I tested Opus 4.5's front-end capabilities and found it to be significantly superior to CodeX's GPT 5.1, although it couldn't match CodeX in terms of strong logic. If you factor in the price... then it can't compare to Codex. Also, I tried Sonnet 4.5, and it still can't compare to GPT 5.1 or CodeX Max... I don't know why so many people say 4.5 is very powerful; personally, when I used 4.5, I felt its capabilities were inferior to Opus 4.0.
Loading thread detail
Fetching the original tweets from X for a clean reading view.
Hang tight—this usually only takes a few seconds.