Press Space to continue
Model performance shifts too rapidly to commit to one AI provider
Press Space to continue
there is no sense in using Claude or Codex one day Claude has best model next day Codex has best model go use any agent platform that allows you to switch between both super easily without losing your context building and using https://squad.so for this reason
Theo - t3.gg@theoSep 29
When I made this video, there were no benchmarks yet, so I had to run them myself. Jaw dropped when I saw the Terminal Bench 4 scores. Performance better than Opus 5.5 for ~1/30th of the price 🤯 https://x.com/theo/status/2105000888192663582/photo/1
open on x · 5 views · 1 clickViews and clicks count once per visitor per day. Clicks are opens of this post on X.