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
- GSM8KDBRX Instruct by 29.467.137.7+29.4
- NarrativeQAMistral V0.1 (7B) by 22.848.871.6+22.8
- bbqDBRX Instruct by 22.779.256.5+22.7
- OpenBookQADBRX Instruct by 13.49177.6+13.4
- simple_safety_testsDBRX Instruct by 10.253.543.3+10.2
- XSTestDBRX Instruct by 8.777.468.7+8.7
- naturalquestions_closedbookMistral V0.1 (7B) by 8.328.436.7+8.3
- MATHDBRX Instruct by 6.135.829.7+6.1
- MMLUDBRX Instruct by 5.964.358.4+5.9
- anthropic_red_teamDBRX Instruct by 5.576.671+5.5
- HarmBenchDBRX Instruct by 3.827.123.3+3.8
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.