Unified Memory

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

triage-017

medium inbox

The prompt

user

TASK: INBOX

From: Kestrel Air <reservations@kestrelair.com>
To: dana.whitfield@inboxly.com
Date: Sat, 17 Oct 2026 18:22 -0500
Subject: Your trip confirmation - DEN to PDX - Confirmation K7Q2MX

Thank you for booking with Kestrel Air, Dana!

CONFIRMATION CODE: K7Q2MX

Flight KA 1186
Saturday, November 14, 2026
Depart: Denver (DEN) 9:40 AM
Arrive: Portland (PDX) 11:55 AM
Seat: 14C | Fare: Main Cabin

Total charged: $186.40 to Visa ending 2208

View or manage your trip: https://www.kestrelair.com/trips/K7Q2MX

Kestrel Air | 3000 Runway Dr, Dallas, TX 75261

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

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 0.82 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

Ornith-1.5 9B

✓ pass · score 100 · 0.76 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

Granite 4.2 8B

✓ pass · score 100 · 0.84 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

Spark-X2.5 4B

✓ pass · score 100 · 0.52 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

Mellum2.1 12B-A2.5B

✓ pass · score 100 · 0.35 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

Ling-3.0-tiny (7.9B-A1.3B)

✗ fail · score 0 · 0.26 s

{"label": "reply_needed"}
Scoring detail
{
  "label": {
    "got": "reply_needed",
    "expected": "fyi",
    "correct": false
  }
}

MiniCPM5 2B

✓ pass · score 100 · 0.34 s

{"label": "fyi"}
Scoring detail
{
  "label": {
    "got": "fyi",
    "expected": "fyi",
    "correct": true
  }
}

K2-Horizon 0.9B

✗ fail · score 0 · 0.18 s

{"label": "urgent_action"}
Scoring detail
{
  "label": {
    "got": "urgent_action",
    "expected": "fyi",
    "correct": false
  }
}

← triage-016All Sort and triage itemstriage-018 →