The two are evenly matched.
Scores updated · 17 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 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Images and chartsEven
Other results15 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 testNorth-Micro-Vision-Instruct by 14.950.435.5+14.9
- MMMU DEV_VALPhi 3.5 Vision Instruct by 10.332.943.2+10.3
- MMMU (val) (Pass@1)Phi 3.5 Vision Instruct by 10.132.943+10.1
- GQA TestDev_BalancedPhi 3.5 Vision Instruct by 7.657.465+7.6
- DocVQA-valNorth-Micro-Vision-Instruct by 6.192.186+6.1
- MMBench DEV_EN_V11Phi 3.5 Vision Instruct by 4.468.773.1+4.4
- MMMBNorth-Micro-Vision-Instruct by 4.272.868.6+4.2
- HallusionBenchNorth-Micro-Vision-Instruct by 361.558.5+3
- OCRBench v2_enNorth-Micro-Vision-Instruct by 2.836.733.9+2.8
- MMLU-Pro testNorth-Micro-Vision-Instruct by 2.130.728.6+2.1
- MTL MMBench_DEVNorth-Micro-Vision-Instruct by 1.763.661.9+1.7
- ChartQA TestPhi 3.5 Vision Instruct by 1.380.882.1+1.3
- ChartQAPhi 3.5 Vision Instruct by 180.881.8+1
- AI2Dtie77.578.1tie
- MMBench_DEVtie0.60.6tie
Questions people ask
Which is better, North-Micro-Vision-Instruct or Phi 3.5 Vision Instruct?
Neither wins more tests than the other in any of the one area where both have results.
How do you compare the two?
We use the 17 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 15 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.