Unified Memory

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

assistant-actions-010

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

Wake me up at 6:15 tomorrow morning.
What we expected
{
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": {
          "type": "clock",
          "value": "06:15"
        }
      },
      "allow_extra_args": [
        "label"
      ]
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 1.35 s

set_alarm({"time":"06:15","label":"Wake up"})
I'll set a wake-up alarm for 6:15 AM tomorrow.
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "Wake up"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Ornith-1.5 9B

✓ pass · score 100 · 1.27 s

set_alarm({"time":"06:15"})
I'll set that alarm for 6:15 AM tomorrow (Thursday, October 22).
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Granite 4.2 8B

✓ pass · score 100 · 1.35 s

set_alarm({"time":"06:15","label":"wake up"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "wake up"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Spark-X2.5 4B

✓ pass · score 100 · 0.41 s

set_alarm({"time":"06:15","label":"tomorrow"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "tomorrow"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Mellum2.1 12B-A2.5B

✓ pass · score 100 · 0.50 s

set_alarm({"time":"06:15","label":"morning"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "morning"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

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

✗ fail · score 0 · 0.57 s

create_reminder({"text":"Wake up at 6:15 AM tomorrow morning.","when":"2026-10-22T06:15:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Wake up at 6:15 AM tomorrow morning.",
        "when": "2026-10-22T06:15:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 0,
      "args": {
        "name": "mismatch"
      }
    }
  ],
  "extra_calls": 0,
  "base": 0
}

MiniCPM5 2B

✓ pass · score 100 · 0.34 s

set_alarm({"time":"06:15","label":"morning"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "morning"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

K2-Horizon 0.9B

✓ pass · score 100 · 0.24 s

set_alarm({"time":"06:15","label":"Wake me up"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "set_alarm",
      "args": {
        "time": "06:15",
        "label": "Wake me up"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "set_alarm",
      "matched_index": 0,
      "score": 1,
      "args": {
        "time": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

← assistant-actions-009All Assistant actions itemsassistant-actions-011 →