Sandra Hogan
E-Mail-Text (das Modell hat genau diesen Text erhalten)
From: Sandra Hogan <sandra.hogan@robinson-shaw.example> To: support@rodriguez.example Date: Wed, Oct 29, 2025 at 10:25 AM Subject: Billing error Dear support team, The amount on your latest invoice doesn't match our records, you charged us for one more item than we received. This concerns invoice #INV-39209. The disputed amount is $481.22. Thank you for handling this. We need an answer by November 12. Best regards, Sandra Hogan Office Manager Robinson-Shaw 843 Courtney Vista West Kevin, CA 56361 Phone: (498) 682-1164 EIN: 90-7086421 This email and any attachments are confidential and intended solely for the addressee.
Fazit
Am günstigsten ohne Fehler: Gemma 4 31B für 0,12 € pro 1.000 Dokumente.
- Claude Sonnet 5 ist ebenfalls fehlerfrei, aber 32,3× teurer.
- Mistral Small 4 ist 1,4× günstiger, aber: falscher Wert (Priorität).
Prompt für alle Modelle
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.
So bewerten wir
Exakte Übereinstimmung pro Feld nach Normalisierung von Datumsangaben, Beträgen und Leerzeichen. Fehlende diakritische Zeichen zählen als Fehler. Die Kosten sind der reale Tokenverbrauch dieses Laufs, umgerechnet zum Kurs in der Fußzeile.
Was jedes Modell extrahiert hat
| Feld | Richtiger Wert | Mistral Small 47 / 9 Felder | Gemma 4 31B9 / 9 Felder | GPT-6 Luna8 / 9 Felder | DeepSeek V4.1 Flash9 / 9 Felder | Qwen3.8 Flash8 / 9 Felder | Gemini 3.5 Flash Lite9 / 9 Felder | Mistral Medium 3.58 / 9 Felder | Gemini 3.8 Flash9 / 9 Felder | GPT-6 Sol9 / 9 Felder | Claude Sonnet 59 / 9 Felder |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Kategorie | billing | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) | billing (richtig) |
| Priorität | normal | highfalscher Wert | normal (richtig) | normal (richtig) | normal (richtig) | normal (richtig) | normal (richtig) | highfalscher Wert | normal (richtig) | normal (richtig) | normal (richtig) |
| Stimmung | neutral | negativefalscher Wert | neutral (richtig) | negativefalscher Wert | neutral (richtig) | negativefalscher Wert | neutral (richtig) | neutral (richtig) | neutral (richtig) | neutral (richtig) | neutral (richtig) |
| Kundenname | Sandra Hogan | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) | Sandra Hogan (richtig) |
| Bestellnummer | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Rechnungsnummer | INV-39209 | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) | INV-39209 (richtig) |
| Betrag | 481.22 | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) | 481.22 (richtig) |
| Währung | USD | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) | USD (richtig) |
| Frist | 2025-11-12 | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) | 2025-11-12 (richtig) |
| Tokens | Eingabe / Ausgabe | 638 / 83 | 667 / 81 | 748 / 131 | 888 / 186 | 991 / 550 | 655 / 101 | 638 / 83 | 655 / 418 | 748 / 108 | 909 / 225 |
| davon verdecktes Nachdenken | als Ausgabe berechnet | 0 | 0 | 70 | 128 | 447 | 0 | 0 | 354 | 47 | 104 |
| davon aus dem Cache | Eingabe mit Rabatt | 406 | 453 | 0 | 586 | 768 | 0 | 0 | 0 | 0 | 0 |
| Kosten für dieses Dokument | dieser Lauf | 0,0001 € | 0,0001 € | 0,0001 € | 0,0002 € | 0,0003 € | 0,0004 € | 0,0015 € | 0,0019 € | 0,0024 € | 0,0037 € |
| Pro 1.000 Dokumente | für die gleiche Art von Dokument | 0,08 € | 0,12 € | 0,13 € | 0,18 € | 0,28 € | 0,41 € | 1,45 € | 1,89 € | 2,37 € | 3,74 € |
| Latenz | dieser Lauf | 0,8 s | 3,3 s | 3 s | 2,7 s | 6,6 s | 0,8 s | 0,7 s | 1,9 s | 3,6 s | 3,6 s |