Allie K. Miller says Claude leads on models and behavior, while Codex leads on features and modalities. She says she still prefers Opus 5.5, but would choose a slightly weaker model for Codex's live voice mode, computer use, and image generation.
At this point, Claude leads on models and behavior and Codex leads on features and modalities.
Opus 5.5 is still my go to.
But live voice mode and computer use and image generation are so powerful that I’d rather go for a slightly worse model and get those.
Source: Allie K. Miller · x.comPublished · added here
