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 →