ModelVerdict

Tyler Robertson

English (US)Text7 fields

Document en-p0002 · layout ticket · 7 fields · public part of the dataset · Same invoice in Czech → · Report an error in this example

Text (the model received exactly this text)

Ticket #29494 · Damaged delivery

Customer: Tyler Robertson
Email: tyler.robertson@inbox.example
Phone: 692-555-0029

The customer reports that the goods arrived damaged and asks for a replacement.
The replacement ships no later than January 15, 2026.
Copy sent to office@johnson-bell.example.

Verdict

Cheapest with no errors: Mistral Small 4 at $0.06 per 1,000 documents.

  • Claude Sonnet 5.5 is also error-free, but 47.8× 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 normalizing dates, amounts, and whitespace. Missing diacritics count as an error. Cost is the actual token spend of this run, converted at the rate shown in the footer.

What each model extracted

FieldCorrect valueMistral Small 47 / 7 fieldsGemma 4 31B7 / 7 fieldsGPT-6 Luna7 / 7 fieldsClaude Haiku 5.57 / 7 fieldsGLM-5.3 Flash7 / 7 fieldsQwen3.8 Flash7 / 7 fieldsDeepSeek V4.1 Flash7 / 7 fieldsGemini 3.5 Flash Lite7 / 7 fieldsMistral Medium 3.57 / 7 fieldsGPT-6 Sol7 / 7 fieldsGemini 3.8 Flash7 / 7 fieldsMistral Large 47 / 7 fieldsClaude Sonnet 57 / 7 fieldsClaude Sonnet 5.57 / 7 fields
NamesTyler RobertsonTyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)Tyler Robertson (correct)
Email addressestyler.robertson@inbox.exampletyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)tyler.robertson@inbox.example (correct)
Phone numbers692-555-0029692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)692-555-0029 (correct)
Addresses—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Dates of birth—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
National IDs—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Bank accounts—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Tokensinput / output324 / 71347 / 71439 / 851,039 / 97314 / 267644 / 349569 / 248335 / 104324 / 74439 / 58335 / 331522 / 9171,037 / 971,039 / 97
including hidden reasoningbilled as output0025020725118400027187200
including cached inputinput billed at a discount20330005123640000000
Cost of this documentthis run$0.0001$0.0001$0.0001$0.0002$0.0002$0.0002$0.0002$0.0004$0.0010$0.0015$0.0015$0.0023$0.0030$0.0030
Per 1,000 documentsfor documents of this type$0.06$0.08$0.09$0.15$0.18$0.19$0.21$0.36$1.04$1.46$1.49$2.27$3.04$3.05
Latencythis run0.9 s1.4 s2.2 s1.6 s3.6 s6.9 s2.4 s0.7 s0.9 s2 s1.5 s74.2 s2.4 s1.9 s

Log in with email

We use your email only to log you in (and for the digest if you tick it). No spam.