Can Docsumo repair a record by adding one member and removing one?
Docsumo repaired the record by adding one line item and removing another. After saving, reloading, and reopening, the stored set and the export matched on the new Concrete mixer row, the missing Site fencing row, and the unchanged header and totals.
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 used Add Line to add Concrete mixer, 150L, weekly hire with Qty 1, Unit price 95, Amount 95, deleted the Site fencing row, then confirmed the record, reloaded the page, and reopened the stored record.
"Table": { "line_items": [ { "Description": { "value": "Telehandler, 4-tonne, weekly hire", "position": [163, 778, 1494, 809], "confidence": 1.0, "review_required": false }, "Qty": { "value": 1.0, "position": [163, 778, 1494, 809], "confidence": 1.0, "review_required": false }, "Unit price": { "value": 850.0, "position": [163, 778, 1494, 809], "confidence": 0.5, "review_required": false }, "Amount": { "value": 850.0, "position": [163, 778, 1494, 809], "confidence": 0.5, "review_required": false } }, { "Description": { "value": "Generator, 20kVA, weekly hire", "position": [163, 849, 1494, 880], "confidence": 1.0, "review_required": false }, "Qty": { "value": 2.0, "position": [163, 849, 1494, 880], "confidence": 1.0, "review_required": false }, "Unit price": { "value": 210.0, "position": [163, 849, 1494, 880], "confidence": 1.0, "review_required": false }, "Amount": { "value": 420.0, "position": [163, 849, 1494, 880], "confidence": 1.0, "review_required": false } }, { "Description": { "value": "Concrete mixer, 150L, weekly hire", "position": [], "confidence": 1.0, "review_required": false }, "Qty": { "value": 1.0, "position": [], "confidence": 1.0, "review_required": false }, "Unit price": { "value": 95.0, "position": [], "confidence": 1.0, "review_required": false }, "Amount": { "value": 95.0, "position": [], "confidence": 1.0, "review_required": false } } ] }
JSON export: stored line items and unchanged totals
Copied from Output file (JSON), lines 112–233
Open the JSON file ↗"data": { "Invoice Details": { "invoice_number": { "value": "TPH-3301", "position": [1354, 417, 1462, 448], "confidence": 1.0, "review_required": false }, "hire_period": { "value": "03 Mar - 10 Mar 2026", "position": [1294, 634, 1515, 665], "confidence": 1.0, "review_required": false }, "site": { "value": "Oakbridge Depot Extension", "position": [142, 634, 421, 665], "confidence": 1.0, "review_required": false }, "currency": { "value": "\u00a3", "position": [0, 0, 0, 0], "confidence": 0.44, "review_required": true } }, "Customer Information": { "billed_to": { "value": "Oakbridge Construction Ltd", "position": [142, 457, 422, 490], "confidence": 1.0, "review_required": false } }, "Totals": { "subtotal": { "value": 1462.0, "position": [1414, 2586, 1515, 2618], "confidence": 0.8, "review_required": false }, "tax": { "value": 292.4, "position": [1432, 2645, 1514, 2677], "confidence": 0.83, "review_required": false }, "total_due": { "value": 1754.4, "position": [1346, 2733, 1485, 2772], "confidence": 0.8, "review_required": false } },
Copied from Output file (JSON), lines 17–111
| ✓ | Expected: Add the new member, remove the unwanted one, and keep every other member unchanged.Found: After save, reload, and reopening, the stored set and export show Concrete mixer added, Site fencing removed, and the rest unchanged. |
It is a pass because the edit had to add one member, remove one member, and leave the rest unchanged. After save, reload, and reopening, the stored grid and export show exactly that result.
Enter committed cells. On the first try, tabbing through the new row did not store its quantity and unit price; typing Enter committed them.
Exported row metadata. The added row was exported with empty source-position arrays, matching a row created in the review screen.
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 | Docsumo → |
Global scenario definition → · Global capability definition → · Docsumo 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.