Claude Opus 5.5 is Anthropic's flagship model for agentic coding, computer use, complex knowledge work, and long-running tasks, with improved efficiency and more natural communication.
Added Sep 22, 2026
Context Window
1.0M
Max Output
128.0K
Avg output tokens (7d)
2.4K tokens
Input Price (Auto)
$4.00/1M
Output Price (Auto)
$20.00/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
53.6
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
63.2%
Better than 91% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
41.2%
Better than 87% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
90.9%
Better than 62% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1705 Elo
Better than 98% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1692 Elo
Better than 96% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
28.8%
Better than 95% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
82.7%
Better than 94% of models compared
MLCR-AA
Medical long-context reasoning
66.7%
Better than 97% of models compared
Reasoning
HLE
Humanity's Last Exam
55.6%
Better than 99% of models compared
CritPt
Research-level physics reasoning
31.7%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
56.6%
Better than 96% of models compared
SciCode
Python programming for scientific computing
60.4%
Better than 96% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
66.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
58.6%
Legacy benchmarks
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
82.7%
Better than 94% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
67.3%
Last updated Oct 2, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Claude Opus 5.5 with similar models from the same provider or model family.
Claude Opus 5
anthropic/claude-opus-5Claude Opus 5 is Anthropic's flagship model for advanced coding, long-running agentic tasks, research, and complex knowledge work.
Claude Opus 4.8
anthropic/claude-opus-4.8Anthropic Claude Opus 4.8 with text, image, and file inputs and a 1M-token context window.
Claude Opus 4.8 Thinking
anthropic/claude-opus-4.8:thinkingAnthropic Claude Opus 4.8 with thinking enabled.
Claude 4.7 Opus
anthropic/claude-opus-4.7Claude Opus 4.7 is a major upgrade for advanced software engineering, long-running complex tasks, and high-resolution vision understanding.
Claude 4.7 Opus Thinking
anthropic/claude-opus-4.7:thinkingClaude Opus 4.7 with thinking enabled (default budget: 16k tokens).
Claude Opus Latest
anthropic/claude-opus-latestCompatibility alias that routes to the newest version of Claude Opus. Currently routes to Claude Opus 5.