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
- HarmBenchPalmyra-X-004 by 46.727.173.8+46.7
- simple_safety_testsPalmyra-X-004 by 46.553.5100+46.5
- MATHPalmyra-X-004 by 40.935.876.7+40.9
- NarrativeQAPalmyra-X-004 by 28.548.877.3+28.5
- GSM8KPalmyra-X-004 by 23.467.190.5+23.4
- anthropic_red_teamPalmyra-X-004 by 2276.698.6+22
- XSTestPalmyra-X-004 by 2177.498.4+21
- AIR-Bench 2024Palmyra-X-004 by 18.825.444.2+18.8
- naturalquestions_closedbookPalmyra-X-004 by 17.328.445.7+17.3
- bbqPalmyra-X-004 by 16.379.295.5+16.3
- MMLUPalmyra-X-004 by 9.664.373.9+9.6
- OpenBookQAPalmyra-X-004 by 1.69192.6+1.6
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.