Claude Sonnet 4

AnthropicProprietaryVerified

Claude Sonnet 4 significantly improves on Sonnet 3.7's capabilities, excelling in coding with a state-of-the-art 72.7% on SWE-bench. The model balances performance and efficiency, with enhanced steerability for greater control over implementations. Features include extended thinking with tool use, parallel tool execution, improved instruction following, and significantly reduced shortcut behaviors.

2025-05-22

Decoder-only Transformer

Proprietary

Compare with other models

Specifications

Architecture: Decoder-only Transformer
License: Proprietary
Context Window: 200,000 tokens
Max Output: 64,000 tokens
Training Data Cutoff: Mar 2025
Type: multimodal
Modalities: textimage

Benchmark Scores

MMLU85.4

Massive Multitask Language Understanding (MMLU) tests knowledge across 57 subjects including mathema...

GPQA70

Graduate-level Problems in Quantitative Analysis (GPQA) evaluates advanced reasoning on graduate-lev...

SWE-bench72.7

Software Engineering Benchmark (SWE-bench) evaluates models on real-world software engineering tasks...

MMMU72.6

Massive Multi-discipline Multimodal Understanding (MMMU) evaluates multimodal understanding across 3...

AIME33.1

American Invitational Mathematics Examination (AIME) problems test advanced mathematical problem-sol...

Advanced Specifications

Model Family: Claude
API Access: Available
Chat Interface: Available
Multilingual Support: Yes

Capabilities & Limitations

Capabilities: codingreasoningtool useparallel tool executionextended thinking
Notable Use Cases: codingsoftware developmentagentic scenariosmulti-feature app development
Function Calling Support: Yes
Tool Use Support: Yes

Resources

www.anthropic.com/news/claude-4

Related Models

Claude Opus 4

Anthropic

Claude Opus 4 is Anthropic's most powerful model and the best coding model in the world, leading on SWE-bench (72.5%) and Terminal-bench (43.2%). It delivers sustained performance on long-running tasks that require focused effort and thousands of steps, with the ability to work continuously for several hours. Features include extended thinking with tool use, parallel tool execution, improved memory capabilities, and significantly reduced shortcut behaviors.

Llama 4 (400B)

GPT-4.1 mini

OpenAI

Smaller version of GPT-4.1 optimized for coding and instruction following while maintaining the 1M token context window. Designed for applications requiring strong coding capabilities with better efficiency.