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

assistant-actions-015

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

Put a dentist appointment on my calendar for Friday at 2:30.

What we expected

{
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": {
          "type": "contains_all",
          "values": [
            "dentist"
          ]
        },
        "start": {
          "type": "datetime",
          "value": "2026-10-23T14:30:00-05:00",
          "tolerance_s": 60
        },
        "end": {
          "type": "datetime",
          "value": "2026-10-23T15:30:00-05:00",
          "tolerance_s": 60
        }
      },
      "allow_extra_args": [
        "location",
        "attendees"
      ]
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 2.82 s

add_calendar_event({"title":"Dentist appointment","start":"2026-10-23T14:30:00-05:00","end":"2026-10-23T15:30:00-05:00"})

I'll add the dentist appointment to your calendar for Friday at 2:30 PM.

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist appointment",
        "start": "2026-10-23T14:30:00-05:00",
        "end": "2026-10-23T15:30:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 1,
      "args": {
        "title": true,
        "start": true,
        "end": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Ornith-1.5 9B

✓ pass · score 100 · 2.35 s

add_calendar_event({"title":"Dentist appointment","start":"2026-10-23T14:30:00-05:00","end":"2026-10-23T15:30:00-05:00"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist appointment",
        "start": "2026-10-23T14:30:00-05:00",
        "end": "2026-10-23T15:30:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 1,
      "args": {
        "title": true,
        "start": true,
        "end": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Granite 4.2 8B

✓ pass · score 100 · 4.22 s

add_calendar_event({"title":"Dentist appointment","start":"2026-10-23T14:30:00-05:00","end":"2026-10-23T15:30:00-05:00"})

I'll add a dentist appointment to your calendar for Friday at 2:30 PM. Since you didn't specify a time zone or exact date, I'll use this coming Friday (October 23, 2026) at 2:30 PM Central Daylight Time.

Let me create the calendar event:

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist appointment",
        "start": "2026-10-23T14:30:00-05:00",
        "end": "2026-10-23T15:30:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 1,
      "args": {
        "title": true,
        "start": true,
        "end": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Spark-X2.5 4B

✓ pass · score 100 · 1.23 s

add_calendar_event({"title":"Dentist Appointment","start":"2026-10-23T14:30:00-05:00","end":"2026-10-23T15:30:00-05:00"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist Appointment",
        "start": "2026-10-23T14:30:00-05:00",
        "end": "2026-10-23T15:30:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 1,
      "args": {
        "title": true,
        "start": true,
        "end": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Mellum2.1 12B-A2.5B

✗ fail · score 0 · 8.29 s

2:30 AM or PM?

Scoring detail

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

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

✗ fail · score 67 · 0.78 s

add_calendar_event({"title":"Dentist Appointment","start":"2026-10-23T14:30:00-05:00","end":"2026-10-23T15:00:00-05:00"})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist Appointment",
        "start": "2026-10-23T14:30:00-05:00",
        "end": "2026-10-23T15:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 0.6666666666666666,
      "args": {
        "title": true,
        "start": true,
        "end": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.6666666666666666
}

MiniCPM5 2B

✗ fail · score 33 · 0.78 s

add_calendar_event({"title":"Dentist appointment","start":"2026-10-30T14:30:00-05:00","end":"2026-10-30T15:30:00-05:00","location":""})

Scoring detail

{
  "n_calls": 1,
  "calls": [
    {
      "name": "add_calendar_event",
      "args": {
        "title": "Dentist appointment",
        "start": "2026-10-30T14:30:00-05:00",
        "end": "2026-10-30T15:30:00-05:00",
        "location": ""
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "add_calendar_event",
      "matched_index": 0,
      "score": 0.3333333333333333,
      "args": {
        "title": true,
        "start": false,
        "end": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.3333333333333333
}

K2-Horizon 0.9B

✗ fail · score 0 · 0.20 s

I'll add a dentist appointment to your calendar for Friday at 2:30 PM. Let me create that for you.

Scoring detail

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

← assistant-actions-014All Assistant actions itemsassistant-actions-016 →