ModelVerdict

Jennifer Moore · 5113

English (US)Scan11 fields

Document en-p0012 · layout en-L06 · 11 fields · public part of the dataset · Same invoice in Czech → · Report an error in this example

Jennifer Moore · 5113

Verdict

Cheapest without an error: Mistral Small 4 at $0.49 per 1,000 documents.

  • GPT-6 Sol is also error-free but 28.1× more expensive.
  • Gemma 4 31B is 3.1× cheaper, but: wrong value (Bank account).

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

FieldCorrect valueGemma 4 31B10 / 11 fieldsMistral Small 411 / 11 fieldsDeepSeek V4.1 Flash11 / 11 fieldsGPT-6 Luna11 / 11 fieldsGemini 3.5 Flash Lite11 / 11 fieldsQwen3.8 Flash11 / 11 fieldsGemini 3.8 Flash11 / 11 fieldsMistral Medium 3.511 / 11 fieldsClaude Sonnet 511 / 11 fieldsGPT-6 Sol11 / 11 fields
SupplierJennifer MooreJennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)Jennifer Moore (correct)
Supplier ID (EIN, IČO…)—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Invoice number51135113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)5113 (correct)
Payment referenceCUST-99694CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)CUST-99694 (correct)
Invoice date2025-08-132025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)2025-08-13 (correct)
Due date2025-08-202025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)2025-08-20 (correct)
Net by tax rate—0 %: 5539.11 (correct)0 %: 5539.11 (correct)— (correct)— (correct)0 %: 5539.11 (correct)0 %: 5539.11 (correct)0 %: 5539.11 (correct)0 %: 5539.11 (correct)0 %: 5539.11 (correct)— (correct)
Tax by rate—0 %: 0.00 (correct)— (correct)— (correct)— (correct)0 %: 0.00 (correct)0 %: 0.00 (correct)0 %: 0.00 (correct)— (correct)— (correct)— (correct)
Total5539.115539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)5539.11 (correct)
CurrencyUSDUSD (correct)USD (correct)USD (correct)USD (correct)USD (correct)USD (correct)USD (correct)USD (correct)USD (correct)USD (correct)
Bank account043000096 822373720 043800096 82237328wrong value043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)043000096 822373720 (correct)
Tokensinput / output584 / 1902,693 / 1411,549 / 3754,871 / 3091,406 / 1903,108 / 1,7281,406 / 4962,693 / 1415,163 / 1724,871 / 157
of which hidden reasoningbilled as output0027121801,5813640066
of which from cacheinput billed at a discount3070436003840000
Cost of this documentthis run$0.0002$0.0005$0.0005$0.0008$0.0009$0.0012$0.0029$0.0051$0.0120$0.0137
Per 1,000 documentsfor the same kind of document$0.16$0.49$0.50$0.76$0.90$1.23$2.91$5.10$12.05$13.75
Latencythis run9.8 s2.3 s4.9 s4.6 s1.9 s26.2 s2.9 s8.6 s3.6 s4 s