Qwen3.5 2B is the stronger all-rounder.
Scores updated · 19 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.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsQwen3.5 2B
Other results16 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.
- MMLU testQwen3.5 2B by 18.835.554.3+18.8
- OCRBench v2_enQwen3.5 2B by 14.233.948.1+14.2
- GQA TestDev_BalancedPhi 3.5 Vision Instruct by 11.16553.9+11.1
- MMBenchPhi 3.5 Vision Instruct by 8.881.973.1+8.8
- HallusionBenchQwen3.5 2B by 758.565.5+7
- DocVQA-valQwen3.5 2B by 6.68692.6+6.6
- MMMBQwen3.5 2B by 5.968.674.5+5.9
- TextVQA-valQwen3.5 2B by 5.37277.3+5.3
- MTL MMBench_DEVQwen3.5 2B by 561.966.9+5
- MMMU DEV_VALQwen3.5 2B by 4.243.247.4+4.2
- ChartQA TestPhi 3.5 Vision Instruct by 3.782.178.4+3.7
- MMBench DEV_EN_V11Qwen3.5 2B by 2.973.176+2.9
- POPEQwen3.5 2B by 2.586.188.6+2.5
- MMLU-Pro testQwen3.5 2B by 1.228.629.8+1.2
- MMMU (val) (Pass@1)Qwen3.5 2B by 1.14344.1+1.1
- MMBench_DEVtie0.60.7tie
Questions people ask
Which is better, Phi 3.5 Vision Instruct or Qwen3.5 2B?
Qwen3.5 2B wins the one area where both have results: images and charts. Phi 3.5 Vision Instruct wins none.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 16 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.