The two are evenly matched.
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.
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.
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.
- MATHQwen2 Instruct (72B) by 27.951.179+27.9
- HumanEvalQwen2 Instruct (72B) by 21.464.686+21.4
- EvalPlusQwen2 Instruct (72B) by 13.665.479+13.6
- MultiPL-EQwen2 Instruct (72B) by 9.659.669.2+9.6
- MMLU-ProQwen2 Instruct (72B) by 8.855.664.4+8.8
- MMLUQwen2 72B by 7.384.276.9+7.3
- C-EvalQwen2 72B by 7.29183.8+7.2
- MBPPQwen2 Instruct (72B) by 3.376.980.2+3.3
- GSM8KQwen2 Instruct (72B) by 1.689.591.1+1.6
- Theorem QAQwen2 Instruct (72B) by 1.343.144.4+1.3
- ARC-Challengetie68.968.9tie
- BBHtie82.482.4tie
- CMMLUtie90.190.1tie
- HellaSwagtie87.687.6tie
- TruthfulQAtie54.854.8tie
Questions people ask
Which is better, Qwen2 72B or Qwen2 Instruct (72B)?
Neither wins more tests than the other in any of the one area where both have results.
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.