User says Opus 5 lags Fable on tricky tasks despite still being a strong model

doodlestein · x · 2026-07-27

The author says Opus 5 is not as smart as they first thought. While it is still a good model, it seems meaningfully worse than Fable once tasks get tricky. They initially suspected context rot, but even after accounting for that, they still find Fable stronger.

The main observation is behavioral: Opus 5 often produces a long list of mistakes it made during a session, which is better than being unaware of them, but Fable seems to avoid those mistakes in the first place by thinking longer before acting.

Related event: Devs Test Opus 5: Strong Coding but Hard to Steer, Lags Fable in Complex Tasks(7 posts)→

Original post →

More from Models

Models channel →