Scores updated · 12 tests both models report · How we compare
Every test, side by side
All 12 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results12 tests
- NarrativeQAPalmyra-X-004 by 66.211.177.3+66.2
- naturalquestions_closedbookPalmyra-X-004 by 42.92.845.7+42.9
- AIR-Bench 2024Claude 3 Sonnet by 40.584.744.2+40.5
- MATHPalmyra-X-004 by 33.643.176.7+33.6
- HarmBenchClaude 3 Sonnet by 2295.873.8+22
- XSTestPalmyra-X-004 by 12.685.898.4+12.6
- bbqPalmyra-X-004 by 5.59095.5+5.5
- MMLUClaude 3 Sonnet by 4.478.373.9+4.4
- GSM8KClaude 3 Sonnet by 1.892.390.5+1.8
- anthropic_red_teamClaude 3 Sonnet by 1.299.898.6+1.2
- OpenBookQAtie91.892.6tie
- simple_safety_teststie100100tie
Questions people ask
How do you compare the two?
We use the 12 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.