Scores updated · 11 tests both models report · How we compare
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results11 tests
- NarrativeQAQwen2.5 Instruct Turbo (7B) by 63.111.174.2+63.1
- AIR-Bench 2024Claude 3 Sonnet by 37.784.747+37.7
- HarmBenchClaude 3 Sonnet by 28.195.867.7+28.1
- naturalquestions_closedbookQwen2.5 Instruct Turbo (7B) by 17.72.820.5+17.7
- MMLUClaude 3 Sonnet by 12.578.365.8+12.5
- XSTestQwen2.5 Instruct Turbo (7B) by 10.885.896.6+10.8
- GSM8KClaude 3 Sonnet by 9.392.383+9.3
- OpenBookQAClaude 3 Sonnet by 5.691.886.2+5.6
- simple_safety_testsClaude 3 Sonnet by 410096+4
- anthropic_red_teamClaude 3 Sonnet by 1.399.898.5+1.3
- bbqtie9090.6tie
Questions people ask
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.