Can Extend AI handle a document fact that is not in the schema?
Extend AI offered no way to ask about a document fact outside the extraction schema. The extraction returned the invoice reference and total due, without an answer about the printed due date.
1 of 1 test case failed
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.
Answer outside the schema, attributedFailEvidence
We loaded the invoice into Extend AI’s Extract Playground, ran an extraction for the invoice reference and total due, and looked for a way to ask about its printed due date.
{ "type": "object", "properties": { "invoice_reference": { "type": ["string", "null"], "description": "The invoice reference number" }, "total_due": { "type": ["number", "null"], "description": "The total amount due on the invoice" } }, "required": ["invoice_reference", "total_due"], "additionalProperties": false }
{ "total_due": 6591.24, "invoice_reference": "MRG-INV-20481" }
Extraction result: the invoice reference and total due
Copied from Output file (JSON)
Open the JSON file ↗| ✗ | Expected: State that the requested fact is absent from the extracted data, or answer it while making clear it comes from the document.Found: No document question-answering option was available; the due-date question could not be asked. |
The printed due date was outside the schema. Extend AI offered no way to ask about it and documented no alternative. This is a failure, not a question left untried: the requirement counts an inability to query as a failure.
No invented values. The invoice extraction result contained no invented values.
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 | Querying → | |
| Scenario | The answer was never in the schema → | |
| Tool | Extend AI → |
Global scenario definition → · Global capability definition → · Extend 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.