Benchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Assistant actions

assistant-actions-016

medium single

The prompt

Tools offered: create_reminder, add_calendar_event, set_timer, set_alarm, control_light, set_thermostat, lock_door, send_message, play_music, get_weather, add_to_list, navigate_to

user

What's the forecast for Lake Wendell, WI on Sunday?

What we expected

{
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": {
          "type": "contains_all",
          "values": [
            "lake wendell"
          ]
        },
        "date": {
          "type": "date",
          "value": "2026-10-25"
        }
      },
      "allow_extra_args": []
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 1.17 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-25"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-25"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 1,
      "args": {
        "location": true,
        "date": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Ornith-1.5 9B

✓ pass · score 100 · 1.26 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-25"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-25"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 1,
      "args": {
        "location": true,
        "date": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Granite 4.2 8B

✓ pass · score 100 · 1.51 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-25"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-25"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 1,
      "args": {
        "location": true,
        "date": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Spark-X2.5 4B

✗ fail · score 50 · 0.55 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-24"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-24"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "location": true,
        "date": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

Mellum2.1 12B-A2.5B

✗ fail · score 50 · 0.59 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-26"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-26"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "location": true,
        "date": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

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

✓ pass · score 100 · 0.38 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-25"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-25"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 1,
      "args": {
        "location": true,
        "date": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

MiniCPM5 2B

✗ fail · score 50 · 0.40 s

get_weather({"location":"Lake Wendell, WI","date":"2026-10-24"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "get_weather",
      "args": {
        "location": "Lake Wendell, WI",
        "date": "2026-10-24"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "get_weather",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "location": true,
        "date": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

K2-Horizon 0.9B

✗ fail · score 0 · 0.16 s

I'll get the weather forecast for Lake Wendell, WI for Sunday.

Scoring detail

{
  "n_calls": 0,
  "calls": [],
  "reason": "no tool calls"
}

← assistant-actions-015All Assistant actions itemsassistant-actions-017 →