Dev's model vibes: Opus 5.5 writes best, Sol 6.1 best value, Sonnet skippable
ricklamers · x · 2026-10-18
Developer Rick Lamers shares his hands-on takes on current coding models, matching others' opinions: Sonnet 5.5 is great but you shouldn't be using it, Opus 5.5 writes super well, Sol 6.1 offers incredible value, while Astra and Fable 5.1 are niche choices usually not worth it.
He also notes an interesting detail: Pi Durable went through 7x rewrites, yet agent session files on disk remain unstandardized.
Related event: Developer Compares Leading AI Models and Praises Google AI Overviews(4 posts)→
More from Models
- MOSS SFT vs Flux 3 Klein vs SD 3.0: Same-Prompt Comparison Exposes SD3's Age — ZootAllures9111 · 2026-10-18
- Quick take: GPT-6 matches Opus 5.5 at coding, far ahead at computer use — _vztu · 2026-10-18
- Open models now above Sol-level, outpacing expectations as community awaits V4.1 Pro — yacineMTB · 2026-10-18
- Codex took 3 days, Opus 5.5 nailed it in an afternoon — banned user's video protest — dotey · 2026-10-18
- Yacine MTB: Users will remember how Anthropic treated them once intelligence proliferates — yacineMTB · 2026-10-18
- Mistral's Timestral forecasting models start at 5M params and run on plain CPUs — lmoroney · 2026-10-18