SWE-bench will hit 90% this year

1 comments

• upmind 1 hour ago
  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
  [-]
  • amazingamazing 1 hour ago
    I use both and think they’re comparable. AMA.
  • lern_too_spel 44 minutes ago
    Gemini at the same level as Claude is believable. Gemini CLI is not at the same level as Claude Code.