Phi 3 Mini 4K Instruct is the stronger all-rounder.
Scores updated · 18 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 Mini 4K Instruct pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+7.2points ahead
Where Mistral 7B pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 18 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningPhi 3 Mini 4K Instruct
- GPQA DiamondPhi 3 Mini 4K Instruct by 7.224.731.9+7.2
Other results17 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.
- MATHPhi 3 Mini 4K Instruct by 37.513.150.6+37.5
- HumanEvalPhi 3 Mini 4K Instruct by 2829.357.3+28
- ARC-ChallengePhi 3 Mini 4K Instruct by 26.36086.3+26.3
- TruthfulQAPhi 3 Mini 4K Instruct by 22.542.264.7+22.5
- MBPPPhi 3 Mini 4K Instruct by 18.751.169.8+18.7
- TriviaQAMistral 7B by 13.875.261.4+13.8
- HellaSwagMistral 7B by 7.983.275.3+7.9
- WinoGrandeMistral 7B by 6.878.471.6+6.8
- MMLUPhi 3 Mini 4K Instruct by 6.764.270.9+6.7
- ANLIPhi 3 Mini 4K Instruct by 6.547.153.6+6.5
- MedQAPhi 3 Mini 4K Instruct by 6.55056.5+6.5
- BoolQPhi 3 Mini 4K Instruct by 5.972.278.1+5.9
- PIQAPhi 3 Mini 4K Instruct by 5.877.783.5+5.8
- Popular aggregated benchmarkPhi 3 Mini 4K Instruct by 4.656.561.1+4.6
- AGI EVALPhi 3 Mini 4K Instruct by 3.935.139+3.9
- Social IQAPhi 3 Mini 4K Instruct by 374.677.6+3
- OpenBookQAPhi 3 Mini 4K Instruct by 2.479.882.2+2.4
Questions people ask
Which is better, Mistral 7B or Phi 3 Mini 4K Instruct?
Phi 3 Mini 4K Instruct wins the one area where both have results: reasoning. Mistral 7B wins none.
How do you compare the two?
We use the 18 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 17 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.