Phi 3.5 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 3.5 Mini Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+4.7points 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 Mini Instruct
- GPQA DiamondPhi 3.5 Mini Instruct by 4.725.730.4+4.7
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.
- GSM8KPhi 3.5 Mini Instruct by 30.355.986.2+30.3
- HumanEvalPhi 3.5 Mini Instruct by 25.637.262.8+25.6
- ARC-ChallengePhi 3.5 Mini Instruct by 23.561.184.6+23.5
- TruthfulQAPhi 3.5 Mini Instruct by 19.244.864+19.2
- MBPPPhi 3.5 Mini Instruct by 1950.669.6+19
- BBHPhi 3.5 Mini Instruct by 13.955.169+13.9
- MMLU-ProPhi 3.5 Mini Instruct by 13.733.747.4+13.7
- HellaSwagGemma (7B) by 12.882.269.4+12.8
- BoolQPhi 3.5 Mini Instruct by 126678+12
- WinoGrandeGemma (7B) by 10.57968.5+10.5
- Social IQAPhi 3.5 Mini Instruct by 9.265.574.7+9.2
- PIQAPhi 3.5 Mini Instruct by 2.978.181+2.9
- OpenBookQAGemma (7B) by 1.680.879.2+1.6
Questions people ask
Which is better, Gemma (7B) or Phi 3.5 Mini Instruct?
Phi 3.5 Mini 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.