Unified MemoryBenchmarks / Which Small AI Model Should You Run on a Mac? We Ran 312 Tests / Read images
vision-022
hard boarding_passphoto
The prompt
1 image attached (not shown).
user
What seat is this passenger assigned? Reply with only the answer, no other words.
What we expected
{
"answer": "31B",
"accept": [],
"type": "text",
"match": "alnum"
}What each model answered
LFM2.5-VL 3B
✓ pass · score 100 · 0.48 s
31B
Scoring detail
{
"type": "text",
"compact": "31b"
}MiMo-V2.6 Distill 9B
✓ pass · score 100 · 1.50 s
31B
Scoring detail
{
"type": "text",
"compact": "31b"
}MiniCPM-V 4.7 1B
✓ pass · score 100 · 0.96 s
31B
Scoring detail
{
"type": "text",
"compact": "31b"
}