Llama 3.1 Instruct 405B 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 Llama 3.1 Instruct 405B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+21.1points 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.
ReasoningLlama 3.1 Instruct 405B
- GPQA DiamondLlama 3.1 Instruct 405B by 21.151.530.4+21.1
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.
- MGSMLlama 3.1 Instruct 405B by 43.791.647.9+43.7
- Arena HardLlama 3.1 Instruct 405B by 32.369.337+32.3
- HumanEvalLlama 3.1 Instruct 405B by 26.28962.8+26.2
- MMLU-ProLlama 3.1 Instruct 405B by 25.973.347.4+25.9
- HellaSwagLlama 3.1 Instruct 405B by 19.889.269.4+19.8
- MMMLULlama 3.1 Instruct 405B by 18.473.855.4+18.4
- WinoGrandeLlama 3.1 Instruct 405B by 16.785.268.5+16.7
- OpenBookQALlama 3.1 Instruct 405B by 14.89479.2+14.8
- BBHLlama 3.1 Instruct 405B by 13.982.969+13.9
- ARC-ChallengeLlama 3.1 Instruct 405B by 12.396.984.6+12.3
- GSM8KLlama 3.1 Instruct 405B by 10.696.886.2+10.6
- PIQALlama 3.1 Instruct 405B by 4.985.981+4.9
- MBPPPhi 3.5 Mini Instruct by 1.268.469.6+1.2
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Phi 3.5 Mini Instruct?
Llama 3.1 Instruct 405B 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.