ModelVerdict

Daniel Stewart

Inglés (EE. UU.)Correo9 campos

Documento en-p0017 · diseño thread · 9 campos · parte pública del conjunto de datos · La misma factura en otro idioma: Checo → · Informar de un error en este ejemplo

Texto del correo (el modelo recibió exactamente este texto)

From: Daniel Stewart <daniel.stewart@williams-ross.example>
To: support@johnson-singleton.example
Date: Tue, Apr 21, 2026 at 8:51 AM
Subject: Re: Cancellation

Hello,

Following up on our previous email below, we're still waiting for a solution. We need an answer by the end of the month.

Best regards,
Daniel Stewart
Williams, Ross and Donaldson

On Fri, Apr 17, 2026 at 10:35 AM, support@johnson-singleton.example wrote:

> Hello, thank you for your message. We've logged your request as ticket #48521 and are looking into it.
>
> Johnson-Singleton

> On Fri, Apr 17, 2026 at 5:51 AM, Daniel Stewart <daniel.stewart@williams-ross.example> wrote:

> > Hello,
> >
> > We would like to cancel our order, we no longer need the goods. Order #10296889.
> >
> > Best regards,
> > Daniel Stewart
> > Williams, Ross and Donaldson

Veredicto

El más barato sin errores: Gemini 3.5 Flash Lite, a 0,42 € por cada 1000 documentos.

  • Gemini 3.8 Flash tampoco comete errores, pero es 7× más caro.
  • Gemma 4 31B es 3,4× más barato, pero: valor incorrecto (Prioridad).
  • Mistral Small 4 es 3× más barato, pero: valor incorrecto (Prioridad).
  • GPT-6 Luna es 3× más barato, pero: valor incorrecto (Sentimiento).

Prompt enviado a todos los modelos

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.

Cómo puntuamos

Coincidencia exacta por campo tras normalizar fechas, importes y espacios. La falta de diacríticos cuenta como error. El coste es el gasto real en tokens de esta ejecución, convertido al tipo de cambio indicado en el pie de página.

Lo que extrajo cada modelo

CampoValor correctoGemma 4 31B7 / 9 camposMistral Small 47 / 9 camposGPT-6 Luna8 / 9 camposDeepSeek V4.1 Flash8 / 9 camposGemini 3.5 Flash Lite9 / 9 camposQwen3.8 Flash8 / 9 camposMistral Medium 3.58 / 9 camposGPT-6 Sol9 / 9 camposGemini 3.8 Flash9 / 9 camposClaude Sonnet 58 / 9 campos
Categoríacancellationcancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)cancellation (correcto)
Prioridadnormal highvalor incorrecto highvalor incorrectonormal (correcto)normal (correcto)normal (correcto)normal (correcto) highvalor incorrectonormal (correcto)normal (correcto)normal (correcto)
Sentimientoneutral negativevalor incorrecto negativevalor incorrecto negativevalor incorrecto negativevalor incorrectoneutral (correcto) negativevalor incorrectoneutral (correcto)neutral (correcto)neutral (correcto) negativevalor incorrecto
Nombre del clienteDaniel StewartDaniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)Daniel Stewart (correcto)
Número de pedido1029688910296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)10296889 (correcto)
Número de factura—— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)
Importe—— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)
Moneda—— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)— (correcto)
Plazo2026-04-302026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)2026-04-30 (correcto)
Tokensentrada / salida733 / 76695 / 76810 / 141955 / 351721 / 961052 / 945695 / 76810 / 92721 / 7091016 / 316
de ellos, razonamiento ocultose factura como salida00822970848033613201
de ellos, desde cachéentrada con descuento4530058607680000
Coste de este documentoesta ejecución0,0001 €0,0001 €0,0001 €0,0003 €0,0004 €0,0005 €0,0015 €0,0023 €0,0029 €0,0048 €
Por cada 1000 documentospara el mismo tipo de documento0,12 €0,14 €0,14 €0,29 €0,42 €0,46 €1,48 €2,34 €2,94 €4,78 €
Latenciaesta ejecución2,6 s0,7 s2,8 s5,9 s0,6 s11,8 s1,3 s2,8 s3 s5,4 s