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+12.1points ahead
Where Mistral 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 12.124.736.8+12.1
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 41.429.370.7+41.4
- GSM8KPhi 3.5 MoE Instruct by 36.552.288.7+36.5
- TruthfulQAPhi 3.5 MoE Instruct by 35.342.277.5+35.3
- ARC-ChallengePhi 3.5 MoE Instruct by 316091+31
- MBPPPhi 3.5 MoE Instruct by 29.751.180.8+29.7
- BBHPhi 3.5 MoE Instruct by 2356.179.1+23
- MMLU-ProPhi 3.5 MoE Instruct by 14.430.945.3+14.4
- BoolQPhi 3.5 MoE Instruct by 12.472.284.6+12.4
- PIQAPhi 3.5 MoE Instruct by 10.977.788.6+10.9
- OpenBookQAPhi 3.5 MoE Instruct by 9.879.889.6+9.8
- Social IQAPhi 3.5 MoE Instruct by 3.474.678+3.4
- WinoGrandePhi 3.5 MoE Instruct by 2.978.481.3+2.9
- HellaSwagtie83.283.8tie
Questions people ask
Which is better, Mistral 7B or Phi 3.5 MoE Instruct?
Phi 3.5 MoE Instruct wins the one area where both have results: reasoning. Mistral 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.