Claude 3.5 Sonnet

FreemiumGeneral Purpose

Anthropic's most capable model for complex reasoning, creative writing, and code generation. Excels at understanding context and producing high-quality outputs.

Tags

reasoningcode-generationcreative-writinganalysis

Benchmark Results

HumanEval

Python code generation benchmark

84.9

SWE-Bench

Software engineering benchmark

78.2

CodeT5+

Code understanding and generation

89.1

Overall Score

88
out of 100

Pricing Information

$3/100K tokens

Per 100K tokens

$20/month

Monthly subscription

Usage Examples

Simple Blog Post

Writing a 1000-word blog post with code examples

~5,000 tokens$0.15

Complex Web App

Building a full-stack web application with authentication, database, and API

~150,000 tokens$4.5

Detailed Metrics

code Quality95
speed85
accuracy92
versatility90
ease Of Use88
documentation85
community80
innovation95
reliability90
cost Effectiveness75