No More Bad Data
AP Receiving by Nuntiq
“95% accurate” still leaves 537 of every 1,000 invoices needing a person.
Capture tools quote accuracy per field. Your team gets whole invoices. So we made some of the ugliest invoices we could, ran them through AP Receiving, and put every answer here for you to check.
Nuntiq calculation: with 15 required fields each right 95% of the time, all 15 are right 0.95 to the power of 15 = 46.3% of the time, so 537 of 1,000 invoices need a touch. Assumes errors are independent; real errors cluster, so reality is somewhat better, and still far from 95%.
The Nuntiq launch film
Coming soon.
The math nobody prints on the brochure
Bad data is not a rounding error.
An invoice is only usable when every field your ERP needs is right: supplier, number, dates, totals, every line. A tool that is right 95% of the time per field gets a whole invoice right less than half the time.
Someone on your team catches the rest. Or nobody does, and it surfaces at payment run, at month end, or in an audit.
38 in 100
invoices go through without a person touching them.
Ardent Partners research, The State of AP 2026 (n=194). Range in 2024 to 2026 surveys: 32.6% to 38.3%.
1 in 5
invoices gets stuck as an exception.
Ardent Partners research, The State of AP 2026: 19.9% average exception rate.
92.7%
of fields on scanned invoices: the best of eight general-purpose AI models in an independent benchmark. About 1 field in 14 still wrong. Off-the-shelf AI is not capture.
Berghaus et al., Fraunhofer IAIS and Lamarr Institute, 2025 (arXiv 2509.04469, preprint): 350 scanned invoices.
4 days
to resolve a single invoice error. Bad data does not just cost a correction; it parks the invoice.
Median of 2,861 organizations benchmarked by APQC (Open Standards Benchmarking, cycle time to resolve an invoice error).
Bad data, meet its match
Eight invoices built to break capture. Open any of them.
Scanned, faxed, photographed, stamped and scribbled on, in four languages, up to 424 lines long. On the left the page, on the right what AP Receiving captured. Point at a value to see where it came from.
Every invoice here is a fictional test document generated by Nuntiq; any resemblance to a real company or person is coincidental. Each answer shown is the first run of our production setup, unedited, and is checked against the answer key written when the invoice was generated.
Flagged, not guessed
If it doesn’t add up, it doesn’t slip through.
Reading an invoice is half the job. Knowing when the reading is incomplete is the other half, and that is where bad data usually gets in.
01
Add it up
Before an invoice moves on, its lines, charges and discounts are added up and compared with the totals printed on the invoice. Deductions such as retainage or withholding tax are checked against the amount due.
02
Read it again
When the numbers do not match, a second AI model reads the invoice again, before anyone on your team has to look at it.
03
Flag it for a person
If it still does not add up, the invoice goes to your team flagged, with the reason and the original document beside the captured data. Then your validation rules check every invoice before it is released.
lines + charges − discounts = printed net, gross − deductions = amount due → moves on. Otherwise: read again, then flag.
The check catches missing lines and totals that do not reconcile. A wrong value that still adds up, such as a misread date, is for your validation rules and your team to catch, which is why every invoice passes them before it is released.
How we test
210 hard invoices. Every value checked against a key.
The eight invoices above come from our capture benchmark: invoices we built to be difficult, each with an answer key, so every captured value is checked, not eyeballed. We run it whenever a model or a prompt changes.
420 of 420
invoices returned with every line, in two full runs over the whole set.
85 in 100
invoices fully right on the first pass, with nobody touching them: every line and every core header field. At “95% per field” it would be fewer than half.
556 of 556
lines on our longest test invoice, 15 pages, captured completely in both runs.
9
languages, from suppliers in 18 countries.
In the set: 25 phone photos, 40 scans, 10 faxes, 15 stamped or handwritten documents, 16 credit notes. The longest invoice runs 15 pages and 556 lines.
Nuntiq capture benchmark, October 2026: 210 invoices in 200 PDFs, synthetic test documents generated by Nuntiq with fictional companies, then printed, scanned, faxed and photographed digitally; two full runs of the production setup, including its totals check and second read. Complete means every line returned; fully right means every line amount and every core header field (invoice number, dates, amounts, currency, order number, supplier, customer) matches the answer key. Benchmark results, not a guarantee for every invoice.
Capture is where it starts
AP Receiving turns every invoice you receive into data your ERP can post.
Invoices arrive by email, direct supplier send, upload, API or e-invoice file and land in one queue. AI reads each document, your business rules enrich and validate the data, and your team reviews only the exceptions before the invoice goes to your ERP.
Any Channel, One Queue
Email, direct supplier send, upload, API or structured e-invoice file, all in the same processing queue.
Zero Templates
AI reads each supplier’s layout from the first invoice. No templates to build, no separator sheets.
Matched and Validated
Matched to your entities, suppliers and purchase orders, then checked by your rules, duplicates included, before anything posts.
Suppliers Help Themselves
Suppliers log in with a one-time code and see the status of their invoices and payments, without calling your team.
Want to see this on your own invoices?
Test invoices prove a point. Yours are the ones that count. Bring the scans, the faxes and the 400-line monsters your team dreads, and see what comes back.
You can be processing your own invoices within a week. ERP integration follows on its own timeline.