Aaron Wood
Text (the model got exactly this text)
Employee record – Jones, Cooper and Adams Employee: Aaron Wood SSN: 905-57-2195 Home address: 111 Christopher Walk Apt. 053, Harrischester, TN 59963 Phone: (441) 555-0031 Personal email: aaron.wood@inbox.example Direct deposit account: 171623448749 Hired as staff accountant starting April 30, 2026, 90-day probation period. Reports to: Robert Cook.
Verdict
Cheapest without an error: Mistral Small 4 at $0.10 per 1,000 documents.
- Claude Sonnet 5 is also error-free but 51.1× 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
| Field | Correct value | Mistral Small 47 / 7 fields | Gemma 4 31B7 / 7 fields | GPT-6 Luna7 / 7 fields | DeepSeek V4.1 Flash7 / 7 fields | Qwen3.8 Flash7 / 7 fields | Gemini 3.5 Flash Lite7 / 7 fields | Mistral Medium 3.57 / 7 fields | Gemini 3.8 Flash7 / 7 fields | GPT-6 Sol7 / 7 fields | Claude Sonnet 57 / 7 fields |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Names | Aaron Wood; Robert Cook | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) | Aaron Wood; Robert Cook (correct) |
| Email addresses | aaron.wood@inbox.example | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) | aaron.wood@inbox.example (correct) |
| Phone numbers | (441) 555-0031 | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) | (441) 555-0031 (correct) |
| Addresses | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) | 111 Christopher Walk Apt. 053, Harrischester, TN 59963 (correct) |
| Dates of birth | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| National IDs | 905-57-2195 | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) | 905-57-2195 (correct) |
| Bank accounts | 171623448749 | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) | 171623448749 (correct) |
| Tokens | input / output | 371 / 123 | 394 / 124 | 469 / 248 | 598 / 367 | 690 / 716 | 382 / 177 | 371 / 123 | 382 / 543 | 469 / 139 | 1,078 / 295 |
| of which hidden reasoning | billed as output | 0 | 0 | 156 | 272 | 546 | 0 | 0 | 433 | 47 | 151 |
| of which from cache | input billed at a discount | 219 | 249 | 0 | 366 | 512 | 0 | 0 | 0 | 0 | 0 |
| Cost of this document | this run | $0.0001 | $0.0001 | $0.0002 | $0.0003 | $0.0004 | $0.0006 | $0.0015 | $0.0023 | $0.0023 | $0.0051 |
| Per 1,000 documents | for the same kind of document | $0.10 | $0.10 | $0.17 | $0.30 | $0.37 | $0.56 | $1.48 | $2.32 | $2.33 | $5.11 |
| Latency | this run | 1 s | 1.9 s | 2.5 s | 4 s | 13.3 s | 0.9 s | 1.3 s | 2.3 s | 5.2 s | 4.5 s |