Llama 3.1 Instruct 405B vs Qwen2 Instruct (72B)
Wins 2 of 2 areas
Coding · Reasoning
Wins 0 of 2 areas
—
Llama 3.1 Instruct 405B is the stronger all-rounder.
Scores updated · 25 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas 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.
Coding 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+14.4points ahead
- Code for real scientific research problemsSciCode+7points ahead
Where Qwen2 Instruct (72B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 25 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 14.451.537.1+14.4
- Humanity's Last Examtie43.7tie
Other results22 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.
- ARC-ChallengeLlama 3.1 Instruct 405B by 2896.968.9+28
- CMMLUQwen2 Instruct (72B) by 16.473.790.1+16.4
- HarmBenchQwen2 Instruct (72B) by 14.162.776.8+14.1
- MBPPQwen2 Instruct (72B) by 11.868.480.2+11.8
- MMLULlama 3.1 Instruct 405B by 11.788.676.9+11.7
- C-EvalQwen2 Instruct (72B) by 11.372.583.8+11.3
- MMLU-ProLlama 3.1 Instruct 405B by 8.973.364.4+8.9
- naturalquestions_closedbookLlama 3.1 Instruct 405B by 6.645.639+6.6
- GSM8KLlama 3.1 Instruct 405B by 5.796.891.1+5.7
- MATHQwen2 Instruct (72B) by 5.273.879+5.2
- AIR-Bench 2024Qwen2 Instruct (72B) by 3.558.662.1+3.5
- HumanEvalLlama 3.1 Instruct 405B by 38986+3
- anthropic_red_teamQwen2 Instruct (72B) by 2.696.599.1+2.6
- NarrativeQALlama 3.1 Instruct 405B by 2.274.972.7+2.2
- HellaSwagLlama 3.1 Instruct 405B by 1.689.287.6+1.6
- OpenBookQAQwen2 Instruct (72B) by 1.49495.4+1.4
- AA IntelligenceLlama 3.1 Instruct 405B by 17.36.3+1
- XSTestQwen2 Instruct (72B) by 195.996.9+1
- bbqtie94.595.1tie
- BBHtie82.982.4tie
- simple_safety_teststie98.898.5tie
- WinoGrandetie85.285.1tie
Questions people ask
Which is better, Llama 3.1 Instruct 405B or Qwen2 Instruct (72B)?
Llama 3.1 Instruct 405B wins all two areas where both have results: coding and reasoning. Qwen2 Instruct (72B) wins none.
Which is better for coding?
Llama 3.1 Instruct 405B. It wins the one coding test both models report.
How do you compare the two?
We use the 25 benchmark tests both models have published scores on. The verdict counts the 3 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 22 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.