Phi 3.5 Vision Instruct is the stronger all-rounder.
Scores updated · 20 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 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsPhi 3.5 Vision Instruct
Other results17 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.
- ChartQA TestPhi 3.5 Vision Instruct by 38.943.282.1+38.9
- ChartQAPhi 3.5 Vision Instruct by 38.343.581.8+38.3
- MMLU testGemma 4 E2B by 33.769.235.5+33.7
- GQA TestDev_BalancedPhi 3.5 Vision Instruct by 26.338.765+26.3
- MMBenchPhi 3.5 Vision Instruct by 19.162.881.9+19.1
- MMLU-Pro testGemma 4 E2B by 15.544.128.6+15.5
- OCRBench v2_enGemma 4 E2B by 9.643.533.9+9.6
- TextVQA-valPhi 3.5 Vision Instruct by 9.562.572+9.5
- MMMBGemma 4 E2B by 5.774.368.6+5.7
- MMMU DEV_VALGemma 4 E2B by 4.547.743.2+4.5
- MMBench DEV_EN_V11Phi 3.5 Vision Instruct by 3.869.373.1+3.8
- MTL MMBench_DEVGemma 4 E2B by 2.964.861.9+2.9
- POPEPhi 3.5 Vision Instruct by 2.18486.1+2.1
- MMMU (val) (Pass@1)Phi 3.5 Vision Instruct by 1.941.143+1.9
- HallusionBenchGemma 4 E2B by 1.359.858.5+1.3
- DocVQA-valtie85.786tie
- MMBench_DEVtie0.60.6tie
Questions people ask
Which is better, Gemma 4 E2B or Phi 3.5 Vision Instruct?
Phi 3.5 Vision Instruct wins the one area where both have results: images and charts. Gemma 4 E2B wins none.
How do you compare the two?
We use the 20 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 17 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.