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

triage-031

hard ticket

The prompt

user

TASK: TICKET

Ticket #48236
From: Tamsin Rowe <tamsin@roweinteriors.co>
Plan: Basic
Subject: Fix this or I'm cancelling

I downgraded from Pro to Basic on September 12 and got a confirmation email saying so. This month you still charged me $49 for Pro instead of $19. I want the $30 difference refunded. If this isn't sorted out I'm cancelling and going elsewhere.

Tamsin Rowe

Reply with only a JSON object: {"category": "<billing|bug|account_access|feature_request|cancellation>", "priority": "<low|medium|high|urgent>"}

What we expected

{
  "category": "billing",
  "priority": "high"
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 0.75 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

Ornith-1.5 9B

✓ pass · score 100 · 0.70 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

Granite 4.2 8B

✓ pass · score 100 · 0.77 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

Spark-X2.5 4B

✓ pass · score 100 · 0.48 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

Mellum2.1 12B-A2.5B

✓ pass · score 100 · 0.31 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

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

✓ pass · score 100 · 0.24 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

MiniCPM5 2B

✓ pass · score 100 · 0.39 s

{"category": "billing", "priority": "high"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "high",
    "expected": "high",
    "correct": true
  }
}

K2-Horizon 0.9B

✗ fail · score 50 · 0.17 s

{"category": "billing", "priority": "urgent"}

Scoring detail

{
  "category": {
    "got": "billing",
    "expected": "billing",
    "correct": true
  },
  "priority": {
    "got": "urgent",
    "expected": "high",
    "correct": false
  }
}

← triage-030All Sort and triage itemstriage-032 →