Phi 4 Mini 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 4 Mini Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.7points ahead
Where Phi 3.5 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 4 Mini Instruct
- GPQA DiamondPhi 4 Mini Instruct by 2.730.433.1+2.7
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.
- MGSMPhi 4 Mini Instruct by 1647.963.9+16
- MMLU-ProPhi 4 Mini Instruct by 5.447.452.8+5.4
- Arena HardPhi 3.5 Mini Instruct by 4.23732.8+4.2
- PIQAPhi 3.5 Mini Instruct by 3.48177.6+3.4
- BoolQPhi 4 Mini Instruct by 3.27881.2+3.2
- GSM8KPhi 4 Mini Instruct by 2.486.288.6+2.4
- TruthfulQAPhi 4 Mini Instruct by 2.46466.4+2.4
- Social IQAPhi 3.5 Mini Instruct by 2.274.772.5+2.2
- WinoGrandePhi 3.5 Mini Instruct by 1.568.567+1.5
- BBHPhi 4 Mini Instruct by 1.46970.4+1.4
- ARC-Challengetie84.683.7tie
- HellaSwagtie69.469.1tie
- OpenBookQAtie79.279.2tie
Questions people ask
Which is better, Phi 3.5 Mini Instruct or Phi 4 Mini Instruct?
Phi 4 Mini Instruct wins the one area where both have results: reasoning. Phi 3.5 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.