Claude 3 Sonnet wins more areas, narrowly.
Scores updated · 21 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 Claude 3 Sonnet pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+2.9points ahead
Where Qwen2 Instruct (72B) pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
ReasoningClaude 3 Sonnet
- GPQA DiamondClaude 3 Sonnet by 2.94037.1+2.9
- Humanity's Last Examtie3.63.7tie
Other results18 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.
- NarrativeQAQwen2 Instruct (72B) by 61.611.172.7+61.6
- naturalquestions_closedbookQwen2 Instruct (72B) by 36.22.839+36.2
- MATHQwen2 Instruct (72B) by 35.943.179+35.9
- ARC-ChallengeClaude 3 Sonnet by 24.393.268.9+24.3
- AIR-Bench 2024Claude 3 Sonnet by 22.684.762.1+22.6
- HarmBenchClaude 3 Sonnet by 1995.876.8+19
- HumanEvalQwen2 Instruct (72B) by 137386+13
- XSTestQwen2 Instruct (72B) by 11.185.896.9+11.1
- MMLU-ProQwen2 Instruct (72B) by 7.656.864.4+7.6
- bbqQwen2 Instruct (72B) by 5.19095.1+5.1
- OpenBookQAQwen2 Instruct (72B) by 3.691.895.4+3.6
- simple_safety_testsClaude 3 Sonnet by 1.510098.5+1.5
- HellaSwagClaude 3 Sonnet by 1.48987.6+1.4
- MMLUClaude 3 Sonnet by 1.478.376.9+1.4
- GSM8KClaude 3 Sonnet by 1.292.391.1+1.2
- anthropic_red_teamtie99.899.1tie
- BBHtie82.982.4tie
- AA Intelligencetie5.96.3tie
Questions people ask
Which is better, Claude 3 Sonnet or Qwen2 Instruct (72B)?
Claude 3 Sonnet wins one of the two areas where both have results: reasoning. Qwen2 Instruct (72B) wins none. They are level on coding.
Which is better for coding?
Neither. All 1 coding tests both models report are ties.
How do you compare the two?
We use the 21 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 18 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.