Can Reducto extract values from a document that mixes digital and scanned pages?
Reducto extracted all five requested values in one call from an invoice mixing digital and scanned pages. The two values exclusive to the scanned page were returned accurately, and the digital-page values were preserved.
1 of 1 test case passed
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.
Values on both digital and scanned pagesPassEvidence
In Reducto Studio, we used the three-page invoice PDF as the extraction input.
Copied from Output file (JSON), result
| Field | Value | Cited page |
|---|---|---|
| invoice_reference | HIS-4402 | 1 |
| order_reference | FWT-PO-2291 | 1 |
| vehicle_registration | LR19 KVM | 2 |
| received_by | J. Whitlock | 2 |
| total_due | £1,246.80 | 3 |
Extraction response: five returned values with citations to their source pages
Open the whole JSON file ↗| ✓ | Expected: Return every requested value from the digital and scanned pages without omissions, invention or altered values.Found: All five values were returned without omissions, invention or degradation. The returned total and invoice total were both £1,246.80, including the pound sign. |
- job_id
- 363d23b8-3208-4e90-8808-e1a461606056
- duration
- 2.257169
Values had to be read from both page types in one extraction. The scanned page had no text layer, yet its two exclusive values were returned with citations to page 2. The delivery recipient came from the recipient line, not the nearby driver line.
No separate OCR charge. The extraction’s usage report counted 0 OCR pages and billed no separate OCR step for the scanned delivery note on page 2.
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 | OCR → | |
| Scenario | A document mixing digital and scanned pages → | |
| Tool | Reducto → |
Global scenario definition → · Global capability definition → · Reducto 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.