Browse all Anthropic text models
Provider logo

Claude Sonnet 4.6 Thinking

anthropic/claude-sonnet-4.6:thinking
Provider logo

Claude Sonnet 4.6 Thinking

anthropic/claude-sonnet-4.6:thinking

Claude 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.

Added Feb 17, 2026

Context Window

1.0M

Max Output

128.0K

Avg output tokens (7d)

2.7K tokens

96%

Input Price (Auto)

$3.00/1M

Output Price (Auto)

$15.00/1M

Cache Read (Auto)

$0.30/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

30.5

Better than 86% of models compared

Coding Index

63.0

Better than 75% of models compared

Agentic Index

33.1

Better than 74% of models compared

Agentic work

AutomationBench-AA

Workflow automation with guardrail penalties

20.1%

Better than 46% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1065 Elo

Better than 60% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1295 Elo

Better than 70% of models compared

Document reasoning

GDP.pdf

Professional PDF reasoning: all-pass rate

15.8%

Better than 66% of models compared

AA-LCR v1.1

Long context reasoning with updated grading

80.0%

Better than 89% of models compared

Reasoning

HLE

Humanity's Last Exam

33.6%

Better than 85% of models compared

IFBench

Instruction-following benchmark

56.6%

Better than 67% of models compared

CritPt

Research-level physics reasoning

3.1%

Coding

Terminal-Bench v4.0

Practical coding and terminal tasks

3.0%

Better than 58% of models compared

SciCode

Python programming for scientific computing

50.1%

Better than 58% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

40.9%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

48.4%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

87.5%

Better than 84% of models compared

Terminal-Bench Hard (legacy)

Agentic coding and terminal use

53.0%

Better than 96% of models compared

T²-Bench Telecom (legacy)

Conversational AI agents in dual-control scenarios

75.7%

Better than 67% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

80.0%

Better than 89% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

39.8%

Last updated Sep 13, 2026

Artificial Analysis

Providers

Auto routing is available for this model. Explicit provider selection is not available.

Loading provider options…

Compare Claude Sonnet 4.6 Thinking with similar models from the same provider or model family.