Anthropic logo

Claude 3.5 Sonnet

by Anthropic

New Claude 3.5 Sonnet delivers better-than-Opus capabilities, faster-than-Sonnet speeds, at the same Sonnet prices. Sonnet is particularly good at: - Coding: Scores ~49% on SWE-Bench Verified, higher than the last best score, and without any fancy prompt scaffolding - Data science: Augments human data science expertise; navigates unstructured data while using multiple tools for insights - Visual processing: excelling at interpreting charts, graphs, and images, accurately transcribing text to derive insights beyond just the text alone - Agentic tasks: exceptional tool use, making it great at agentic tasks (i.e. complex, multi-step problem solving tasks that require engaging with other systems) #multimodal

Chat with Claude 3.5 Sonnet

Capabilities

Vision

Pricing

Input Tokens
Per 1M tokens
Free
Output Tokens
Per 1M tokens
Free
Image Processing
Per 1M tokens
$4800.00/1M tokens

Supported Modalities

Input

text
image
file

Output

text

Performance Benchmarks

Intelligence Index
Overall intelligence score
62.7
Coding Index
Programming capability
49.8
Math Index
Mathematical reasoning
88.0
GPQA
Graduate-level questions
83.4%
MMLU Pro
Multitask language understanding
87.5%
HLE
Human-like evaluation
17.3%
LiveCodeBench
Real-world coding tasks
71.4%
AIME 2025
Advanced mathematics
88.0%

Specifications

Context Length
200K tokens
Provider
Anthropic
Throughput
72.768 tokens/s
Released
Oct 22, 2024
Model ID
anthropic/claude-3.5-sonnet

Ready to try it?

Start chatting with Claude 3.5 Sonnet right now. No credit card required.

Start Chatting

More from Anthropic

View all models