ModelVerdict

Jane Rubio

Anglais (US)E-mail9 champs

Document en-p0010 · mise en page signature · 9 champs · partie publique du jeu de données · Même facture · Tchèque → · Signaler une erreur dans cet exemple

Texte de l'e-mail (le modèle a reçu exactement ce texte)

From: Jane Rubio <jane.rubio@green.example>
To: support@davis-daniels.example
Date: Thu, Apr 17, 2025 at 2:16 PM
Subject: System problem

Hello,

After the last update the integration with our accounting system stopped working. Thank you for handling this. We need this sorted out by tomorrow.

Kind regards,

Jane Rubio
Owner
Green PLC
439 Downs Springs
Roberttown, MT 76282
Phone: (654) 870-5683
EIN: 73-9498746

This email and any attachments are confidential and intended solely for the addressee.

Verdict

Le moins cher sans erreur : Mistral Small 4, à 0,07 € pour 1 000 documents.

  • Claude Sonnet 5 ne fait aucune erreur non plus, mais coûte 49,6× 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

ChampValeur correcteMistral Small 49 / 9 champsGemma 4 31B9 / 9 champsGPT-6 Luna9 / 9 champsDeepSeek V4.1 Flash9 / 9 champsQwen3.8 Flash8 / 9 champsGemini 3.5 Flash Lite8 / 9 champsMistral Medium 3.59 / 9 champsGPT-6 Sol9 / 9 champsGemini 3.8 Flash9 / 9 champsClaude Sonnet 59 / 9 champs
Catégorietechnicaltechnical (correct)technical (correct)technical (correct)technical (correct)technical (correct)technical (correct)technical (correct)technical (correct)technical (correct)technical (correct)
Prioritéurgenturgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)urgent (correct)
Tonaliténeutralneutral (correct)neutral (correct)neutral (correct)neutral (correct) positivevaleur erronée negativevaleur erronéeneutral (correct)neutral (correct)neutral (correct)neutral (correct)
Nom du clientJane RubioJane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)Jane Rubio (correct)
Numéro de commande—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Numéro de facture—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Montant—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Devise—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Échéance2025-04-182025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)2025-04-18 (correct)
Tokensentrée / sortie593 / 68623 / 67713 / 113854 / 156945 / 379611 / 53593 / 68713 / 81611 / 540857 / 200
dont raisonnement cachéfacturé comme sortie0057104291002545388
dont depuis le cacheentrée facturée à prix réduit406453058676800000
Coût de ce documentcette exécution0,0001 €0,0001 €0,0001 €0,0002 €0,0002 €0,0003 €0,0013 €0,0021 €0,0023 €0,0034 €
Pour 1 000 documentspour ce même type de document0,07 €0,10 €0,12 €0,15 €0,20 €0,29 €1,29 €2,06 €2,28 €3,42 €
Latencecette exécution0,8 s2,6 s2,6 s3,5 s5,7 s0,7 s0,7 s2,8 s2,5 s3,4 s