Can Extend AI filter extracted records across multiple documents?
Extend AI offered no way to filter records across the three extracted receipts. It returned separate document extractions or one merged extraction, not a filtered set.
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.
Filter across the extracted setFailEvidence
We loaded three service receipts into Extend’s Extract playground with a four-field text schema, then ran them together with Multifile on and individually with it off. We then looked for a place to enter a total due over 150 condition.
- properties
- { "identifier_number": { "type": ["string", "null"] }, "subtotal": { "type": ["string", "null"] }, "tax": { "type": ["string", "null"] }, "total_due": { "type": ["string", "null"] } }
Show the whole file (1 KB)
{ "type": "object", "properties": { "identifier_number": { "type": ["string", "null"] }, "subtotal": { "type": ["string", "null"] }, "tax": { "type": ["string", "null"] }, "total_due": { "type": ["string", "null"] } }, "required": ["identifier_number", "subtotal", "tax", "total_due"], "additionalProperties": false }
Multifile on: merged extraction {"tax": "$17.33", "subtotal": "$210.00", "total_due": "$227.33", "identifier_number": "GLR-98213"} Multifile off: $90.10 receipt {"tax": "$5.10", "subtotal": "$85.00", "total_due": "$90.10", "identifier_number": "RHS-70234"} Multifile off: $227.33 receipt {"tax": "$17.33", "subtotal": "$210.00", "total_due": "$227.33", "identifier_number": "GLR-98213"} Multifile off: USD 157.50 receipt {"tax": "USD 7.50", "subtotal": "USD 150.00", "total_due": "USD 157.50", "identifier_number": "SPD-2026-0714"}
Extraction JSON: merged output containing the $227.33 receipt's values
Copied from Output file 1 (JSON)
Open the JSON file ↗Collected JSON outputs: three independent receipt extractions
Copied from Output file 2 (JSON), "TC1_TC4_TC5A_baseline_receipt › pdf"
Open the whole JSON file ↗Copied from Output file 2 (JSON), "TC5B_altlabel_receipt › pdf"
Copied from Output file 2 (JSON), "TC5C_altlayout_receipt › pdf"
| ✗ | Expected: Return exactly the receipts whose total due is over 150, with one extracted record per source document.Found: Neither mode offered a filter input to select the $227.33 and USD 157.50 receipts while excluding the $90.10 receipt. |
The task needed the receipts with total due over 150 returned as a set. Extend returns one record per file, or one merged record with Multifile on, and has no filter, search or query box over the set, so the condition could not be applied.
Merged extraction contents. With Multifile on, three files became one record holding the $227.33 receipt’s values. That receipt exceeds 150, but this was not filtering: no condition was applied, and the other match (USD 157.50) and the $90.10 receipt had no entry.
Accurate individual extractions. With Multifile off, the three individual receipt extractions were accurate for the identifier, subtotal, tax and total.
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 | Filter records across documents → | |
| 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.