Claude Opus 4.6
anthropic/claude-opus-4-6
High-end Claude for difficult coding, planning, and slower expert reasoning
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureSupported
AttachmentYes
Open weightsNo
Limits
Context1,000,000 tokens
Max inputN/A
Max output128,000 tokens
Details
Familyclaude-opus
Knowledge cutoff2025-05-31
Release date2026-02-05
Last updated2026-03-13
Modalities
Inputtext, image, pdf
Outputtext
Benchmarks
SWE-Bench Pro
51.9
resolve rate
SWE-Atlas Codebase QnA
33.3
score
SWE-Atlas Codebase QnA
30
score
SWE-Atlas Refactoring
35.58
score
SWE-Atlas Test Writing
36.67
score
SWE-Atlas Test Writing
36.08
score
Artificial Analysis Coding Agent Index
51.3
average pass@1
SWE-Atlas Codebase QnA
71.9
pass@1
SWE-Bench Pro
11.8
pass@1
Terminal-Bench
70.2
pass@1
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A