Anthropic released Claude Sonnet 5.5 on September 28. On Terminal-Bench 4.0, a test of real command-line coding work, it scored 70.6%, ahead of Claude Opus 5.5 at 66.4% and far ahead of the last Sonnet at 10.3%. It is also the first Sonnet to beat Pokémon Red working only from screenshots of the game.
It costs half as much per token as Opus, writes over 30% faster than Sonnet 5 and uses fewer tokens per task. But Opus is still ahead on several other tests, and Anthropic still says Opus is the one for complex work. So the question isn't which model is better. It's which one to pick for each job.
What Anthropic shipped
| Test (Anthropic's numbers) | Sonnet 5.5 | Opus 5.5 | Sonnet 5 |
|---|---|---|---|
| Terminal-Bench 4.0 (agentic coding) | 70.6% | 66.4% | 10.3% |
| FrontierCode 1.1 (hard coding) | 46.2% (max effort) | 54.4% | 42.4% |
| CursorBench 4.0 (coding in an editor) | 55.5% | 57.8% | 34.1% |
| GDPval-AA v2.1 (knowledge work) | 1844 | 1846 | 1449 |
| OSWorld 2.1 (using a computer) | 80.1% | 81.8% | 57.0% |
| Humanity's Last Exam (with tools) | 64.5% | 67.7% | 54.9% |
| Price per 1M tokens (in / out) | $2 / $10 | $4 / $20 | $2 / $10 |
Read the table as two groups. On everyday work (command-line coding, knowledge work, using a computer) Sonnet 5.5 matches or beats Opus. On the hardest problems (FrontierCode, Humanity's Last Exam) Opus keeps a clear lead. Anthropic's own advice follows the same line: Sonnet 5.5 is strongest at well-scoped everyday tasks, fixing bugs and making polished documents, slides and spreadsheets; Opus 5.5 is built for complex work that needs careful judgment.
The cheat sheet
| The task | Use | Why |
|---|---|---|
| Fix a bug you can point to | Sonnet 5.5 | Well-scoped, and the thing Anthropic says it does best |
| Scripts, installs, CI and terminal work | Sonnet 5.5 | Its best test: 70.6% vs Opus's 66.4% |
| Emails, docs, reports | Sonnet 5.5 | Polished documents, half the price per token |
| Slide decks | Sonnet 5.5 | Polished slides, and a sharp eye for design |
| Spreadsheets and data clean-up | Sonnet 5.5 | Everyday, well-scoped, checkable |
| UI and design polish | Sonnet 5.5 | Anthropic calls out its eye for design |
| Clicking through apps for you | Sonnet 5.5 | Nearly tied with Opus (80.1% vs 81.8%) for half the price |
| A new feature across many files | Opus 5.5 | Leads on hard coding (54.4% vs 46.2% on FrontierCode) |
| Refactors, migrations, architecture | Opus 5.5 | Complex work where one wrong call is expensive |
| Vague or high-stakes asks | Opus 5.5 | Careful judgment is what it's built for |
| Hard research and reasoning | Opus 5.5 | Leads on Humanity's Last Exam (67.7% vs 64.5%) |
| Sonnet failed twice on it | Opus 5.5 | Stop retrying: escalate the one step that's stuck |
Free, for your email
Get the full setup steps + the copy-paste setup prompt
The rest of this guide (3 more sections) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.
Unlocks: How to switch models · Make your usage limit last longer · Before you rely on it
50,000+ follow where these guides come from. No spam, reply “unsubscribe” any time.