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

assistant-actions-033

hard multi

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

ok good night. bedroom lights off, alarm for 6:45 am, and drop the thermostat to 66

What we expected

{
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": {
          "type": "norm",
          "value": "bedroom"
        },
        "state": {
          "type": "norm",
          "value": "off"
        }
      },
      "allow_extra_args": [
        "brightness"
      ]
    },
    {
      "name": "set_alarm",
      "args": {
        "time": {
          "type": "clock",
          "value": "06:45"
        }
      },
      "allow_extra_args": [
        "label"
      ]
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": {
          "type": "number",
          "value": 66,
          "tolerance": 0
        }
      },
      "allow_extra_args": [
        "mode"
      ]
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 2.27 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45"})
set_thermostat({"temp_f":66})

I'll take care of those three for you.

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Ornith-1.5 9B

✓ pass · score 100 · 2.58 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45"})
set_thermostat({"temp_f":66})

I'll take care of all three right away.

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Granite 4.2 8B

✗ fail · score 33 · 1.38 s

control_light({"room":"bedroom","state":"off"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": null,
      "score": 0,
      "args": "no call"
    },
    {
      "expected": "set_thermostat",
      "matched_index": null,
      "score": 0,
      "args": "no call"
    }
  ],
  "extra_calls": 0,
  "base": 0.3333333333333333
}

Spark-X2.5 4B

✓ pass · score 100 · 0.93 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45","label":"bedroom wake"})
set_thermostat({"temp_f":66})

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45",
        "label": "bedroom wake"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Mellum2.1 12B-A2.5B

✗ fail · score 33 · 0.42 s

control_light({"room":"bedroom","state":"off"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": null,
      "score": 0,
      "args": "no call"
    },
    {
      "expected": "set_thermostat",
      "matched_index": null,
      "score": 0,
      "args": "no call"
    }
  ],
  "extra_calls": 0,
  "base": 0.3333333333333333
}

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

✓ pass · score 100 · 0.73 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45","label":"Wake up"})
set_thermostat({"temp_f":66,"mode":"heat"})

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45",
        "label": "Wake up"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66,
        "mode": "heat"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

MiniCPM5 2B

✓ pass · score 100 · 0.80 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45","label":"good night"})
set_thermostat({"temp_f":66})

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45",
        "label": "good night"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

K2-Horizon 0.9B

✓ pass · score 100 · 0.49 s

control_light({"room":"bedroom","state":"off"})
set_alarm({"time":"06:45","label":"alarm"})
set_thermostat({"temp_f":66,"mode":"auto"})

Scoring detail

{
  "n_calls": 3,
  "calls": [
    {
      "name": "control_light",
      "args": {
        "room": "bedroom",
        "state": "off"
      },
      "error": null
    },
    {
      "name": "set_alarm",
      "args": {
        "time": "06:45",
        "label": "alarm"
      },
      "error": null
    },
    {
      "name": "set_thermostat",
      "args": {
        "temp_f": 66,
        "mode": "auto"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "control_light",
      "matched_index": 0,
      "score": 1,
      "args": {
        "room": true,
        "state": true
      }
    },
    {
      "expected": "set_alarm",
      "matched_index": 1,
      "score": 1,
      "args": {
        "time": true
      }
    },
    {
      "expected": "set_thermostat",
      "matched_index": 2,
      "score": 1,
      "args": {
        "temp_f": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

← assistant-actions-032All Assistant actions itemsassistant-actions-034 →