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

assistant-actions-021

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

It's freezing in here. Heat the house to 71.

What we expected

{
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": {
          "type": "number",
          "value": 71,
          "tolerance": 0
        },
        "mode": {
          "type": "optional",
          "inner": {
            "type": "norm",
            "value": "heat"
          }
        }
      },
      "allow_extra_args": []
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✗ fail · score 50 · 0.91 s

set_thermostat({"temp_f":71,"mode":"auto"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "auto"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "temp_f": true,
        "mode": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

Ornith-1.5 9B

✓ pass · score 100 · 1.40 s

set_thermostat({"temp_f":71,"mode":"heat"})

I'll turn up the heat to 71° right now.

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Granite 4.2 8B

✓ pass · score 100 · 1.37 s

set_thermostat({"temp_f":71,"mode":"heat"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Spark-X2.5 4B

✓ pass · score 100 · 0.41 s

set_thermostat({"temp_f":71,"mode":"heat"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Mellum2.1 12B-A2.5B

✓ pass · score 100 · 0.44 s

set_thermostat({"temp_f":71})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

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

✓ pass · score 100 · 0.29 s

set_thermostat({"temp_f":71,"mode":"heat"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

MiniCPM5 2B

✓ pass · score 100 · 0.28 s

set_thermostat({"temp_f":71})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

K2-Horizon 0.9B

✓ pass · score 100 · 0.23 s

set_thermostat({"temp_f":71,"mode":"heat"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 71,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_thermostat",
      "matched_index": 0,
      "score": 1,
      "args": {
        "temp_f": true,
        "mode": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

← assistant-actions-020All Assistant actions itemsassistant-actions-022 →