#9
Claude Sonnet 5.5
claude-sonnet-5-5
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 90 tok/s
Release Date
September 28th, 2026
Lab
Anthropic
Type
Proprietary
Context Size
1M
Max Output Tokens
128K
Cost per 1 million tokens
$2.00 / $10.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
93.20 pts
Rank #9
92th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Sonnet 5.5 is Anthropic's September 28th, 2026 Sonnet refresh — Opus-adjacent everyday help at $2/$10. Our tests score helpfulness 93.5, instruction following 95.0, and comprehension 95.5, well above Claude Sonnet 5's 87.5/88.0/89.0. Empathy is 90.5: warmer than Sonnet 4.6's 88.0, short of Opus 5.5's 95.5. Creative writing is 91.5: clearer and more literary than Sonnet 5's 87.0. Speed is 90.0. The default 5.5-family driver when you want strong follow-through without Opus 5.5's bill.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
Baidu
Bytedance
DeepSeek
Google
Meta
Minimax
Mistral
Moonshot
OpenAI
Qwen
SpaceX AI
Tencent
Xiaomi
Zhipu AI

Intelligence

Overall Score · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M input tokens · Lower is better

Anthropic Models

Overall Score · Same provider

Claude Sonnet Family

Overall Score · Same model family

Closest Rivals

Overall Score · Nearest by overall rank