Can FutureSmart Document Intelligence extract repeated records?
FutureSmart Document Intelligence correctly extracted a repeated set of records from the invoice, with the three line items bound to the right records. It matched the source on description, quantity, unit price, amount, and GBP currency. A delivery note on page 2 yielded no extractable text in this pass, so that page’s contents were not visible here.
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 counts this row.
Repeated set with correct associationPassEvidence
{ "summary": "This document is an invoice from Harrowgate Industrial Supplies Ltd to Fenwick Water Treatment Ltd for the supply of dosing and chemical-feed equipment. It includes a delivery note confirming the receipt of the items on 18 February 2026.", "document_type": "invoice", "line_items": [ { "amount": 680, "quantity": 2, "unit_price": 340, "description": "Dosing pump, 240V" }, { "amount": 144, "quantity": 3, "unit_price": 48, "description": "Chemical feed tubing, 10m coil" }, { "amount": 215, "quantity": 1, "unit_price": 215, "description": "Inline flow sensor" } ], "currency": "GBP", "file_name": "invoice_HIS-4402_-_Digital_Scanned_Digital.pdf" }
Copied from Proof 1 · Output file (JSON), lines 1–26
Open the JSON file ↗Its contents are printed above, under What the tool returned.
Open the JSON file ↗These are scenario-level criteria. Each test case's Expected and Found are listed separately.
- Whether every genuine record in the repeated set is returned.
- Whether each value stays attached to the correct record.
- Whether no extra records are invented and no genuine record is omitted.
| ✓ | Found: All three line items were present with correct values and associations; none were dropped, duplicated, or misbound. |
The output matched the invoice’s three goods-supplied line items, with the correct quantities, unit prices, amounts, and record association. No item was dropped, duplicated, or bound to the wrong record.
item_code omitted. The output did not include the item_code field, even though the schema defined it. That gap affects completeness, not the record-to-field association check.
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 | Nested & Repeated Fields → | |
| Scenario | A repeated set of records → | |
| Tool | FutureSmart Document Intelligence → |
Global scenario definition → · Global capability definition →
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.