Comparison · no marketing math

Tablewise vs MarkItDown

Both convert documents to Markdown. They disagree on one thing: a spreadsheet is not a paragraph. Here is where each one wins, with a benchmark you can re-run.

Short answer

Use MarkItDown for plain documents — PDFs without tables, Word text, HTML, EPUB, emails. It is free, mature and has an official MCP server. Use Tablewise when the document carries numbers in a table that a model has to read correctly: monthly packs, budgets, P&L, invoices, ledgers. Or when you need to prove where a figure came from.

Tablewise uses MarkItDown for the formats where it is good. The difference is what happens with spreadsheets and with provenance.

Where they differ

MarkItDownTablewise
Merged cells / multi-level headersFlattened into UnnamedRebuilt as a real table
Formula without a cached valueEmpty cell(formula not calculated)
Percentage formatting0.876987.69%
Hidden sheetsSilently droppedKept and labelled
Provenance headerNosource, engine, converted
Desktop app for non-technical usersNoYes
Hosted API with monthly plansNoYes
Deterministic, no AI, no networkYesYes (CLI and desktop)
PDF table reconstruction (Docling)BasicYes, via Docling

Benchmark, same file, same machine

Five synthetic workbooks generated by bench/run_benchmark.py. Numbers are defects (lower is better) or wins (higher is better):

CaseUnnamed colsNaN cellsFormatted %Formulas marked
financial_pack0 / 110 / 413 / 03 / 0
invoices_dates0 / 00 / 04 / 00 / 0
formula_model0 / 00 / 60 / 06 / 0
hidden_sheet0 / 00 / 00 / 00 / 0
ledger_negatives0 / 00 / 00 / 00 / 0

Format: Tablewise / MarkItDown. Full page with the raw outputs: benchmark.

When MarkItDown is the better choice

When Tablewise pays for itself

Try it on your own worst spreadsheet

Free key, 50 units a month, no card. Or run the CLI locally and send nothing anywhere.

Get a free key Read the docs