Unified Memory

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

vision-024

medium chart

The prompt

1 image attached (not shown).

user

Read the chart: how many minutes of exercise were logged on Thursday? Reply with only the number (no units or currency symbols).
What we expected
{
  "answer": 40,
  "accept": [],
  "type": "number"
}

What each model answered

LFM2.5-VL 3B

✓ pass · score 100 · 2.88 s

40
Scoring detail
{
  "type": "number",
  "parsed": 40
}

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 1.92 s

40
Scoring detail
{
  "type": "number",
  "parsed": 40
}

MiniCPM-V 4.7 1B

✗ fail · score 0 · 0.74 s

42
Scoring detail
{
  "type": "number",
  "parsed": 42
}

← vision-023All Read images itemsvision-025 →