",
      "position": [1398, 3135, 1526, 3158],
      "confidence": 1,
      "review_required": false
    }
  },
  "Summary": {
    "total_due": {
      "value": 1246.8,
      "position": [1385, 5421, 1510, 5443],
      "confidence": 0.88,
      "review_required": false
    }
  }
}

Downloaded JSON: five extracted values grouped into three sections

Copied from Output file (JSON), lines 2–63

Open the JSON file ↗
Expected vs. Found
✓Expected: Return all requested values accurately from both digital and scanned pages, with none missing or invented.Found: The total was 1246.8, matching the document’s numeric total of 1246.8; all five requested values were accurate, with none missing or invented.
Supporting proof
Proof 1Screenshot
Results screenshot: extracted fields beside the invoice preview
Open original ↗
Why this result

Page 2 was verified to contain zero extractable characters. Returning its two unique values accurately shows that Docsumo read the scanned image; the digital-page values were also accurate.

Also observed in this test case

Confidence and review flags. The total due had confidence 0.88, while the remaining fields had confidence 1. None of the fields was marked as needing review.

Tested by Rugved Nichite · evidence dated 5 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
Docsumo
Build or version
Not exposed by the hosted product
Surface
Web app
Set up before the run
The invoice had digital pages around an image-only delivery note. Extraction had to request the invoice reference, order reference, vehicle registration, delivery recipient and total due.
Tested
5 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
CapabilityOCR →
ScenarioA document mixing digital and scanned pages →
ToolDocsumo →

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
16 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/docsumo/a-document-mixing-digital-and-scanned-pages · 1 pass · 0 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 · 176 KB
Output file (JSON) ↗text/plain; charset=utf-8 · 1 KB
Proof 1 · Screenshot ↗image/png · 129 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)89fb14d7c0897bbfef47ffa3aa3930ee7eccf62c8a9430710d1906598c9bdfec
Output file (JSON)0c304236a63360af0feb83c52626e8b77542031c2919b1de17e7cf36b2b7a8a2
Proof 1 · Screenshotbf2e45b99c0c48068b77ffb7b976b1f3a94bafa41f128f369cd1184296c9776c