Can Nanonets repair a record by adding one member and removing one?
Nanonets let a user add one line item and remove another while preserving the other two rows. Both corrections persisted after a full page reload and appeared in the JSON export.
1 of 1 test case passed
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.
Add one member and remove onePassEvidence
We requested the invoice’s line items, deleted the site fencing row, and added a concrete mixer with quantity 1, unit price £95.00 and amount £95.00 in the review table. We saved without re-running extraction, then fully reloaded the page.
Only the tool's reply to input 1 is copied here; its replies to inputs 2 and 3 were not copied as text. The rest of what the tool returned is shown in the evidence under Proof.
The extraction is complete. Return this JSON: {"line_items":[{"description":"Telehandler, 4-tonne, weekly hire","quantity":1,"unit_price":"£850.00","amount":"£850.00"},{"description":"Generator, 20kVA, weekly hire","quantity":2,"unit_price":"£210.00","amount":"£420.00"},{"description":"Site fencing, per 10m panel, weekly","quantity":8,"unit_price":"£24.00","amount":"£192.00"}]}
Transcribed from Proof 3 · Screenshot
[ { "description": "Telehandler, 4-tonne, weekly hire", "quantity": 1, "unit_price": "£850.00", "amount": "£850.00" }, { "description": "Generator, 20kVA, weekly hire", "quantity": 2, "unit_price": "£210.00", "amount": "£420.00" }, { "description": "Concrete mixer, 150L, weekly hire", "quantity": "1", "unit_price": "£95.00", "amount": "£95.00" } ]
| ✓ | Expected: Keep the added item, remove the deleted item, and leave every other item’s values unchanged.Found: After reload, the concrete mixer remained, site fencing was absent, and the two retained rows kept their original quantities, unit prices and amounts. |
A repair had to change the saved set, not just the on-screen table. The full reload and export confirmed both edits with the other rows untouched. The chat reply still contained the original extraction.
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 | Review and Correction → | |
| Scenario | Repair a record → | |
| Tool | Nanonets → |
Global scenario definition → · Global capability definition → · Nanonets 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.