Users say Opus 5 breaks things, while Opus 4.8 still feels strong

omarsar0 · x · 2026-07-28

A user compares Anthropic models and says:

The post is a short but concrete qualitative take on model behavior and reliability, not just a generic ranking.

Related event: Claude Opus 5 Hands-on: Impressive Single-Prompt Generation, but Lags Behind Fable in Complex Tasks(24 posts)→

Original post →

More from Models

Models channel →