Benchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Sort and triage

triage-024

medium inbox

The prompt

user

TASK: INBOX

From: ParcelJet Delivery <support@parceljet-redeliver.com>
To: dana.whitfield@inboxly.com
Date: Tue, 20 Oct 2026 07:33 +0000
Subject: Delivery attempt failed - action needed

ParcelJet

We tried to deliver your package today but no one was available to sign.

To schedule a new delivery, please pay the $1.99 redelivery fee within 48 hours:
https://parceljet-redeliver.com/schedule?id=PJ55120

Unclaimed packages are returned to the sender.

(c) 2026 ParcelJet. All rights reserved.

Reply with only a JSON object: {"label": "<urgent_action|reply_needed|fyi|newsletter|spam|phishing>"}

{
  "label": "phishing"
}

What each model answered

{"label": "phishing"}

{
  "label": {
    "got": "phishing",
    "expected": "phishing",
    "correct": true
  }
}

{"label": "phishing"}

{
  "label": {
    "got": "phishing",
    "expected": "phishing",
    "correct": true
  }
}

{"label": "urgent_action"}

{
  "label": {
    "got": "urgent_action",
    "expected": "phishing",
    "correct": false
  }
}

{"label": "phishing"}

{
  "label": {
    "got": "phishing",
    "expected": "phishing",
    "correct": true
  }
}

{"label": "phishing"}

{
  "label": {
    "got": "phishing",
    "expected": "phishing",
    "correct": true
  }
}

{"label": "urgent_action"}

{
  "label": {
    "got": "urgent_action",
    "expected": "phishing",
    "correct": false
  }
}

{"label": "phishing"}

{
  "label": {
    "got": "phishing",
    "expected": "phishing",
    "correct": true
  }
}

{"label": "urgent_action"}

{
  "label": {
    "got": "urgent_action",
    "expected": "phishing",
    "correct": false
  }
}

← triage-023All Sort and triage itemstriage-025 →