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+14.7points ahead
Where Phi 3.5 MoE 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 14.751.536.8+14.7
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.
- MGSMLlama 3.1 Instruct 405B by 32.991.658.7+32.9
- Arena HardLlama 3.1 Instruct 405B by 31.469.337.9+31.4
- MMLU-ProLlama 3.1 Instruct 405B by 2873.345.3+28
- HumanEvalLlama 3.1 Instruct 405B by 18.38970.7+18.3
- MBPPPhi 3.5 MoE Instruct by 12.468.480.8+12.4
- GSM8KLlama 3.1 Instruct 405B by 8.196.888.7+8.1
- ARC-ChallengeLlama 3.1 Instruct 405B by 5.996.991+5.9
- HellaSwagLlama 3.1 Instruct 405B by 5.489.283.8+5.4
- OpenBookQALlama 3.1 Instruct 405B by 4.49489.6+4.4
- MMMLULlama 3.1 Instruct 405B by 3.973.869.9+3.9
- WinoGrandeLlama 3.1 Instruct 405B by 3.985.281.3+3.9
- BBHLlama 3.1 Instruct 405B by 3.882.979.1+3.8
- PIQAPhi 3.5 MoE Instruct by 2.785.988.6+2.7
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Phi 3.5 MoE Instruct?
Llama 3.1 Instruct 405B wins the one area where both have results: reasoning. Phi 3.5 MoE 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.