SWE-bench will hit 90% this year
fabraix.com
1 thread
Maybe unpopular opinion but I think at this point SWE-Bench has done its part and we need a new benchmark because Gemini being on/near the same level as Claude is obviously wrong
Gemini at the same level as Claude is believable. Gemini CLI is not at the same level as Claude Code.
I use both and think they’re comparable. AMA.
Not sure which version of Gemini are you using but Claude is so much better for me. Gemini is generally overeager to make a code change even when I am just asking conceptual questions, among other issues.