Compare models

Context, limits, capabilities, price and use cases side by side — up to 4 models at a time. The URL holds your selection, so you can share it.

Claude Sonnet 5.5 Add a modelChat with this model

Attribute	Claude Sonnet 5.5anthropic/claude-sonnet-5-5
Specs
Context window	1M
Max output	128K
Input modalities	TextImage
Output modalities	Text
Capabilities
Streaming	Supported
Tool calling	Supported
Structured output (JSON)	Supported
Image input	Supported
Thinking mode	Supported
Price / 1M tokens
Input	$ 2.00
Output	$ 10.00
Cache read	$ 0.10
Cache write	$ 2.50
What it is good at
Best for	Agentic coding Documents, slides and spreadsheets Charts and computer use
Published benchmarks
CursorBench 4.0score	55.5%effort max(setup not fully disclosed)
FrontierCode v1.1 (Main)score	46.2%effort max · Claude Code(setup not fully disclosed)
Terminal-Bench 4.0pass_rate	70.6%effort max · Claude Code(setup not fully disclosed)
SWE-Bench Proresolved_rate	81.3%effort max(setup not fully disclosed)
OSWorld 2.1 (partial credit)score	80.1%effort max(setup not fully disclosed)
AA-Briefcase v1.1score	1811effort max(setup not fully disclosed)
GDPval-AA v2.1elo	1844effort max(setup not fully disclosed)
Chartography (no tools)score	61.6%effort max(setup not fully disclosed)
Humanity's Last Examaccuracy	56.9%effort max(setup not fully disclosed)
Humanity's Last Exam (with tools)accuracy	64.5%effort max(setup not fully disclosed)