Anthropic: Claude 3.5 Sonnet

Anthropic: Claude 3.5 Sonnet

anthropic · Released Oct 22, 2024 Specialist
Intelligence #79 / 544
62.8 Our Score
AA Index #209 / 365
15.9 Artificial Analysis
Input #530 / 551
$6.00 per 1M tokens
Output #526 / 551
$30.00 per 1M tokens
Context #168 / 551
200,000 tokens

Analysis Summary

Anthropic: Claude 3.5 Sonnet sits in the Specialist tier on our leaderboard, ranked #79 of 544 published models on overall intelligence. At $6.00 input and $30.00 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and vision.

Editorial notes

Claude 3.5 Sonnet offers strong coding capability, vision support, tool use, and function calling with a 200K context window, but its intelligence index reflects an older generation now well behind current Anthropic flagships.

Assessed May 5, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.5Technical5.5Value5.5Content7.5
Intelligence 3.5/10
Technical 5.5/10
Content 7.5/10
Value 5.5/10

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

Capabilities

Tool Use Function Calling Vision

Performance Indices

Source: Artificial Analysis

15.9 Intelligence Index
30.2 Coding Index

Benchmark Scores

Intelligence

GPQA Diamond 59.9% Graduate-level scientific reasoning
HLE 3.9% Humanity's Last Exam
MMLU Pro 77.2% Multi-task language understanding
MATH 500 77.1% Mathematical problem-solving
AIME 15.7% Competition mathematics
SciCode 36.6% Scientific computing

Technical

LiveCodeBench 38.1% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Anthropic: Claude 3.5 Sonnet stack up?

Compare side-by-side with other specialist models.

Compare Models

Model Information

OpenRouter ID anthropic/claude-3.5-sonnet
Provideranthropic
Model FamilyClaude 3.5
Release Date October 22, 2024
Context Length200,000 tokens
Max Completion8,192 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $6.00 $0.006000
Output $30.00 $0.030000

Leaderboard Categories