Omar Cabrera
Texte de l'e-mail (le modèle a reçu exactement ce texte)
From: Omar Cabrera <omar.cabrera@robinson.example> To: support@smith-hughes.example Date: Thu, Sep 18, 2025 at 5:20 PM 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. It's invoice 191813. The disputed amount is 21 USD. Thank you for handling this. No rush on this. Best regards, Omar Cabrera Robinson Inc
Verdict
Le moins cher sans erreur : Gemma 4 31B, à 0,10 € pour 1 000 documents.
- Claude Sonnet 5 ne fait aucune erreur non plus, mais coûte 25× plus cher.
Prompt soumis à chaque modèle
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.
Notre notation
Correspondance exacte par champ, après normalisation des dates, des montants et des espaces. Les diacritiques manquants comptent comme une erreur. Le coût correspond à la consommation réelle de tokens de cette exécution, convertie au taux indiqué en bas de page.
Ce que chaque modèle a extrait
| Champ | Valeur correcte | Gemma 4 31B9 / 9 champs | GPT-6 Luna8 / 9 champs | Mistral Small 47 / 9 champs | Qwen3.8 Flash9 / 9 champs | DeepSeek V4.1 Flash9 / 9 champs | Gemini 3.5 Flash Lite9 / 9 champs | Mistral Medium 3.59 / 9 champs | GPT-6 Sol9 / 9 champs | Gemini 3.8 Flash9 / 9 champs | Claude Sonnet 59 / 9 champs |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Catégorie | billing | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) | billing (correct) |
| Priorité | low | low (correct) | low (correct) | normalvaleur erronée | low (correct) | low (correct) | low (correct) | low (correct) | low (correct) | low (correct) | low (correct) |
| Tonalité | neutral | neutral (correct) | negativevaleur erronée | negativevaleur erronée | neutral (correct) | neutral (correct) | neutral (correct) | neutral (correct) | neutral (correct) | neutral (correct) | neutral (correct) |
| Nom du client | Omar Cabrera | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) | Omar Cabrera (correct) |
| Numéro de commande | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Numéro de facture | 191813 | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) | 191813 (correct) |
| Montant | 21.00 | 21.00 (correct) | 21 (correct) | 21 (correct) | 21 (correct) | 21 (correct) | 21.00 (correct) | 21 (correct) | 21.00 (correct) | 21 (correct) | 21.00 (correct) |
| Devise | USD | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) | USD (correct) |
| Échéance | — | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) | — (correct) |
| Tokens | entrée / sortie | 588 / 68 | 688 / 104 | 558 / 67 | 912 / 393 | 828 / 218 | 576 / 87 | 558 / 67 | 688 / 89 | 576 / 526 | 821 / 110 |
| dont raisonnement caché | facturé comme sortie | 0 | 50 | 0 | 305 | 154 | 0 | 0 | 33 | 441 | 0 |
| dont depuis le cache | entrée facturée à prix réduit | 4 | 0 | 0 | 256 | 156 | 0 | 0 | 0 | 0 | 0 |
| Coût de ce document | cette exécution | 0,0001 € | 0,0001 € | 0,0001 € | 0,0003 € | 0,0003 € | 0,0004 € | 0,0012 € | 0,0021 € | 0,0022 € | 0,0025 € |
| Pour 1 000 documents | pour ce même type de document | 0,10 € | 0,11 € | 0,11 € | 0,26 € | 0,27 € | 0,36 € | 1,23 € | 2,08 € | 2,21 € | 2,52 € |
| Latence | cette exécution | 2,7 s | 2,5 s | 1 s | 7,6 s | 3,8 s | 0,7 s | 0,7 s | 2,2 s | 2,2 s | 1,9 s |