Tool in benchmark · Version 1

Extend AI in Structured Document Extraction

Scenario-level performance from current published Results.

3 scenarios with published Results · 19 scenarios in the benchmark

How Extend AI performed

Open a capability to explore its scenarios. Each row reports the test set in its published Result; counts are not combined into an overall score.

Nested & Repeated Fields4 scenarios · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
The set is legitimately emptyRound 1 · Graded 6 Oct 2026 · Published 7 Oct 2026	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 set	View Result →
A repeated set of records	No published result
The set contains a non-record	No published result
The set continues across a page break	No published result

OCR2 scenarios · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
A document mixing digital and scanned pagesRound 1 · Graded 18 Sept 2026 · Published 6 Oct 2026	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 set	View Result →
A cleanly scanned document	No published result

Source Grounding2 scenarios · 1 with published Results

Scenario	Published outcomes	Test coverage	Result
Trace a value to its locationRound 1 · Graded 6 Oct 2026 · Published 6 Oct 2026	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 set	View Result →
The field is absent	No published result

Field Extraction5 scenarios · 0 with published Results

Scenario	Published outcomes	Test coverage	Result
The field is absent	No published result
The same field across layouts	No published result
The value is directly available	No published result
The value must be derived	No published result
The value needs a supplied definition	No published result

Querying3 scenarios · 0 with published Results

Scenario	Published outcomes	Test coverage	Result
Aggregate across documents	No published result
Filter records across documents	No published result
The answer was never in the schema	No published result

Review and Correction3 scenarios · 0 with published Results

Scenario	Published outcomes	Test coverage	Result
Correct a field value	No published result
Corrected data goes downstream	No published result
Repair a record	No published result

Training1 scenario · 0 with published Results

Scenario	Published outcomes	Test coverage	Result
A field the tool can only get right from examples	No published result

Published evidence and test coverage answer different questions.

Publication availability

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

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

Scenario scope

The 19 scenarios describe this benchmark’s scope. They are not an assumed applicability or test-coverage denominator for Extend AI.