Does Landing AI total across all uploaded documents?
Landing AI fails to total across uploaded documents. Chat answered with one file’s own amount or refused, and Extract returned each invoice’s own total in the cross-document field instead of one combined sum.
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 counts this row.
Total across every documentFailEvidence
Input 1: “What is the total due added up across all documents in this project?”
Input 2: “Across the invoices in this project (Blackwood, Thistlewood and HIS-4402), which ones have a total due over £2,500?”
Input 3: “What is the total of the total due amounts across all three invoices in this project (Blackwood, Thistlewood and HIS-4402)?”
Response 1 answers Input 1.
Response 2 answers Input 2.
Response 3, the final response, answers Input 3.
I cannot find the answer in the provided document.
Transcribed from Proof 4 · Screenshot
Every message the tool sent, in order (6)
- Response to input 1
The total amount is $90.10.
- Response to input 2
I cannot find the answer in the provided document.
- Final response
I cannot find the answer in the provided document.
- Response 4
{ "invoice_reference": "MRG-INV-20481", "total_due": 6591.24, "total_due_all_documents": "£6,591.24" }
- Response 5
{ "invoice_reference": "TPH-3301", "total_due": 1754.4, "total_due_all_documents": "£1,754.40" }
- Response 6
{ "invoice_reference": "HIS-4402", "total_due": 1246.8, "total_due_all_documents": "£1,246.80" }
| ✗ | Expected: The correct total across every extracted document, with refusal handled separately.Found: Chat gave one file’s amount or refused, and Extract returned each invoice’s total instead of one combined amount. |
Chat tab, file Baseline_receipt (project of 3 receipts; same chat as the previous question) Question: What is the total due added up across all documents in this project? Answer: The total amount is $90.10. Visual reference for the answer: 8. table (the baseline receipt table, total $90.10) Footer on screen: "Chat works with this file only and isn't available as an API."
The product had to produce one combined total across the set. Chat gave one file’s amount or said it could not find the answer, and Extract returned each file’s own total in the aggregate field, so the required cross-document total never appeared.
Totals matched individually. The three invoice totals matched the source invoices individually, so the problem was combining them.
Chat scope notice. Chat states that it works with the open file only.
Aggregate field failed. The cross-document field still returned one invoice total for each file.
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 row says which 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 row 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 | Aggregate across documents → | |
| Tool | Landing AI → |
Global scenario definition → · Global capability definition → · Landing 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.