Claude Opus 4.7
anthropic/claude-opus-4-7
Stronger Opus tier for advanced software work and high-stakes reasoning
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureFixed
AttachmentYes
Open weightsNo
Limits
Context1,000,000 tokens
Max inputN/A
Max output128,000 tokens
Details
Familyclaude-opus
Knowledge cutoff2026-01-31
Release date2026-04-16
Last updated2026-04-16
Modalities
Inputtext, image, pdf
Outputtext
Benchmarks
SWE-Bench Pro
64.3
resolve rate
Terminal-Bench
66.1
success rate
SWE-Atlas Refactoring
48.57
score
Artificial Analysis Coding Agent Index
66.6
average pass@1
SWE-Atlas Codebase QnA
81
pass@1
SWE-Bench Pro
44.9
pass@1
Terminal-Bench
73.8
pass@1
Artificial Analysis Coding Agent Index
61.2
average pass@1
SWE-Atlas Codebase QnA
78.4
pass@1
SWE-Bench Pro
34.4
pass@1
Terminal-Bench
70.6
pass@1
Artificial Analysis Coding Agent Index
59.9
average pass@1
SWE-Atlas Codebase QnA
71.7
pass@1
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A