Sheila Evans
Email text (the model got exactly this text)
From: Sheila Evans <sheila.evans@villarreal-jones.example> To: support@lowery.example Date: Tue, Jul 28, 2026 at 3:47 PM Subject: Billing error Hello, We need a corrected invoice, our company address on it is wrong. We're talking about 63.27 USD. Many thanks, we really enjoy working with your team. We need this sorted out by July 30. Best regards, Sheila Evans Purchasing Manager Villarreal, Jones and Rosario 258 Oconnor Locks Leslieview, WI 70726 Phone: (226) 393-9408 EIN: 29-1247285 This email and any attachments are confidential and intended solely for the addressee.
Verdict
Cheapest without an error: Mistral Small 4 at $0.08 per 1,000 documents.
- Claude Sonnet 5 is also error-free but 48× more expensive.
Prompt given to every model
You triage the support inbox. Read the email below and return only JSON with these keys:
category one of: billing (invoices, payments, charges), delivery (where is the order, shipping,
address change), complaint (damaged, wrong or defective goods, warranty claims),
technical (login, app or system errors, integrations), cancellation (cancel an order,
contract or subscription), sales (quotes, prices, interest before buying)
priority one of: urgent, high, normal, low (rules below)
sentiment one of: positive, neutral, negative (the customer's tone)
customer_name full name of the customer who wrote the request
order_number the customer's order number, if mentioned
invoice_number invoice number, if mentioned
amount the amount of money the request is about (number)
currency ISO 4217 code of that amount (USD, EUR, CZK, …)
deadline the date by which the customer wants a resolution or answer (YYYY-MM-DD)
Priority rules:
- urgent: the customer cannot work right now, or the deadline is at most 1 day after the email date
- high: the deadline is at most 7 days after the email date, or the customer threatens to cancel
or escalate (lawyer, ending the business)
- low: the customer says explicitly that it is not urgent
- normal: everything else
Rules:
- A thread: judge the newest message; order numbers, invoice numbers and amounts may come from the
quoted earlier messages. A forwarded email: the customer is the original sender, not the
colleague who forwarded it.
- Resolve relative deadlines ("by Friday", "by tomorrow", "by the end of the month") against the
date of the message that states them.
- Support ticket numbers, tax IDs and phone numbers are not order or invoice numbers.
- If a value is not in the email, return null. Do not guess.
- 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 | Mistral Small 49 / 9 fields | Gemma 4 31B8 / 9 fields | GPT-6 Luna9 / 9 fields | DeepSeek V4.1 Flash9 / 9 fields | Qwen3.8 Flash9 / 9 fields | Gemini 3.5 Flash Lite8 / 9 fields | Mistral Medium 3.59 / 9 fields | Gemini 3.8 Flash9 / 9 fields | GPT-6 Sol9 / 9 fields | Claude Sonnet 59 / 9 fields |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Category | billing | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) |
| Priority | high | high (correct) | urgentwrong value | high (correct) | high (correct) | high (correct) | urgentwrong value | high (correct) | high (correct) | high (correct) | high (correct) |
| Sentiment | positive | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) | positive (correct) |
| Customer name | Sheila Evans | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) | Sheila Evans (correct) |
| Order number | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Invoice number | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Amount | 63.27 | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) | 63.27 (correct) |
| Currency | USD | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) |
| Deadline | 2026-07-30 | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) | 2026-07-30 (correct) |
| Tokens | input / output | 629 / 74 | 656 / 73 | 741 / 117 | 884 / 212 | 981 / 402 | 644 / 93 | 629 / 74 | 644 / 288 | 741 / 92 | 898 / 223 |
| of which hidden reasoning | billed as output | 0 | 0 | 58 | 158 | 307 | 0 | 0 | 231 | 33 | 110 |
| of which from cache | input billed at a discount | 406 | 453 | 0 | 586 | 768 | 0 | 0 | 0 | 0 | 0 |
| Cost of this document | this run | $0.0001 | $0.0001 | $0.0001 | $0.0002 | $0.0002 | $0.0004 | $0.0015 | $0.0016 | $0.0024 | $0.0040 |
| Per 1,000 documents | for the same kind of document | $0.08 | $0.12 | $0.13 | $0.21 | $0.23 | $0.43 | $1.50 | $1.56 | $2.40 | $4.03 |
| Latency | this run | 1 s | 2.4 s | 2.5 s | 2.9 s | 6.4 s | 0.7 s | 0.8 s | 1.7 s | 2.7 s | 3.7 s |