Developer's detailed take: Opus 5.5 nears Fable 5.1 at lower cost, wins back Claude Code users
dejavucoder · x · 2026-09-26
A long-form model-switching account details why a developer returned to Anthropic: after four months mainly on the Codex app, they found GPT 5.6 Sol great at nearly everything, while Astra was undercooked on eagerness and instruction following (stopping mid-task to ask questions) despite strong writing, frontend, and computer use.
They argue Anthropic had gone through a periodic 'aura loss' — disappointing Opus 5, pricey Fable 5.1 — but Opus 5.5 delivers near-Fable 5.1 performance at a lower price. It feels collaborative and fast, 'eager but not over-eager,' excels at frontend, is decent at computer use/image/video gen, handles frontier coding like inference engineering, and shows less 'neuralese' in writing (knowledge cutoff June 2026). Having mostly quit around Opus 4.7, the author is back on Claude Code thanks to Opus 5.5, while still daily-driving GPT 6 Sol and Astra.
More from coding & agent
- Skip pptx: Web-Based AI Slides Look Better, But You Still Need PowerPoint for the Boss — lxfater · 2026-09-26
- Personal Agents Will Be Interchangeable; Personal Context Is the Real Moat — vaibhavbetter · 2026-09-26
- Matt Pocock: your CODING_STANDARDS.md should be empty for only 5 minutes — mattpocockuk · 2026-09-26
- Custom benchmark: 35B Qwen3.6 scores 95% vs 53% for 120B GPT-OSS on coding agent — pauliusztin · 2026-09-26
- Installing DeepSeek Harness on a Muse cloud VM to unlock Chinese web search — op7418 · 2026-09-26
- Coded animation lands in a single AI one-shot, no assets or examples needed — eschadiol · 2026-09-26