ModelVerdict

Joseph Jackson

Anglais (US)E-mail9 champs

Document en-p0040 · mise en page thread · 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: 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

Verdict

Le moins cher sans erreur : Gemma 4 31B, à 0,11 € pour 1 000 documents.

  • Claude Sonnet 5 ne fait aucune erreur non plus, mais coûte 31,7× plus cher.
  • Mistral Small 4 est 1,5× moins cher, mais : valeur erronée (Priorité).

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 48 / 9 champsGemma 4 31B9 / 9 champsGPT-6 Luna9 / 9 champsDeepSeek V4.1 Flash9 / 9 champsGemini 3.5 Flash Lite9 / 9 champsQwen3.8 Flash8 / 9 champsMistral Medium 3.58 / 9 champsGemini 3.8 Flash9 / 9 champsGPT-6 Sol9 / 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)
Prioriténormal highvaleur erronéenormal (correct)normal (correct)normal (correct)normal (correct) urgentvaleur erronée highvaleur erronéenormal (correct)normal (correct)normal (correct)
Tonaliténegativenegative (correct)negative (correct)negative (correct)negative (correct)negative (correct)negative (correct)negative (correct)negative (correct)negative (correct)negative (correct)
Nom du clientJoseph JacksonJoseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (correct)Joseph Jackson (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)
Échéance—— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)— (correct)
Tokensentrée / sortie676 / 57728 / 57802 / 146942 / 302716 / 761 039 / 1 364676 / 57716 / 275802 / 1071 013 / 193
dont raisonnement cachéfacturé comme sortie009525701 28701995689
dont depuis le cacheentrée facturée à prix réduit406405860768374000
Coût de ce documentcette exécution0,0001 €0,0001 €0,0001 €0,0003 €0,0004 €0,0006 €0,0013 €0,0014 €0,0025 €0,0036 €
Pour 1 000 documentspour ce même type de document0,07 €0,11 €0,14 €0,26 €0,37 €0,64 €1,33 €1,44 €2,46 €3,64 €
Latencecette exécution1,1 s4 s2,4 s3,8 s0,6 s22,9 s0,6 s1,6 s2,9 s3,6 s