Qwen2.5 Instruct 72B is the stronger all-rounder.
Scores updated · 16 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.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen2.5 Instruct 72B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+12.8points ahead
Where Llama 3 (70B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 16 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningQwen2.5 Instruct 72B
- GPQA DiamondQwen2.5 Instruct 72B by 12.836.349.1+12.8
Other results15 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.
- HumanEvalQwen2.5 Instruct 72B by 38.448.286.6+38.4
- MultiPL-EQwen2.5 Instruct 72B by 28.846.375.1+28.8
- ARC-ChallengeQwen2.5 Instruct 72B by 25.768.894.5+25.7
- C-EvalQwen2.5 Instruct 72B by 2465.289.2+24
- CMMLUQwen2.5 Instruct 72B by 22.367.289.5+22.3
- MATHQwen2.5 Instruct 72B by 22.166.388.4+22.1
- MMLU-ProQwen2.5 Instruct 72B by 18.352.871.1+18.3
- MBPPQwen2.5 Instruct 72B by 17.870.488.2+17.8
- GSM8KQwen2.5 Instruct 72B by 15.380.595.8+15.3
- naturalquestions_closedbookLlama 3 (70B) by 11.647.535.9+11.6
- MMLUQwen2.5 Instruct 72B by 7.569.577+7.5
- NarrativeQALlama 3 (70B) by 5.379.874.5+5.3
- HellaSwagLlama 3 (70B) by 3.28884.8+3.2
- OpenBookQAQwen2.5 Instruct 72B by 2.893.496.2+2.8
- BBHLlama 3 (70B) by 1.28179.8+1.2
Questions people ask
Which is better, Llama 3 (70B) or Qwen2.5 Instruct 72B?
Qwen2.5 Instruct 72B wins the one area where both have results: reasoning. Llama 3 (70B) wins none.
How do you compare the two?
We use the 16 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 15 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.