Reconstructs the supplied bank-statement schema into a nested JSON object with separate statement.metadata, account_holder, account, branch, balances, transactions, summary, rewards, and disclaimers sections instead of flattening the document into OCR text.
What was measured
Schema Adherence
Does the output follow the supplied JSON schema hierarchy exactly, with correct nesting, field names, and data types?
decisive for this rankingtransformation
If the tool does not follow the supplied JSON schema exactly, the extracted data cannot be reliably used for structured querying or downstream automation. (3 of 3 judges)
What was given, what came back
Test input: Bank Statement PDF · pdf · group: business-document-extraction
Input — what we sent
Research media bank statement 2 jul.png
Bank Statement PDF
A four-page bank statement PDF with dense transaction tables, balance-forward bridges, account metadata, rewards data, and disclaimer text. It was used to stress schema-driven extraction, multi-page continuity, row completeness, and financial numerical accuracy.
Why this input is hard
- · Table extraction across 50+ transaction rows
- · Multi-page continuity with balance-forward bridges
- · Parsing structured account metadata alongside unstructured transaction descriptions
- · Numerical accuracy for deposits, withdrawals, running balances, and summaries
- · Extraction of nested rewards and disclaimer sections
Output — unretouched
Loading file...
Also checked on this input — same tool, 6 other criteria
Extraction Accuracy✓ WorkedDocsumo extracts the bank statement into structured customer, branch, and summary fields, including the account holder name, address, totals, and closing balance, and also supports QA over the document.Extraction Accuracy✓ WorkedExtracts bank-statement account and balance fields into correctly typed values, including account holder 'MR SEENIVASAN', account number '42710540422', opening_balance 114453.65, and closing_balance 116149.46.Extraction Accuracy✓ WorkedCaptures both long bank-statement disclaimer strings as dedicated fields, preserving the insurance_coverage and reporting_period text instead of dropping or flattening it.Semantic Field Enrichment✓ WorkedDerives transaction_type and transaction_id from the transaction narration, labeling the sample record as UPI with transaction_id 917615251879 instead of leaving only raw description text.Structural Clean Output✓ WorkedProduces directly copyable JSON from the workflow, so the bank-statement extraction is immediately usable without a transformation layer after configuration.Table & Record Completeness◐ MixedOvercounts the bank-statement transaction table in the summary, reporting total_transactions 43 when the researcher says 40 should be counted after excluding balance-forward, tax, and charge entries.
Provenance
- Observation
- 0a4f8a1a-6dec-4424-b76b-d0568f8dcd32
- 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: "retab",
scenario: "business-document-extraction"
})MCP · mcp.aidemos.com/api/mcp
Free with attribution.
Same input, same check — 7 other tools
measured on Schema Adherence
Datalab✓ WorkedCan emit the bank-statement extraction as nested schema-shaped JSON, with separate metadata, account_holder/account, branch, transactions, summary, rewards, and disclaimers objects instead of flat OCR text.Extend AI✓ WorkedThe tool reconstructs the bank-statement hierarchy into nested JSON with branch, account, rewards, metadata, balances, summary, and transaction-related objects present in the requested layout.Landing AI✓ WorkedReconstructs the supplied bank-statement hierarchy instead of flat OCR, with nested statement.metadata, account_holder.address, account, branch, statement_period, balances, transactions, summary, rewards, and disclaimers objects present in the extracted JSON flow.LlamaParse✓ WorkedThe bank-statement output follows the requested nested schema closely, reconstructing metadata, account_holder, account, branch, statement_period, balances, transactions, summary, rewards, and disclaimers as structured objects rather than flat OCR text.Nanonets✓ WorkedPreserves the supplied bank-statement hierarchy in structured JSON, with nested statement.metadata, account_holder, account, balances, transactions, summary, rewards, and disclaimers objects instead of flattening the document into OCR text.Reducto✓ WorkedPreserves a nested, schema-shaped JSON structure for the bank statement instead of flattening the document into raw OCR, including top-level objects like metadata, account_holder, account, branch, statement_period, transactions, and summary.Unstract✓ WorkedFollows the requested nested bank-statement schema instead of flattening the document, populating structured objects such as metadata, account_holder, account, branch, balances, transactions, and summary.
This evidence is published in
Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com