Can Landing AI use a supplied definition to choose the right value?
Landing AI returned the value selected by the supplied definition instead of the more prominent alternative. The invoice number CFS-7710 was the more prominent candidate, and the returned value, CFS-CN-40821, matched the consignment reference.
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.
Definition overrides the prominent numberPassEvidence
Input · Definition of the schema field consignment_reference: “The consignment reference number (the identifier tied to the physical shipment), NOT the invoice number.”
{ "consignment_reference": "CFS-CN-40821" }
Returned JSON: the consignment reference CFS-CN-40821 as the field's only value
Copied from Output file 1 (JSON), line 2
Open the JSON file ↗The tool’s response is printed above, under What the tool returned. Show this file
{ "consignment_reference": { "value": "CFS-CN-40821", "ranges": [ { "end": 225, "start": 196 }, { "end": 1802, "start": 1752 } ] } }
| ✓ | Expected: The value the field's definition selects, the consignment reference, rather than the more prominent invoice number.Found: It returned CFS-CN-40821, the consignment reference, not the invoice number CFS-7710; its metadata points the value to the consignment reference row of the document. |
The field's name fits both the invoice number and the consignment reference, and only its definition rules out the invoice number. Landing AI returned the consignment reference, the value the definition selects, so the result is a Pass.
Invoice number is more prominent. The invoice number CFS-7710 is labelled beside the billing block and repeats in the footer of every page; the consignment reference does not appear in the footers.
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 value needs a supplied definition → | |
| Tool | Landing AI → |
Global scenario definition → · Global capability definition → · Landing AI 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.