Benchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Assistant actions
assistant-actions-026
medium 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
Add eggs, butter and flour to the grocery list.
What we expected
{
"calls": [
{
"name": "add_to_list",
"args": {
"list": {
"type": "norm",
"value": "grocery"
},
"item": {
"type": "contains_all",
"values": [
"eggs"
]
}
},
"allow_extra_args": []
},
{
"name": "add_to_list",
"args": {
"list": {
"type": "norm",
"value": "grocery"
},
"item": {
"type": "contains_all",
"values": [
"butter"
]
}
},
"allow_extra_args": []
},
{
"name": "add_to_list",
"args": {
"list": {
"type": "norm",
"value": "grocery"
},
"item": {
"type": "contains_all",
"values": [
"flour"
]
}
},
"allow_extra_args": []
}
]
}What each model answered
MiMo-V2.6 Distill 9B
✓ pass · score 100 · 2.20 s
add_to_list({"list":"grocery","item":"eggs"})
add_to_list({"list":"grocery","item":"butter"})
add_to_list({"list":"grocery","item":"flour"})Scoring detail
{
"n_calls": 3,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "butter"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "flour"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 1,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 2,
"score": 1,
"args": {
"list": true,
"item": true
}
}
],
"extra_calls": 0,
"base": 1
}Ornith-1.5 9B
✓ pass · score 100 · 2.99 s
add_to_list({"list":"grocery","item":"eggs"})
add_to_list({"list":"grocery","item":"butter"})
add_to_list({"list":"grocery","item":"flour"})I'll add those to your grocery list.
Scoring detail
{
"n_calls": 3,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "butter"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "flour"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 1,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 2,
"score": 1,
"args": {
"list": true,
"item": true
}
}
],
"extra_calls": 0,
"base": 1
}Granite 4.2 8B
✗ fail · score 33 · 1.42 s
add_to_list({"list":"grocery","item":"eggs"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
}
],
"extra_calls": 0,
"base": 0.3333333333333333
}Spark-X2.5 4B
✓ pass · score 100 · 0.98 s
add_to_list({"list":"grocery","item":"eggs"})
add_to_list({"list":"grocery","item":"butter"})
add_to_list({"list":"grocery","item":"flour"})Scoring detail
{
"n_calls": 3,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "butter"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "flour"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 1,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 2,
"score": 1,
"args": {
"list": true,
"item": true
}
}
],
"extra_calls": 0,
"base": 1
}Mellum2.1 12B-A2.5B
✗ fail · score 33 · 0.46 s
add_to_list({"list":"grocery","item":"eggs"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
},
{
"expected": "add_to_list",
"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 · 0.71 s
add_to_list({"list":"grocery","item":"eggs"})
add_to_list({"list":"grocery","item":"butter"})
add_to_list({"list":"grocery","item":"flour"})Scoring detail
{
"n_calls": 3,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "butter"
},
"error": null
},
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "flour"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 1,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": 2,
"score": 1,
"args": {
"list": true,
"item": true
}
}
],
"extra_calls": 0,
"base": 1
}MiniCPM5 2B
✗ fail · score 33 · 0.36 s
add_to_list({"list":"grocery","item":"eggs, butter, flour"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs, butter, flour"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
},
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
}
],
"extra_calls": 0,
"base": 0.3333333333333333
}K2-Horizon 0.9B
✗ fail · score 33 · 0.23 s
add_to_list({"list":"grocery","item":"eggs"})Scoring detail
{
"n_calls": 1,
"calls": [
{
"name": "add_to_list",
"args": {
"list": "grocery",
"item": "eggs"
},
"error": null
}
],
"per_call": [
{
"expected": "add_to_list",
"matched_index": 0,
"score": 1,
"args": {
"list": true,
"item": true
}
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
},
{
"expected": "add_to_list",
"matched_index": null,
"score": 0,
"args": "no call"
}
],
"extra_calls": 0,
"base": 0.3333333333333333
}← assistant-actions-025All Assistant actions itemsassistant-actions-027 →