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+11.1points ahead
Where Gemma (7B) 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 11.125.736.8+11.1
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.
- HumanEvalPhi 3.5 MoE Instruct by 33.537.270.7+33.5
- GSM8KPhi 3.5 MoE Instruct by 32.855.988.7+32.8
- TruthfulQAPhi 3.5 MoE Instruct by 32.744.877.5+32.7
- MBPPPhi 3.5 MoE Instruct by 30.250.680.8+30.2
- ARC-ChallengePhi 3.5 MoE Instruct by 29.961.191+29.9
- BBHPhi 3.5 MoE Instruct by 2455.179.1+24
- BoolQPhi 3.5 MoE Instruct by 18.66684.6+18.6
- Social IQAPhi 3.5 MoE Instruct by 12.565.578+12.5
- MMLU-ProPhi 3.5 MoE Instruct by 11.633.745.3+11.6
- PIQAPhi 3.5 MoE Instruct by 10.578.188.6+10.5
- OpenBookQAPhi 3.5 MoE Instruct by 8.880.889.6+8.8
- WinoGrandePhi 3.5 MoE Instruct by 2.37981.3+2.3
- HellaSwagPhi 3.5 MoE Instruct by 1.682.283.8+1.6
Questions people ask
Which is better, Gemma (7B) or Phi 3.5 MoE Instruct?
Phi 3.5 MoE Instruct wins the one area where both have results: reasoning. Gemma (7B) 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.