Early Claude Opus 5 feedback says it matches Fable 5 on short tasks, but gets less complete on long ones
ZeroStateReflex · x · 2026-07-25
Emad-style early feedback on Claude Opus 5 says it is a strong but quirky model.
- On shorter tasks, it could match or beat Fable 5-level performance.
- On longer tasks, it seemed less ambitious and less likely to deliver a complete set of work.
- The post also points to a “neo-gothic shader” example generated with the model.
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11
- User Hails Unconfirmed 'DeepSeek 4.1 Flash' as an Inflection Point in LLMs — himanshustwts · 2026-09-11