ModelVerdict

Matthew Ramirez

English (US)Text7 fields

Document en-p0009 · layout hr · 7 fields · public part of the dataset · Same invoice in Czech → · Report an error in this example

Text (the model got exactly this text)

Employee record – Mcconnell LLC

Employee: Matthew Ramirez
Date of birth: July 23, 1989
SSN: 937-88-8960
Home address: 57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103
Phone: 569-555-0053
Direct deposit account: 276797981875

Hired as staff accountant, 90-day probation period.

Employer: Mcconnell LLC, EIN 59-4944725

Verdict

Cheapest without an error: Gemma 4 31B at $0.10 per 1,000 documents.

  • Claude Sonnet 5 is also error-free but 34× more expensive.

Prompt given to every model

Find all personal data of natural persons in the text below (for anonymisation) and return only
JSON with these keys, each a list of strings (an empty list when there is none):

person_names       full names of people, each person once, as written in the text
email_addresses    email addresses of people
phone_numbers      phone numbers of people, as written
postal_addresses   home or delivery addresses of people, as written (street, city, ZIP)
birth_dates        dates of birth (YYYY-MM-DD)
national_ids       national identification numbers (e.g. SSN, birth numbers)
bank_accounts      bank account numbers of people, as written

Rules:
- Only data of natural persons. Company names, company registration or tax numbers (EIN, IČO,
  VAT), generic company addresses such as info@ or support@, order and ticket numbers are not
  personal data: leave them out.
- Dates that are not dates of birth (meetings, deliveries, start dates) are not personal data.
- Do not invent or complete values; copy them from the text.

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 31B7 / 7 fieldsGPT-6 Luna7 / 7 fieldsMistral Small 47 / 7 fieldsDeepSeek V4.1 Flash7 / 7 fieldsQwen3.8 Flash7 / 7 fieldsGemini 3.5 Flash Lite6 / 7 fieldsMistral Medium 3.57 / 7 fieldsGemini 3.8 Flash7 / 7 fieldsGPT-6 Sol7 / 7 fieldsClaude Sonnet 57 / 7 fields
NamesMatthew RamirezMatthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)Matthew Ramirez (correct)
Email addresses—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Phone numbers569-555-0053569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)569-555-0053 (correct)
Addresses57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 2910357092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)57092 Armstrong Inlet Apt. 568, Ralphburgh, MD 29103 (correct)
Dates of birth1989-07-231989-07-23 (correct)1989-07-23 (correct)1989-07-23 (correct)1989-07-23 (correct)1989-07-23 (correct) nullmissing fieldJuly 23, 1989 (correct)1989-07-23 (correct)1989-07-23 (correct)1989-07-23 (correct)
National IDs937-88-8960937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)937-88-8960 (correct)
Bank accounts276797981875276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)276797981875 (correct)
Tokensinput / output397 / 120469 / 166380 / 122603 / 298698 / 642385 / 155380 / 123385 / 630469 / 1941,079 / 136
of which hidden reasoningbilled as output0800208473005231080
of which from cacheinput billed at a discount2460036651200000
Cost of this documentthis run$0.0001$0.0001$0.0001$0.0003$0.0003$0.0005$0.0015$0.0027$0.0029$0.0035
Per 1,000 documentsfor the same kind of document$0.10$0.13$0.13$0.25$0.34$0.50$1.49$2.65$2.88$3.52
Latencythis run4.7 s1.9 s0.9 s4.1 s11.8 s0.8 s1.6 s2.5 s4.4 s2.3 s