Qwen2 72B is the stronger all-rounder.
Scores updated · 17 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 Qwen2 72B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+1.6points ahead
Where Llama 3 (70B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 17 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results16 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.
- C-EvalQwen2 72B by 25.865.291+25.8
- CMMLUQwen2 72B by 22.967.290.1+22.9
- HumanEvalQwen2 72B by 16.448.264.6+16.4
- MATHLlama 3 (70B) by 15.266.351.1+15.2
- MMLUQwen2 72B by 14.769.584.2+14.7
- MultiPL-EQwen2 72B by 13.346.359.6+13.3
- Theorem QAQwen2 72B by 10.832.343.1+10.8
- EvalPlusQwen2 72B by 10.654.865.4+10.6
- TruthfulQAQwen2 72B by 9.245.654.8+9.2
- GSM8KQwen2 72B by 980.589.5+9
- Multi-MathematicsQwen2 72B by 8.967.176+8.9
- MBPPQwen2 72B by 6.570.476.9+6.5
- MMLU-ProQwen2 72B by 2.852.855.6+2.8
- BBHQwen2 72B by 1.48182.4+1.4
- HellaSwagtie8887.6tie
- ARC-Challengetie68.868.9tie
Questions people ask
Which is better, Llama 3 (70B) or Qwen2 72B?
Qwen2 72B wins the one area where both have results: reasoning. Llama 3 (70B) wins none.
How do you compare the two?
We use the 17 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 16 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.