Qwen2.5 Instruct 72B 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.
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+12.3points 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.
ReasoningQwen2.5 Instruct 72B
- GPQA DiamondQwen2.5 Instruct 72B by 12.336.849.1+12.3
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.
- Arena HardQwen2.5 Instruct 72B by 43.337.981.2+43.3
- MMLU-ProQwen2.5 Instruct 72B by 25.845.371.1+25.8
- MGSMQwen2.5 Instruct 72B by 17.558.776.2+17.5
- HumanEvalQwen2.5 Instruct 72B by 15.970.786.6+15.9
- MBPPQwen2.5 Instruct 72B by 7.480.888.2+7.4
- GSM8KQwen2.5 Instruct 72B by 7.188.795.8+7.1
- OpenBookQAQwen2.5 Instruct 72B by 6.689.696.2+6.6
- PIQAPhi 3.5 MoE Instruct by 688.682.6+6
- MMMLUQwen2.5 Instruct 72B by 4.969.974.8+4.9
- ARC-ChallengeQwen2.5 Instruct 72B by 3.59194.5+3.5
- HellaSwagQwen2.5 Instruct 72B by 183.884.8+1
- WinoGrandeQwen2.5 Instruct 72B by 181.382.3+1
- BBHtie79.179.8tie
Questions people ask
Which is better, Phi 3.5 MoE Instruct or Qwen2.5 Instruct 72B?
Qwen2.5 Instruct 72B 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.