Unified Memory

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

triage-040

hard ticket

The prompt

user

TASK: TICKET

Ticket #48277
From: Mateo Ruiz <mateo@ruizroofing.com>
Plan: Pro
Subject: URGENT!!! need Spanish invoices by Friday

URGENT - I have a big new client meeting Friday and they want invoices in Spanish. Brightdesk only lets me make invoices in English. Can you add a Spanish language option before then?? This could be a $40k contract for me.

Mateo

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

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 0.78 s

{"category": "feature_request", "priority": "low"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "low",
    "expected": "low",
    "correct": true
  }
}

Ornith-1.5 9B

✓ pass · score 100 · 0.69 s

{"category": "feature_request", "priority": "low"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "low",
    "expected": "low",
    "correct": true
  }
}

Granite 4.2 8B

✓ pass · score 100 · 0.80 s

{"category": "feature_request", "priority": "low"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "low",
    "expected": "low",
    "correct": true
  }
}

Spark-X2.5 4B

✗ fail · score 50 · 0.49 s

{"category": "feature_request", "priority": "urgent"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "urgent",
    "expected": "low",
    "correct": false
  }
}

Mellum2.1 12B-A2.5B

✗ fail · score 50 · 0.30 s

{"category":"feature_request","priority":"urgent"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "urgent",
    "expected": "low",
    "correct": false
  }
}

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

✓ pass · score 100 · 0.25 s

{"category": "feature_request", "priority": "low"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "low",
    "expected": "low",
    "correct": true
  }
}

MiniCPM5 2B

✓ pass · score 100 · 0.40 s

{"category": "feature_request", "priority": "low"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "low",
    "expected": "low",
    "correct": true
  }
}

K2-Horizon 0.9B

✗ fail · score 50 · 0.16 s

{"category": "feature_request", "priority": "urgent"}
Scoring detail
{
  "category": {
    "got": "feature_request",
    "expected": "feature_request",
    "correct": true
  },
  "priority": {
    "got": "urgent",
    "expected": "low",
    "correct": false
  }
}

← triage-039All Sort and triage itemstriage-041 →