User reports Anthropic Opus 5 and Sonnet 5 feel like legitimate regressions
bindureddy · x · 2026-08-23
Users report that Anthropic's latest generation models, Opus 5 and Sonnet 5, feel like legitimate regressions. Issues include excessive spinning, higher costs, and a lack of noticeable quality gains. In contrast, the previous Opus 4.8 and Sonnet 4.6 are considered the best models currently available.
Related event: Users Report Anthropic's Opus 5 and Sonnet 5 as a Regression(6 posts)→
More from Models
- 80% of Tasks Don't Need Expensive Models: A Task-to-Model Guide — bindureddy · 2026-08-24
- User Test: Opus 5 Suffers from Severe Long-Context Failure — ATTlKA · 2026-08-24
- New Claude Models 'Marshmallow' and 'Melon' Spotted, Likely Opus Update — kimmonismus · 2026-08-24
- Test: Qwen 3.8 27B Runs Well on Intel Arc B70 32GB — philfung · 2026-08-24
- Claude Opus experiences severe failures in coding tasks today — taylorwilsdon · 2026-08-24
- Testing MiniMax H3 Ref2va: follows 5 of 6 storyboard panels correctly — smereces · 2026-08-24