Claude Code

Set Up Claude Sonnet 5.5, the Model That Beats Opus 5.5 at Coding

Claude Sonnet 5.5 scores 70.6% on Terminal-Bench, ahead of Opus 5.5. The score table, what it costs, how to switch, the two catches, and a prompt to test it on your own code

2min read
1prompts to copy
3numbered steps
6sections

Anthropic's Claude Sonnet 5.5 is the second model in the Claude 5.5 family. On Terminal-Bench 4.0, an agentic coding test, it scores 70.6%, up from 10.3% for Sonnet 5 and ahead of Opus 5.5 at 66.4%.

Here's the score table, the price, how to switch, and the catches.

The score table

BenchmarkSonnet 5.5Sonnet 5Opus 5.5
Terminal-Bench 4.070.6%10.3%66.4% (Xhigh effort)
CursorBench 4.055.5%34.1%57.8%
OSWorld 2.1 (partial)80.1%57.0%81.8%

It runs 30% or more faster than Sonnet 5. Opus 5.5 still wins on CursorBench and OSWorld.

Keep reading

Free, for an email.

Unlocks 5 more sections, 1 copy-paste prompt, the document version, and every other guide on the site, for free. Enter your email once to keep reading.

45,000+ follow where these guides come from.No spam. Unsubscribe in one click.

Read next

Set Up Claude Haiku 5.5, the 10x Cheaper Claude Model
Claude Haiku 5.5 costs a tenth of the old Haiku per token and reads a million tokens at once. What it costs, the one-line switch, the two catches that change your bill, and three cheap things to build with it this week
2 min
Gemini 4 Argon Just Beat Claude at Coding: The Cheat Sheet for Which AI to Use for What
Google's new model tops a real-world coding test the day it was announced, but you can't use it yet. What it scored, what it costs, when it opens up, and which AI to pick for each kind of job until then.
3 min
Claude Sonnet 5.5 vs Opus 5.5: The Cheat Sheet for Which Claude to Use on Every Task
The new Sonnet beat Opus on a coding test the day it came out, at half the price per token. Here is when to use each one, so the work gets done well and your usage limit lasts.
3 min