Can Nanonets extract the same field across documents with different layouts?
Nanonets returned the correct document number, subtotal, tax and total due from all three differently laid-out documents with one unchanged prompt: Riverside RHS-70234 ($90.10), GreenLeaf GLR-98213 ($227.33) and Sunrise SPD-2026-0714 (USD 157.50). It read the GreenLeaf number from a boxed work-order block rather than a receipt-number label.
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.
Same field across three layoutsPassEvidence
“Extract the following fields from this document and return the result as JSON: identifier_number (the receipt or work order number that uniquely identifies this document), subtotal____, tax____, total_due____.”
Returned JSON: Riverside's document number, subtotal, tax and total due
Copied from Output file 1 (JSON), lines 1–6
{ "identifier_number": "RHS-70234", "subtotal": "$85.00", "tax": "$5.10", "total_due": "$90.10" }
Returned JSON: Sunrise's document number, subtotal, tax and total due
Copied from Output file 2 (JSON), lines 1–6
{ "identifier_number": "SPD-2026-0714", "subtotal": "USD 150.00", "tax": "USD 7.50", "total_due": "USD 157.50" }
Returned JSON: GreenLeaf's document number, subtotal, tax and total due
Copied from Output file 3 (JSON), lines 1–6
{ "identifier_number": "GLR-98213", "subtotal": "$210.00", "tax": "$17.33", "total_due": "$227.33" }
| ✓ | Expected: The correct document number, subtotal, tax and total due from each differently laid-out document.Found: Nanonets returned each document's number, subtotal, tax and total due as written; returned and source totals were Riverside $90.10, GreenLeaf $227.33 and Sunrise USD 157.50. |
The same prompt and fields were used for all three documents, and each output matched its own source document despite different label wording, label position, layout and currency format. That is what the scenario asks, so the test case passes.
Currency format preserved. Sunrise's subtotal, tax and total due kept the USD prefix used in its receipt (USD 150.00, USD 7.50, USD 157.50) rather than changing to dollar signs.
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 | Field Extraction → | |
| Scenario | The same field across layouts → | |
| Tool | Nanonets → |
Global scenario definition → · Global capability definition → · Nanonets 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.