← Back to all models
C

Claude Sonnet 4

by Anthropic
Flagship Proprietary Multimodal 🏆 Ranked #7 of 22
85.4
Overall Score
out of 100
About

Anthropic's fourth-generation Sonnet model, offering a significant leap in reasoning depth and coding accuracy over the 3.x series. Claude Sonnet 4 introduces refined tool use and improved adherence to complex multi-step instructions.

Key Metrics
Context Window
200K
tokens
Avg Response
820
milliseconds
Input Cost
$3.0
per million tokens
Output Cost
$15.0
per million tokens
Arena ELO
1345
Chatbot Arena rating
MT-Bench
9.2
out of 10
Benchmark Scores
MMLU
91.0%
HumanEval
93.5%
MATH
79.2%
GPQA
65.8%
MT-Bench
92.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Improved reasoning over 3.5 ✓ Stronger tool use ✓ Better instruction adherence ✓ Safety-focused ✓ Long-context handling
Limitations
⚠ Higher cost than 3.5 Sonnet ⚠ No image generation ⚠ Verbose on simple tasks
Ideal Use Cases
Complex analysis Software engineering Agentic workflows Legal review Technical writing
Model Details
Provider Anthropic
Released 2025-08-05
Open source No
Multimodal Yes
Tier Flagship
Global rank #7 / 22
Pricing (USD)
Input tokens $3.0/M
Output tokens $15.0/M
Per 1,000 tokens ≈ $0.0030 input / $0.0150 output
All Benchmarks
MMLU 91.0%
HumanEval 93.5%
MATH 79.2%
GPQA 65.8%
MT-Bench 9.2/10
Arena ELO 1345
Compare this model View leaderboard
Similar Models

You might also consider

o
o3
OpenAI
93.7
score
Flagship

OpenAI's most powerful reasoning model, using extended chain-of-thought to tackle the hardest problems in mathematics, science, and coding. o3 sets new standards on GPQA and competitive maths at the cost of higher latency and price.
C
Claude Opus 4
Anthropic
90.7
score
Flagship

Anthropic's most powerful and intelligent model, built for the most demanding tasks where quality outweighs cost. Claude Opus 4 leads on complex multi-step reasoning, graduate-level science, and nuanced long-form writing.
C
Claude Sonnet 4.6
Anthropic
88.3
score
Flagship

The latest and most capable Sonnet model to date. Claude Sonnet 4.6 brings further gains in mathematical reasoning and instruction following, making it Anthropic's most well-rounded model at the Sonnet price point.