Claude Sonnet 5
anthropic/claude-sonnet-5
Everyday Claude agent model for coding, planning, browsing, and general work
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureFixed
AttachmentYes
Open weightsNo
Limits
Context1,000,000 tokens
Max inputN/A
Max output128,000 tokens
Details
Familyclaude-sonnet
Knowledge cutoff2026-01-31
Release date2026-06-30
Last updated2026-06-30
Modalities
Inputtext, image, pdf
Outputtext
Benchmarks
SWE-Bench Verified
85.2
resolved
SWE-Bench Pro
63.2
resolve rate
SWE-Bench Multilingual
78.3
resolve rate
Terminal-Bench
80.4
success rate
OSWorld-Verified
81.2
success rate
BrowseComp
84.7
accuracy
FrontierCode
38.8
pass rate
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A