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)→

Original post →

More from coding & agent

coding & agent channel →