Every team tests Sonnet 5.5: half Opus's token price, matches it on writing readability
kieranklaassen · x · 2026-09-29
The Every team tested Anthropic's new Sonnet 5.5 across coding, writing, design, and knowledge work:
- Half of Opus 5.5's per-token price, but per-task cost is murkier — it burns tokens fast on high effort, hence medium as the default.
- It handled coding tasks Opus 5 couldn't, rebuilding Every's document editor Proof on low effort.
- Its prose tied Opus 5.5 as the most readable on their writing bench, at just under a seventh-grade reading level.
- It eagerly fills gaps left in briefs.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16