Qwen3 VL 2B Instruct is the stronger all-rounder.
Scores updated · 13 tests both models report · How we compare
Where each one wins
Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Images and charts rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3 VL 2B Instruct pulls ahead
- Reads text in imagesOCRBench+1.6points ahead
Where Ministral 3 3B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 13 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsQwen3 VL 2B Instruct
- OCRBenchQwen3 VL 2B Instruct by 1.673.575.1+1.6
Other results12 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- MMMU DEV_VALMinistral 3 3B by 12.950.837.9+12.9
- ChartQA TestMinistral 3 3B by 9.879.169.3+9.8
- DocVQA-valMinistral 3 3B by 7.189.682.5+7.1
- MMBench DEV_EN_V11Qwen3 VL 2B Instruct by 5.269.274.4+5.2
- MMLU-Pro testMinistral 3 3B by 4.747.542.8+4.7
- MMLU testMinistral 3 3B by 36663+3
- GQA TestDev_BalancedQwen3 VL 2B Instruct by 2.854.457.2+2.8
- HallusionBenchQwen3 VL 2B Instruct by 2.165.267.3+2.1
- MMMBMinistral 3 3B by 1.173.472.3+1.1
- MTL MMBench_DEVMinistral 3 3B by 167.466.4+1
- OCRBench v2_entie41.441.7tie
- MMBench_DEVtie0.70.7tie
Questions people ask
Which is better, Ministral 3 3B or Qwen3 VL 2B Instruct?
Qwen3 VL 2B Instruct wins the one area where both have results: images and charts. Ministral 3 3B wins none.
How do you compare the two?
We use the 13 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 12 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.