Tool in benchmark · Version 1

Extend AI in Structured Document Extraction

Scenario-level performance from current published Results.

14Passed
3Failed
3No published Result yet

17 of 20 scenarios published

CapabilityScenariosResult
Field Extraction5 pass · 0 fail · 5 of 5 published
Nested & Repeated Fields3 pass · 0 fail · 3 of 4 published
OCR1 pass · 0 fail · 1 of 2 published
Querying0 pass · 3 fail · 3 of 3 published
Review and Correction3 pass · 0 fail · 3 of 3 published
Source Grounding2 pass · 0 fail · 2 of 2 published
Training0 of 1 published
PassedFailedPublished, different test setNo published Result yet

Where Extend AI failed

3 of 17 graded scenarios. Open a Result to see the conversation and the evidence.

Querying

Aggregate across documents

Extend AI returned £7,838.04 instead of the required £9,592.44 when asked to total three invoices. The shortfall equals one invoice’s £1,754.40 contribution.

View Result →
Querying

Filter records across 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.

View Result →
Querying

The answer was never 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.

View Result →

How Extend AI performed

Open a capability to explore its scenarios. Each row reports the test set in its published Result.

Field Extraction5 pass
ScenarioPublished outcomesTest coverageResult
The field is absent
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI passes this absent-field case: it returned null for the added field and no grounding to an invented value. The receipt contains no loyalty or membership data, and the response carries an empty citations array.

1/1 assessed1/1 gradablePublished test setView Result →
The same field across layouts
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI returned the correct value for the same field across documents laid out differently. The shown runs returned $90.10, $227.33, and USD 157.50, each matching its source document.

1/1 assessed1/1 gradablePublished test setView Result →
The value is directly available
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI passed the directly available value scenario. It returned the receipt number once under its label, and the JSON result matched that value as a string.

1/1 assessed1/1 gradablePublished test setView Result →
The value must be derived
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI derived a fuel cost that was not stated in the invoice. It returned £81.00, the required result of multiplying 450 miles by £0.18 per mile.

1/1 assessed1/1 gradablePublished test setView Result →
The value needs a supplied definition
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI selected the consignment reference required by the supplied definition, not the more prominent invoice number. It cited the consignment line on page 1.

1/1 assessed1/1 gradablePublished test setView Result →
Nested & Repeated Fields3 pass1 no Result yet
ScenarioPublished outcomesTest coverageResult
A repeated set of records
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI returned the three line items on the invoice page as three records, each with its own description, item code, quantity, unit price and amount, with nothing dropped, duplicated or placed on the wrong record. The subtotal, VAT and total due lines below the table were not returned as records.

1/1 assessed1/1 gradablePublished test setView Result →
The set contains a non-record
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI extracted the genuine invoice items without including the total row. It returned five items from five genuine source rows, with none missing or substituted.

1/1 assessed1/1 gradablePublished test setView Result →
The set is legitimately empty
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI returned an empty set for the legitimately empty document. The extracted set of damage or exception entries is empty, and the source references are empty too. Page 3 says no damage or exceptions were reported.

1/1 assessed1/1 gradablePublished test setView Result →
The set continues across a page breakNo published result
OCR1 pass1 no Result yet
ScenarioPublished outcomesTest coverageResult
A document mixing digital and scanned pages
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI returned the requested values from a document mixing digital and scanned pages. The decision-relevant finding is that the image-only page was processed rather than skipped: the scanned-page values and the digital-page values both came back correct in one extraction call.

1/1 assessed1/1 gradablePublished test setView Result →
A cleanly scanned documentNo published result
Querying3 fail
ScenarioPublished outcomesTest coverageResult
Aggregate across documents
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

Extend AI returned £7,838.04 instead of the required £9,592.44 when asked to total three invoices. The shortfall equals one invoice’s £1,754.40 contribution.

1/1 assessed1/1 gradablePublished test setView Result →
Filter records across documents
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

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.

1/1 assessed1/1 gradablePublished test setView Result →
The answer was never in the schema
0 Pass1 Fail0 Not gradable
1 of 1 test case failed
What happened

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.

1/1 assessed1/1 gradablePublished test setView Result →
Review and Correction3 pass
ScenarioPublished outcomesTest coverageResult
Correct a field value
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI saved a corrected receipt number to the stored record: after RHS-70234 was changed to RHS-99999 on its review screen, saved and the run reloaded, the stored record read RHS-99999. The subtotal, tax and total due stayed at 85, 5.1 and 90.1.

1/1 assessed1/1 gradablePublished test setView Result →
Corrected data goes downstream
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI delivered the corrected receipt number through its API. The subtotal, tax and total due stayed at $85.00, $5.10 and $90.10.

1/1 assessed1/1 gradablePublished test setView Result →
Repair a record
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI let a user add and remove invoice items through Human Review. After approval, the traffic cones were present, the site fencing was absent and the telehandler and generator values were unchanged.

1/1 assessed1/1 gradablePublished test setView Result →
Source Grounding2 pass
ScenarioPublished outcomesTest coverageResult
The field is absent
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI passes this absent-field case: it returned null for the added field and no grounding to an invented value. The receipt contains no loyalty or membership data, and the response carries an empty citations array.

1/1 assessed1/1 gradablePublished test setView Result →
Trace a value to its location
1 Pass0 Fail0 Not gradable
1 of 1 test case passed
What happened

Extend AI traced the returned value to the correct document location. It returned 6103 with a citation to page 2 on "Subtotal" beside £6,103.00. The PDF shows "Subtotal" once on page 2 and not on page 1.

1/1 assessed1/1 gradablePublished test setView Result →
Training1 no Result yet
ScenarioPublished outcomesTest coverageResult
A field the tool can only get right from examplesNo published result

Reading these Results

Published evidence and test coverage answer different questions.

Publication availability

Which scenarios have a Result?

A published Result is public evidence for this tool on one scenario. “No published result” does not say whether testing has taken place.

Test coverage

What does each Result cover?

Assessed includes Pass, Fail and Not gradable. Gradable includes Pass and Fail. Both use the pinned test count in that published Result.

Scenario scope

Out of 19 scenarios

The summary counts each of the 19 scenarios once. A scenario fails when any of its published test cases failed. “No published Result yet” means nothing is public for that scenario; it does not say whether Extend AI was tested on it.

Extend AI in Structured Document Extraction | AI Demos