Joseph Jackson
E-Mail-Text (das Modell hat genau diesen Text erhalten)
From: Joseph Jackson <joseph.jackson@campbell-hansen.example> To: support@hicks-richard.example Date: Wed, Jun 3, 2026 at 2:26 PM Subject: Re: Error in the app Hello, Following up on our previous email below, we're still waiting for a solution. We're really disappointed, this is the third time we're writing about this. Best regards, Joseph Jackson Campbell-Hansen On Mon, Jun 1, 2026 at 4:03 PM, support@hicks-richard.example wrote: > Hello, thank you for your message. We've logged your request as ticket #10209 and are looking into it. > > Hicks, Richard and Levy > On Mon, Jun 1, 2026 at 2:26 PM, Joseph Jackson <joseph.jackson@campbell-hansen.example> wrote: > > Hello, > > > > After the last update the integration with our accounting system stopped working. > > > > Best regards, > > Joseph Jackson > > Campbell-Hansen
Fazit
Am günstigsten ohne Fehler: Gemma 4 31B für 0,11 € pro 1.000 Dokumente.
- Claude Sonnet 5 ist ebenfalls fehlerfrei, aber 31,7× teurer.
- Mistral Small 4 ist 1,5× 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 48 / 9 Felder | Gemma 4 31B9 / 9 Felder | GPT-6 Luna9 / 9 Felder | DeepSeek V4.1 Flash9 / 9 Felder | Gemini 3.5 Flash Lite9 / 9 Felder | Qwen3.8 Flash8 / 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 | technical | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) | technical (richtig) |
| Priorität | normal | highfalscher Wert | normal (richtig) | normal (richtig) | normal (richtig) | normal (richtig) | urgentfalscher Wert | highfalscher Wert | normal (richtig) | normal (richtig) | normal (richtig) |
| Stimmung | negative | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) | negative (richtig) |
| Kundenname | Joseph Jackson | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) | Joseph Jackson (richtig) |
| Bestellnummer | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Rechnungsnummer | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Betrag | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Währung | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Frist | — | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) | — (richtig) |
| Tokens | Eingabe / Ausgabe | 676 / 57 | 728 / 57 | 802 / 146 | 942 / 302 | 716 / 76 | 1.039 / 1.364 | 676 / 57 | 716 / 275 | 802 / 107 | 1.013 / 193 |
| davon verdecktes Nachdenken | als Ausgabe berechnet | 0 | 0 | 95 | 257 | 0 | 1.287 | 0 | 199 | 56 | 89 |
| davon aus dem Cache | Eingabe mit Rabatt | 406 | 4 | 0 | 586 | 0 | 768 | 374 | 0 | 0 | 0 |
| Kosten für dieses Dokument | dieser Lauf | 0,0001 € | 0,0001 € | 0,0001 € | 0,0003 € | 0,0004 € | 0,0006 € | 0,0013 € | 0,0014 € | 0,0025 € | 0,0036 € |
| Pro 1.000 Dokumente | für die gleiche Art von Dokument | 0,07 € | 0,11 € | 0,14 € | 0,26 € | 0,37 € | 0,64 € | 1,33 € | 1,44 € | 2,46 € | 3,64 € |
| Latenz | dieser Lauf | 1,1 s | 4 s | 2,4 s | 3,8 s | 0,6 s | 22,9 s | 0,6 s | 1,6 s | 2,9 s | 3,6 s |