Unified Memory

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

assistant-actions-018

hard 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

Remind me next Friday at 4 to submit the expense report.
What we expected
{
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": {
          "type": "contains_all",
          "values": [
            "expense report"
          ]
        },
        "when": {
          "type": "datetime",
          "value": "2026-10-30T16:00:00-05:00",
          "tolerance_s": 60
        }
      },
      "allow_extra_args": []
    }
  ]
}

What each model answered

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 2.08 s

create_reminder({"text":"Submit the expense report","when":"2026-10-30T16:00:00-05:00"})
I'll set that reminder for Friday, October 30 at 4:00 PM.
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-30T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 1,
      "args": {
        "text": true,
        "when": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Ornith-1.5 9B

✗ fail · score 50 · 1.64 s

create_reminder({"text":"Submit the expense report","when":"2026-11-13T16:00:00-05:00"})
.
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-11-13T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "text": true,
        "when": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

Granite 4.2 8B

✓ pass · score 100 · 1.73 s

create_reminder({"text":"Submit the expense report","when":"2026-10-30T16:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-30T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 1,
      "args": {
        "text": true,
        "when": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Spark-X2.5 4B

✓ pass · score 100 · 0.73 s

create_reminder({"text":"Submit the expense report","when":"2026-10-30T16:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-30T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 1,
      "args": {
        "text": true,
        "when": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

Mellum2.1 12B-A2.5B

✗ fail · score 50 · 0.76 s

create_reminder({"text":"Submit the expense report","when":"2026-10-31T16:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-31T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "text": true,
        "when": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

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

✓ pass · score 100 · 0.50 s

create_reminder({"text":"Submit the expense report","when":"2026-10-30T16:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-30T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 1,
      "args": {
        "text": true,
        "when": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

MiniCPM5 2B

✓ pass · score 100 · 0.51 s

create_reminder({"text":"Submit the expense report.","when":"2026-10-30T16:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report.",
        "when": "2026-10-30T16:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 1,
      "args": {
        "text": true,
        "when": true
      }
    }
  ],
  "extra_calls": 0,
  "base": 1
}

K2-Horizon 0.9B

✗ fail · score 50 · 0.31 s

create_reminder({"text":"Submit the expense report","when":"2026-10-24T04:00:00-05:00"})
Scoring detail
{
  "n_calls": 1,
  "calls": [
    {
      "name": "create_reminder",
      "args": {
        "text": "Submit the expense report",
        "when": "2026-10-24T04:00:00-05:00"
      },
      "error": null
    }
  ],
  "per_call": [
    {
      "expected": "create_reminder",
      "matched_index": 0,
      "score": 0.5,
      "args": {
        "text": true,
        "when": false
      }
    }
  ],
  "extra_calls": 0,
  "base": 0.5
}

← assistant-actions-017All Assistant actions itemsassistant-actions-019 →