Rose-Rojas Group LLC · INV-16447

English (US)PDF text11 fields

Document en-p0020 · layout en-L05 · 11 fields · public part of the dataset · Same invoice in Czech → · Report an error in this example

PDF text layer (the model received only this text)

SELLER
Rose-Rojas Group LLC                                      Invoice
4509 Main Street
Seattle, WA 98154
                                                          INV-16447
Tel. (228) 555-0173    EIN: 56-2825760
                                                          Date                 05/14/2026
BUYER                                                     Terms                Net 14
Frontier Industries Corp.                                 Due date             05/28/2026
4474 Market Street
Raleigh, NC 27696                                         Pay by ACH
                                                          Bank                 PNC Bank, N.A.
                                                          Account name         Rose-Rojas Group LLC
                                                          Routing number       043000096
                                                          Account number       36165444
                                                          Payment reference    INV-16447



Description                              Qty   Unit               Unit price     Tax            Amount
LED troffer light 2 x 4 ft                11     ea                   85.99        T              945.89
Scissor lift rental                        1    day                  402.99        T              402.99
Installation labor                       2.7     hr                   70.99                       191.67

Thank you for your business!                   Subtotal                                         1,540.55
                                               Non-taxable                                        191.67
                                               Taxable at 7.25%                                 1,348.88
                                               Sales tax (7.25%)                                   97.79
                                               Total                                            1,638.34


                                                                          Total due: $1,638.34

Verdict

Cheapest without an error: GPT-6 Luna at $0.17 per 1,000 documents.

Claude Sonnet 5 is also error-free but 27× more expensive.

Prompt given to every model

Extract the following data from the attached document and return only JSON with these keys:

supplier_name      supplier's name (exactly as printed, including the legal form)
supplier_id        supplier's tax ID (EIN), if printed
invoice_number     document number
payment_reference  payment reference to quote with the payment
issue_date         invoice date (YYYY-MM-DD)
due_date           due date (YYYY-MM-DD)
net_by_rate        amount per sales tax rate, e.g. {"8.25": 1845.00}; non-taxable amounts under "0"
vat_by_rate        sales tax per rate, e.g. {"8.25": 152.21}
total              total due (number, negative for credit notes)
currency           ISO 4217 currency code (USD, GBP, EUR, …)
bank_account       supplier's bank details as "routing-number account-number", or IBAN

Rules:
- Return the supplier's data only, never the customer's.
- If a value is not on the document, return null. Do not guess.
- If the document has no tax breakdown, return net_by_rate and vat_by_rate as null.
- Amounts as numbers with a decimal point, no thousands separators and no currency symbol.

How we score

Exact match per field after normalising dates, amounts and whitespace. Missing diacritics count as an error. Cost is the real token spend of this run, converted at the rate shown in the footer.

What each model extracted

Field	Correct value	GPT-6 Luna11 / 11 fields	Mistral Small 411 / 11 fields	Gemma 4 31B11 / 11 fields	DeepSeek V4.1 Flash11 / 11 fields	Qwen3.8 Flash9 / 11 fields	Gemini 3.5 Flash Lite11 / 11 fields	Gemini 3.8 Flash11 / 11 fields	Mistral Medium 3.511 / 11 fields	GPT-6 Sol11 / 11 fields	Claude Sonnet 511 / 11 fields
Supplier	Rose-Rojas Group LLC	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)	Rose-Rojas Group LLC (correct)
Supplier ID (EIN, IČO…)	56-2825760	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)	56-2825760 (correct)
Invoice number	INV-16447	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)
Payment reference	INV-16447	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)	INV-16447 (correct)
Invoice date	2026-05-14	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)	2026-05-14 (correct)
Due date	2026-05-28	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)	2026-05-28 (correct)
Net by tax rate	0 %: 191.67, 7.25 %: 1348.88	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	: 191.67,7.25 %: 1348.88wrong value	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)	0 %: 191.67, 7.25 %: 1348.88 (correct)
Tax by rate	0 %: 0.00, 7.25 %: 97.79	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	: 0.00,7.25 %: 97.79wrong rate	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)	7.25 %: 97.79 (correct)
Total	1638.34	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)	1638.34 (correct)
Currency	USD	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)	USD (correct)
Bank account	043000096 36165444	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)	043000096 36165444 (correct)
Tokens	input / output	713 / 202	683 / 181	722 / 226	879 / 403	1,043 / 1,254	710 / 225	710 / 451	683 / 181	713 / 116	873 / 291
of which hidden reasoning	billed as output	84	0	0	258	1,036	0	288	0	0	78
of which from cache	input billed at a discount	0	246	309	438	512	0	0	0	0	0
Cost of this document	this run	$0.0002	$0.0002	$0.0002	$0.0004	$0.0007	$0.0008	$0.0022	$0.0024	$0.0026	$0.0047
Per 1,000 documents	for the same kind of document	$0.17	$0.18	$0.19	$0.37	$0.68	$0.78	$2.22	$2.38	$2.59	$4.66
Latency	this run	2.9 s	1.4 s	12.2 s	5.8 s	17.1 s	1 s	2.8 s	1.2 s	2.9 s	3.4 s