Phi 3.5 MoE Instruct is the stronger all-rounder.
Scores updated · 14 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.
Reasoning rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Phi 3.5 MoE Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.7points ahead
Where Phi 4 Mini Instruct pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 14 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningPhi 3.5 MoE Instruct
- GPQA DiamondPhi 3.5 MoE Instruct by 3.736.833.1+3.7
Other results13 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.
- HellaSwagPhi 3.5 MoE Instruct by 14.783.869.1+14.7
- WinoGrandePhi 3.5 MoE Instruct by 14.381.367+14.3
- TruthfulQAPhi 3.5 MoE Instruct by 11.177.566.4+11.1
- PIQAPhi 3.5 MoE Instruct by 1188.677.6+11
- OpenBookQAPhi 3.5 MoE Instruct by 10.489.679.2+10.4
- BBHPhi 3.5 MoE Instruct by 8.779.170.4+8.7
- MMLU-ProPhi 4 Mini Instruct by 7.545.352.8+7.5
- ARC-ChallengePhi 3.5 MoE Instruct by 7.39183.7+7.3
- Social IQAPhi 3.5 MoE Instruct by 5.57872.5+5.5
- MGSMPhi 4 Mini Instruct by 5.258.763.9+5.2
- Arena HardPhi 3.5 MoE Instruct by 5.137.932.8+5.1
- BoolQPhi 3.5 MoE Instruct by 3.484.681.2+3.4
- GSM8Ktie88.788.6tie
Questions people ask
Which is better, Phi 3.5 MoE Instruct or Phi 4 Mini Instruct?
Phi 3.5 MoE Instruct wins the one area where both have results: reasoning. Phi 4 Mini Instruct wins none.
How do you compare the two?
We use the 14 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 13 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.