Evidence · first-party tested/Best AI Tools for Extracting Structured Data from Business Documents

Keeps all 8 advertising line items as separate records with no row merging or duplication.

✓ Worked🧾 artifact-verifiedinput + output shownTest date not recordedNanonets →
What was measured
Table & Record Completeness

Are all tabular rows and line items extracted without merging, duplication, omission, or phantom records?

decisive for this rankingtransformation

Missing, duplicated, or merged rows and line items directly corrupt the structured dataset and break query results. (3 of 3 judges)

What was given, what came back

Test input: Invoice PDF · pdf · group: business-document-extraction
Input — what we sent
Invoice PDF.pdf
Invoice PDF

A two-page broadcast advertising invoice PDF with nested header metadata, billing and remit addresses, and eight line items spanning a page break. It was used to stress hierarchical line-item extraction, amount precision, time/day parsing, code extraction, and summary validation.

Why this input is hard
  • · Nested line-item hierarchy extraction
  • · Multi-page continuity across a page break
  • · Precision on large dollar amounts and totals
  • · Parsing complex time slots and day patterns
  • · Extraction of Ad IDs and reconciliation codes
  • · Mapping structured metadata sections correctly
  • · Financial summary validation
  • · Handling political advertising compliance text
Output — unretouched
Output 1
Output 1
Output 2
research-media-docstrange-nanonets-invoice-output-de26bbf8b091.csv
Loading file...
Output 3
Output 3
Also checked on this input — same tool, 4 other criteria
Extraction Accuracy✓ WorkedExtracts invoice and finance values accurately, including invoice number 4064621-1 and summary totals of 8 aired spots, 29750 gross, 4462.5 commission, and 25287.5 net amount due.Schema Adherence✓ WorkedPreserves the requested invoice hierarchy, populating invoice_metadata, advertiser, station, account_details, billing_address, remit_address, flight_dates, line_items, and summary as separate JSON objects rather than flattening the page.Semantic Field Enrichment✗ FailedPartially extracts line 8's schedule metadata: flight_period_start, flight_period_end, frequency, and days_pattern are null even though the source row and other records contain scheduling information.Semantic Field Enrichment⚠ StruggledConcatenates the program-description field with the rate-category label on at least one row, producing strings like "Fox 9 AM News at 4:30amPolitical Issue Rates" instead of a cleanly separated description.
Provenance
Observation
9501f1c6-ecdd-4252-bf26-6fa252a44f29
Evidence run
a061b9e7-a9c5-443d-a171-b296aaf51b8c
Study
Extract and query structured data from documents using natural language
Research task
86b9y25e5
Tested at
not recorded
Source
first-party
Evidence state
verified
Proof shown
input + output shown
Cost / latency
not captured
Repeat run
not captured
Tester
not captured

The last three rows are honest blanks, not placeholders — our capture has no field for them yet.

Query this
get_evidence({
  tool: "nanonets",
  scenario: "business-document-extraction"
})
MCP · mcp.aidemos.com/api/mcp
JSON · ai.aidemos.com/v1/observations/9501f1c6-ecdd-4252-bf26-6fa252a44f29
Free with attribution.
Same input, same check — 8 other tools
measured on Table & Record Completeness
Datalab✓ WorkedExtracts all eight invoice line items as separate records without merging, including rows that span the page break.Docsumo✓ WorkedThe line-item table keeps all 8 rows, including the row that spans the page break, without introducing a duplicate line item.Extend AI✓ WorkedIt extracts all 8 advertising line items as separate records, preserving item boundaries across the page break without merging adjacent rows.Landing AI✓ WorkedExtracts all 8 advertising line items as separate records, preserving the page-break continuation instead of merging or omitting rows.LlamaParse✗ FailedThe tool extracts invoice line items as structured rows, but it introduces an incorrect 8th line item with line_number 9, so the table record set is not fully faithful to the source invoice’s eight advertising records.Reducto✓ WorkedExtracts all eight advertising line items as separate records and preserves the page-spanning table without merging adjacent rows.Retab✓ WorkedExtracts all 8 advertising line items as separate structured records without duplication or omission.Unstract✓ WorkedExtracts the line-item table without losing the row that crosses the page break; line 8 is returned in full with no duplication or data loss.
This evidence is published in
Best AI Tools for Extracting Structured Data from Business Documents →docsumo →
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com