Can Nanonets filter records across documents?
Nanonets returned the matching documents for the tested cross-document filter. It produced the two receipts above $150 and left out the one below that threshold. The screenshot also shows a Data Extraction step over three files before the final JSON answer.
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 counts this row.
Filter across the extracted setPassEvidence
“Extract total_due from each of these documents, then tell me which documents have a total_due greater than $150. Return the result as JSON: an array of the matching documents with their filename and total_due.”
[ { "filename": "TC5B_altlabel_receipt.pdf", "total_due": 227.33 }, { "filename": "TC5C_altlayout_receipt.pdf", "total_due": 157.5 } ]
Copied from Proof 1 · Output file (JSON), lines 1–10
Open the JSON file ↗Its contents are printed above, under What the tool returned.
Open the JSON file ↗| ✓ | Expected: Exactly the matching records.Found: The product returned the two matching documents with their values and left out the third. |
The three source receipts were checked against the threshold. Nanonets returned the two over $150 and omitted the one below it, so the set split correctly. The screenshot also shows a Data Extraction step over the three files before the answer.
Three-document set. Three documents were in scope, with two above the threshold and one below it.
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 | Filter records across documents → | |
| 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.