AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 17 November 2026

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.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

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
What we sent

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.

Input 1Document (PDF)
Input PDF: Sunrise Plumbing & Drain receipt totaling USD 157.50
Open the PDF ↗
Input 2Document (PDF)
Input PDF: GreenLeaf Appliance Repair invoice totaling $227.33
Open the PDF ↗
Input 3Document (PDF)
Input PDF: Riverside Home Services receipt totaling $90.10
Open the PDF ↗
ConfigurationCaptured file (JSON)
Schema JSON: four required receipt fields, each allowing text or no value
Cited values1 value from this file
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)
JSON
{
  "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
}
Open the JSON file ↗
What the tool returned
Text
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 vs. Found
✗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.
Supporting proof
Proof 1Screenshot
Result screenshot: merged extraction containing the $227.33 receipt's values, with no filter input
Open original ↗
Proof 2Screenshot
Result screenshot: separate extraction of the USD 157.50 receipt, with no filter input
Open original ↗
Proof 3Screenshot
Result screenshot: separate extraction of the $227.33 receipt, with no filter input
Open original ↗
Proof 4Screenshot
Result screenshot: separate extraction of the $90.10 receipt, with no filter input
Open original ↗
Proof 5Screenshot
Configuration screenshot: three receipts, the four-field schema and Multifile's merged-output explanation
Open original ↗
Why this result

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.

Also observed in this test case

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.

Tested by Rugved Nichite · evidence dated 17 November 2026

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.

Software that produced the output
Extend AI
Build or version
Not exposed by the hosted product
Model
extraction version 4.10.0
Surface
Web app
Set up before the run
Service receipts from Sunrise Plumbing & Drain, GreenLeaf Appliance Repair and Riverside Home Services had to yield comparable totals, with both matching and non-matching receipts available for a cross-document filter.
Multifile
on · off
Engine
Performance
Tested
17 November 2026 · Rugved Nichite

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

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.

The rules
  • 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.

LevelNameScope
BenchmarkStructured Document Extraction →19 scenarios · 10 tools
CapabilityQuerying →
ScenarioFilter records across documents →
ToolExtend AI →

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.

from the publication record
19 November 2026First publishedStructured Document Extraction v1

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.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/structured-document-extraction/results/extend-ai/filter-records-across-documents · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-17

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.

Input 1 · Document (PDF) ↗application/pdf · 7 KB
Input 2 · Document (PDF) ↗application/pdf · 8 KB
Input 3 · Document (PDF) ↗application/pdf · 7 KB
Output file 1 (JSON) ↗application/json · 0 KB
Output file 2 (JSON) ↗application/json · 0 KB
Proof 1 · Screenshot ↗image/png · 165 KB
Proof 2 · Screenshot ↗image/png · 135 KB
Proof 3 · Screenshot ↗image/png · 139 KB
Proof 4 · Screenshot ↗image/png · 138 KB
Proof 5 · Screenshot ↗image/png · 203 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input 1 · Document (PDF)0276d246d69482340b53797f4eaa21831977cede22c8c8f14fc48dbf84757660
Input 2 · Document (PDF)4a0b1754da9f52ce35a783d58f8e8a1b5e1353b5b992d5553122886f1cd4a638
Input 3 · Document (PDF)1f464ae863aadb1682805b8ee3fdd8b368a2ddd4e0f602e1cb194640b9253302
Configuration · Captured file (JSON)d01ccb8bd77f47753f712395ed725bfa320bcf807104e4add47669bcdc3e2616
Output file 1 (JSON)bd2cd981fa045987dbb2a1f96ffe5f359114186aa0da8e88f7b7455a51106277
Output file 2 (JSON)37c2183c851cd3709bd1e0c76c19edb5d5fa8633f151db932d8522f691693ea6
Proof 1 · Screenshot248040d076b81122bd71049c6fca4ee4c5f0b6e7e8e3b536de62cd7dc2a4ddc6
Proof 2 · Screenshot4177739c6a0670eceb6eeacad148f3f475059c47ff41d1ecf029fe863a692207
Proof 3 · Screenshota7cf81521428d991c022eb53c99b3358d5bef8d927acf584fc7e72f13dc6e889
Proof 4 · Screenshot2338c51f00edfb82b6f2ff233cdba0325ba559b68748e47be8d705b7217e0a1e
Proof 5 · Screenshot5f5d4cb254b894830217bfee9a5b43e45ca2f07cfd215af1645589aaaddecfbd