Unified MemoryBenchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Read images
vision-014
medium parking_signreasoning
The prompt
1 image attached (not shown).
user
These signs are posted together on one pole. Can I park here at 8:00 AM on a Tuesday? Reply with only Yes or No.
What we expected
{
"answer": "no",
"accept": [],
"type": "yes_no"
}What each model answered
LFM2.5-VL 3B
✓ pass · score 100 · 2.88 s
No
Scoring detail
{
"type": "yes_no",
"first_token": "no"
}MiMo-V2.6 Distill 9B
✗ fail · score 0 · 1.94 s
Yes
Scoring detail
{
"type": "yes_no",
"first_token": "yes"
}MiniCPM-V 4.7 1B
✓ pass · score 100 · 1.32 s
No.
Scoring detail
{
"type": "yes_no",
"first_token": "no"
}