Benchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Assistant actions
assistant-actions-025
easy 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
Lock the garage and turn on the porch light.
What we expected
{
"calls": [
{
"name": "lock_door",
"args": {
"door": {
"type": "norm",
"value": "garage"
}
},
"allow_extra_args": []
},
{
"name": "control_light",
"args": {
"room": {
"type": "norm",
"value": "porch"
},
"state": {
"type": "norm",
"value": "on"
}
},
"allow_extra_args": [
"brightness"
]
}
]
}What each model answered
MiMo-V2.6 Distill 9B
✓ pass · score 100 · 1.36 s
lock_door({"door":"garage"})
control_light({"room":"porch","state":"on"})Scoring detail
{
"n_calls": 2,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "control_light",
"args": {
"room": "porch",
"state": "on"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 1,
"args": {
"room": true,
"state": true
}
}
],
"extra_calls": 0,
"base": 1
}Ornith-1.5 9B
✓ pass · score 100 · 1.67 s
lock_door({"door":"garage"})
control_light({"room":"porch","state":"on"})Scoring detail
{
"n_calls": 2,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "control_light",
"args": {
"room": "porch",
"state": "on"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 1,
"args": {
"room": true,
"state": true
}
}
],
"extra_calls": 0,
"base": 1
}Granite 4.2 8B
✗ fail · score 50 · 1.02 s
lock_door({"door":"garage"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": null,
"score": 0,
"args": "no call"
}
],
"extra_calls": 0,
"base": 0.5
}Spark-X2.5 4B
✓ pass · score 100 · 0.52 s
lock_door({"door":"garage"})
control_light({"room":"porch","state":"on"})Scoring detail
{
"n_calls": 2,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "control_light",
"args": {
"room": "porch",
"state": "on"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 1,
"args": {
"room": true,
"state": true
}
}
],
"extra_calls": 0,
"base": 1
}Mellum2.1 12B-A2.5B
✗ fail · score 50 · 0.37 s
lock_door({"door":"garage"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": null,
"score": 0,
"args": "no call"
}
],
"extra_calls": 0,
"base": 0.5
}Ling-3.0-tiny (7.9B-A1.3B)
✓ pass · score 100 · 0.40 s
lock_door({"door":"garage"})
control_light({"room":"porch","state":"on"})Scoring detail
{
"n_calls": 2,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "control_light",
"args": {
"room": "porch",
"state": "on"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 1,
"args": {
"room": true,
"state": true
}
}
],
"extra_calls": 0,
"base": 1
}MiniCPM5 2B
✓ pass · score 100 · 0.48 s
lock_door({"door":"garage"})
control_light({"room":"porch","state":"on"})Scoring detail
{
"n_calls": 2,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "control_light",
"args": {
"room": "porch",
"state": "on"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 1,
"args": {
"room": true,
"state": true
}
}
],
"extra_calls": 0,
"base": 1
}K2-Horizon 0.9B
✗ fail · score 33 · 0.44 s
lock_door({"door":"garage"})
set_alarm({"time":"06:30","label":"Garage Lock"})
set_thermostat({"temp_f":72,"mode":"auto"})Scoring detail
{
"n_calls": 3,
"calls": [
{
"name": "lock_door",
"args": {
"door": "garage"
},
"error": null
},
{
"name": "set_alarm",
"args": {
"time": "06:30",
"label": "Garage Lock"
},
"error": null
},
{
"name": "set_thermostat",
"args": {
"temp_f": 72,
"mode": "auto"
},
"error": null
}
],
"per_call": [
{
"expected": "lock_door",
"matched_index": 0,
"score": 1,
"args": {
"door": true
}
},
{
"expected": "control_light",
"matched_index": 1,
"score": 0,
"args": {
"name": "mismatch"
}
}
],
"extra_calls": 1,
"base": 0.5
}← assistant-actions-024All Assistant actions itemsassistant-actions-026 →