3 points | by ryanmerket 12 hours ago ago
2 comments
Both models returned a fully functional result. The only Kimi downside was it added markdown where it was asked to only return the code text.
So the real headline should be more like “Kimi is more verbose than Muse”
Muse won all but one test where they tied
Both models returned a fully functional result. The only Kimi downside was it added markdown where it was asked to only return the code text.
So the real headline should be more like “Kimi is more verbose than Muse”
Muse won all but one test where they tied