Unified Memory

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

vision-028

easy calendar

The prompt

1 image attached (not shown).

user

What time does the Dentist appointment start? Reply with only the time, for example 3:15 PM.
What we expected
{
  "answer": "15:30",
  "accept": [],
  "type": "time"
}

What each model answered

LFM2.5-VL 3B

✓ pass · score 100 · 2.92 s

3:30 PM
Scoring detail
{
  "type": "time",
  "parsed": "15:30",
  "explicit_ampm_or_24h": true
}

MiMo-V2.6 Distill 9B

✗ fail · score 0 · 3.78 s

4:30 PM
Scoring detail
{
  "type": "time",
  "parsed": "16:30",
  "explicit_ampm_or_24h": true
}

MiniCPM-V 4.7 1B

✓ pass · score 100 · 1.81 s

3:30 - 4:30
Scoring detail
{
  "type": "time",
  "parsed": "03:30",
  "explicit_ampm_or_24h": false
}

← vision-027All Read images itemsvision-029 →