#5
Claude Sonnet 4.5
claude-sonnet-4-5
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 68.5 tok/s
Release Date
September 29, 2025
Lab
Anthropic
Type
Proprietary
Context Size
200K
Max Output Tokens
64K
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.
89.66 pts
Rank #5
92th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Sonnet 4.5 is a significant leap forward in reasoning and agentic capabilities, positioning itself as a top-tier model for complex tasks. It excels in instruction following and coding, demonstrating state-of-the-art performance in handling multi-step workflows and computer use. The model also shows marked improvements in comprehension and creative writing, balancing precise control with natural, empathetic responses. Its alignment training ensures it handles sensitive topics with care while maintaining high helpfulness across diverse domains.

Intelligence

Overall Score; Higher is better

Claude Opus…
Gemini 3.1 …
Claude Opus…
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3
GPT 5.2
GLM 5
GPT 5

Speed

Output Tokens per Second; Higher is better

GLM 5
GPT 5
Gemini 3 Fl…
Grok 4
GLM 4.6
Claude Sonn…
Grok 3
GLM 4.7
Kimi K2.5
o1

Price

USD per 1M Tokens; Lower is better

Gemini 3.1 …
Gemini 3 Pro
o3
Gemini 2.5 …
GPT 4o
Claude Sonn…
Grok 3
Grok 4
Claude Opus…
Claude Opus…

anthropic Models

Overall Score; Same provider comparison

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

Claude Sonnet Family

Overall Score; Same model family comparison

Claude Sonn…

Closest Rivals

Overall Score; Nearest by overall rank

Claude Opus…
Gemini 3.1 …
Claude Opus…
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3
GPT 5.2
GLM 5
GPT 5