#5
Claude Sonnet 4.6
claude-sonnet-4-6
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 80 tok/s
Release Date
April 10th, 2026
Lab
Anthropic
Type
Proprietary
Context Size
200K
Max Output Tokens
8.2K
Cost per 1 million tokens
$3.00 / $15.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
90.62 pts
Rank #5
92th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Sonnet 4.6 delivers frontier performance across coding, agents, and professional work at scale. It sits perfectly between Sonnet 4.5 and Opus 4.5, offering exceptional comprehension and instruction following. Its creative writing and empathy scores are also highly competitive, making it an excellent all-around model for complex reasoning and long-context tasks.

Intelligence

Overall Score; Higher is better

Claude Opus…
Claude Opus…
Gemini 3.1 …
Claude Opus…
Claude Sonn…
GPT-5.4
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3

Speed

Output Tokens per Second; Higher is better

DeepSeek V3
GPT-5.4
ChatGPT 4o
GPT 4o
Grok 3 Mini
Claude Sonn…
GPT 5.1
Grok 4.1 Fa…
GLM 4.5 Air
GPT 5.2

Price

USD per 1M Tokens; Lower is better

Gemini 3 Pro
o3
Gemini 2.5 …
GPT-5.4
GPT 4o
Claude Sonn…
Claude Sonn…
Grok 3
Grok 4
Claude Opus…

Anthropic Models

Overall Score; Same provider comparison

Claude Opus…
Claude Opus…
Claude Opus…
Claude Sonn…
Claude Sonn…
Claude Opus…
Claude Haik…

Claude Sonnet Family

Overall Score; Same model family comparison

Claude Sonn…
Claude Sonn…

Closest Rivals

Overall Score; Nearest by overall rank

Claude Opus…
Claude Opus…
Gemini 3.1 …
Claude Opus…
Claude Sonn…
GPT-5.4
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3