Sonnet 5.5 Ships With Opus-Level Writing Gains, But Mid-Tier Models May Be Dying
every · x · 2026-09-29
Dan Shipper's hands-on testing shows Sonnet 5.5 dramatically improved at writing, scoring 65% overall and 90% on paragraph revision in his Editorial Checks benchmark — beating Opus 5.5 on writing while being faster and cheaper. Heavy users argue mid-tier models are disappearing: stacks now split between frontier (Opus/Fable) and ultra-cheap (Jev/Luna), with GPT-6 Astra topping the benchmark at 82%.
Related event: Hands-on: Sonnet 5.5 matches Opus in writing at half the token price(2 posts)→
More from coding & agent
- Dev Builds Interactive 3D Plasma Globe Desktop Wallpaper with Claude Sonnet 5.5 — chaseleantj · 2026-09-29
- Turning coding-agent failures into regression tests with Kitaru session replay — strickvl · 2026-09-29
- Open-source Collaborator puts terminals, context files and code on one infinite canvas for agent dev — adnan_hashmi · 2026-09-29
- Almost no MCP servers make money: would agents pay per call for tools? — Prestigious_Lab_2998 · 2026-09-29
- Running Codex for 5 days to enumerate every published AI safety idea — AaronBergman18 · 2026-09-29
- Sonnet 5.5 Lands in Conductor, and the Benchmark Chart Is Surprising — charlieholtz · 2026-09-29