Evidence · first-party tested/Best AI Tools for Extracting Structured Data from PDFs and Business Documents
It leaves summary.total_transactions null even though the statement has 51 transactions, so the summary count is not extracted as a usable value.
What was measured
Extraction Accuracy
Are field values correct, complete, and free of OCR or parsing errors? Includes numerical precision on financial fields.
decisive for this rankingtransformation
The whole point is to pull the right values from documents; wrong or incomplete field values mean the tool failed at the job. (3 of 3 judges)
What was given, what came back
Test input: Bank Statement PDF · pdf · group: financial-document-extraction
Input — what we sent
A 4-page bank statement PDF with 51 transactions, balances, rewards, and disclaimer text, used to test schema-driven extraction of dense financial tables and multi-page continuity.
Why this input is hard
- · Table extraction across 50+ transaction rows
- · Multi-page continuity with BALANCE FORWARD bridges
- · Structured metadata vs. free-text transaction descriptions
- · Numerical accuracy for balances, deposits, withdrawals, and summaries
- · Nested schema population for account, branch, balances, rewards, and disclaimers
Output — unretouched
Also checked on this input — same tool, 4 other criteria
Schema Adherence✓ WorkedIt preserves the requested nested schema directly in the output, populating structured objects such as statement, account, balances, transactions, summary, rewards, and disclaimers instead of flattening the document into OCR text.Semantic Field Enrichment✗ FailedIt does not populate the derived transaction_type field, leaving it null across the statement instead of classifying deposits and withdrawals.Table & Record Completeness✗ FailedIt merges adjacent bank-statement rows into a single record description, so one extracted transaction can absorb neighboring content rather than staying row-bounded.Table & Record Completeness✗ FailedIt undercounts the transaction table, extracting 47 transactions when the statement actually contains 51, so 4 records are missing.
Provenance
- Observation
- 4b039231-2d8c-4c73-8ccb-1d789b555f37
- Evidence run
- ec4d736d-95f9-4c88-884c-e280435f7b7b
- 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: "financial-document-extraction"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 7 other tools
measured on Extraction Accuracy
Datalab✓ WorkedExtracts the visible document-level values correctly, including State Bank of India, 16 Jul 2019, INR, account number 42710540422, account type SMART BANKING SAVINGS ACCOUNT, branch Rajaji Salai, MICR 600036005, IFSC SCBL0036078, and phone 25349005.Extend AI⚠ StruggledIts bank summary aggregation is off: the report says `summary.total_transactions` is 49, while the expected count is 40 after excluding Balance Forward, tax, and charge entries.Landing AI✓ WorkedExtracts the statement’s top-level values with the correct content and precision, including bank_name "Standard Chartered", statement_date "16 Jul 2019", currency "INR", account number "42710540422", opening balance 114453.65, and closing balance 116149.46.LlamaParse⚠ StruggledLeaves some transaction value_date fields blank even where the statement shows dates in that column, so transaction metadata is incomplete.Reducto✓ WorkedThe tool correctly extracts the bank statement currency as INR and includes citation metadata for that field.Retab✓ WorkedPreserves long disclaimer prose in dedicated fields, capturing two separate strings for insurance_coverage and reporting_period rather than collapsing them into one blob.Unstract✗ FailedDerives an incorrect summary transaction count, reporting 43 when the statement actually contains 51 rows.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com