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.
More from Models
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11
- antirez Weighs In on Anthropic Banning Minors From Using Claude — antirez · 2026-09-11
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11