Donald Price · 2025-3394

Verdict
Cheapest without an error: Gemma 4 31B at $0.15 per 1,000 documents.
- GPT-6 Sol is also error-free but 90.8× 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 | Gemma 4 31B11 / 11 fields | Mistral Small 411 / 11 fields | DeepSeek V4.1 Flash11 / 11 fields | Gemini 3.5 Flash Lite11 / 11 fields | GPT-6 Luna11 / 11 fields | Qwen3.8 Flash11 / 11 fields | Gemini 3.8 Flash11 / 11 fields | Mistral Medium 3.511 / 11 fields | Claude Sonnet 511 / 11 fields | GPT-6 Sol11 / 11 fields |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Supplier | Donald Price | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) | Donald Price (correct) |
| Supplier ID (EIN, IČO…) | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Invoice number | 2025-3394 | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) |
| Payment reference | 2025-3394 | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) | 2025-3394 (correct) |
| Invoice date | 2025-12-28 | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) | 2025-12-28 (correct) |
| Due date | 2026-01-27 | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) | 2026-01-27 (correct) |
| Net by tax rate | — | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | — (correct) | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | 0 %: 1278.00 (correct) | — (correct) |
| Tax by rate | — | 0 %: 0.00 (correct) | — (correct) | — (correct) | 0 %: 0.00 (correct) | 0 %: 0.00 (correct) | 0 %: 0.00 (correct) | 0 %: 0.00 (correct) | — (correct) | — (correct) | — (correct) |
| Total | 1278.00 | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (correct) | 1278.00 (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 | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Tokens | input / output | 584 / 177 | 2,693 / 125 | 1,549 / 581 | 1,406 / 176 | 4,871 / 526 | 3,108 / 597 | 1,406 / 725 | 2,693 / 125 | 5,163 / 163 | 4,871 / 168 |
| of which hidden reasoning | billed as output | 0 | 0 | 481 | 0 | 429 | 466 | 586 | 0 | 0 | 80 |
| of which from cache | input billed at a discount | 3 | 0 | 436 | 0 | 0 | 2,944 | 0 | 0 | 0 | 0 |
| Cost of this document | this run | $0.0002 | $0.0005 | $0.0006 | $0.0009 | $0.0009 | $0.0013 | $0.0038 | $0.0050 | $0.0120 | $0.0139 |
| Per 1,000 documents | for the same kind of document | $0.15 | $0.48 | $0.63 | $0.86 | $0.87 | $1.31 | $3.77 | $4.98 | $11.96 | $13.86 |
| Latency | this run | 2.8 s | 1.4 s | 7.4 s | 1.7 s | 5.6 s | 11.2 s | 3.8 s | 8.1 s | 2.7 s | 4.7 s |