Unified Memory

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

vision-026

easy chart

The prompt

1 image attached (not shown).

user

In which year did this chart reach its lowest point? Reply with only the year.
What we expected
{
  "answer": "2021",
  "accept": [],
  "type": "choice",
  "options": [
    [
      "2018"
    ],
    [
      "2019"
    ],
    [
      "2020"
    ],
    [
      "2021"
    ],
    [
      "2022"
    ],
    [
      "2023"
    ],
    [
      "2024"
    ],
    [
      "2025"
    ]
  ]
}

What each model answered

LFM2.5-VL 3B

✓ pass · score 100 · 1.28 s

2021
Scoring detail
{
  "type": "choice",
  "normalized": "2021"
}

MiMo-V2.6 Distill 9B

✓ pass · score 100 · 2.18 s

2021
Scoring detail
{
  "type": "choice",
  "normalized": "2021"
}

MiniCPM-V 4.7 1B

✓ pass · score 100 · 0.97 s

2021
Scoring detail
{
  "type": "choice",
  "normalized": "2021"
}

← vision-025All Read images itemsvision-027 →