Claude Sonnet 5.5 with adaptive thinking for complex coding, multi-step tool use, visual analysis, and detailed planning. Supports a 1M-token context window and five reasoning effort levels, with stronger thinking available when a task needs it.
Added Sep 28, 2026
Context Window
1M
Max Output
128K
Input Price (Auto)
$2.00/1M
Output Price (Auto)
$10.00/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
56.0
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
71.3%
Better than 99% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
44.7%
Better than 97% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
93.1%
Better than 89% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1811 Elo
Better than 99% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1844 Elo
Better than 99% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
25.8%
Better than 89% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
82.7%
Better than 95% of models compared
Reasoning
HLE
Humanity's Last Exam
55.0%
Better than 99% of models compared
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
63.6%
Better than 99% of models compared
SciCode
Python programming for scientific computing
61.0%
Better than 98% of models compared
Legacy benchmarks
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
82.7%
Better than 95% of models compared
Last updated Sep 28, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare Claude Sonnet 5.5 Thinking with similar models from the same provider or model family.
Claude Sonnet 5.5
anthropic/claude-sonnet-5.5Claude Sonnet 5.5 handles everyday coding, tool-based workflows, visual analysis, and polished writing with a 1M-token context window. This version skips up-front thinking and can reason between tool calls for faster responses; use Thinking for deeper planning and complex problems.
Claude Sonnet 5
anthropic/claude-sonnet-5Claude Sonnet 5 supports coding, agentic workflows, long-context reasoning, computer use, and practical knowledge work.
Claude Sonnet 5 Thinking
anthropic/claude-sonnet-5:thinkingClaude Sonnet 5 with adaptive thinking enabled for complex coding, planning, and agentic work.
Claude Sonnet Latest
anthropic/claude-sonnet-latestCompatibility alias that routes to the newest version of Claude Sonnet. Currently routes to Claude Sonnet 5.5 Thinking.
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6Claude Sonnet 4.6 is Anthropic's most capable Sonnet yet — a full upgrade across coding, computer use, long-context reasoning, agent planning, and design. Supports up to a 1M-token context window at Sonnet pricing.
Claude Sonnet 4.6 Thinking
anthropic/claude-sonnet-4.6:thinkingClaude Sonnet 4.6 with extended thinking enabled for tougher coding, planning, and multi‑tool tasks. Ideal for long‑horizon agent workflows and complex problem solving.