Anthropic: Claude 3.7 Sonnet (thinking)
Analysis Summary
Claude 3.7 Sonnet (thinking) is the extended-reasoning variant of Anthropic's Claude 3.7 Sonnet, activating a chain-of-thought mode that significantly boosts performance on hard reasoning and mathematics tasks. Its intelligence index of 27.1 and math index of 56.3 place it well above the standard Sonnet variant, and its long-context reasoning score of 0.607 indicates strong performance on extended document tasks. Vision, tool use, and function calling are all supported.
For businesses, this variant is the better choice for complex analysis, technical writing, multi-step reasoning, and tasks where answer quality is critical. The agentic index of 37.9 and tau2 of 0.547 suggest reliable performance in structured agentic pipelines. It shares the same pricing as the base Sonnet, so the reasoning uplift comes at no additional cost per token.
Teams already using Claude 3.7 Sonnet should default to the thinking variant for demanding tasks. At $3 input and $15 output, it remains a premium option, best reserved for high-value workflows where reasoning depth justifies the spend.
Assessed June 30, 2026
Editorial notes
Claude 3.7 Sonnet (thinking) adds extended reasoning to Anthropic's Sonnet base, with a strong math index of 56.3, vision, tool use, and reliable long-context performance across complex tasks.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Anthropic: Claude 3.7 Sonnet (thinking) compares
Anthropic: Claude 3.7 Sonnet (thinking) ranks #93 of 385 AI models we track for overall intelligence, #54 of 129 for coding, #121 of 293 for agentic tasks. Its 200K-token context window is larger than 65% of the models we list. At $3.00 per million input tokens it is cheaper than 10% of comparable models.
About Anthropic: Claude 3.7 Sonnet (thinking)
Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities. It introduces a hybrid reasoning approach, allowing users to choose between rapid responses and..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Anthropic: Claude 3.7 Sonnet (thinking) stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $3.00 | $0.003000 |
| Output | $15.00 | $0.015000 |
Leaderboard Categories
External Resources
Frequently asked questions about Anthropic: Claude 3.7 Sonnet (thinking)
How much does Anthropic: Claude 3.7 Sonnet (thinking) cost?
Anthropic: Claude 3.7 Sonnet (thinking) costs $3.00 per million input tokens and $15.00 per million output tokens.
What is the context window of Anthropic: Claude 3.7 Sonnet (thinking)?
Anthropic: Claude 3.7 Sonnet (thinking) has a context window of 200,000 tokens (200K).
Is Anthropic: Claude 3.7 Sonnet (thinking) good for coding?
On our coding benchmark index, Anthropic: Claude 3.7 Sonnet (thinking) ranks #54 of 129 models, placing it in the broader range of the field for code generation and debugging.
What can Anthropic: Claude 3.7 Sonnet (thinking) do?
Anthropic: Claude 3.7 Sonnet (thinking) supports image/vision input, tool use, and function calling.
Who created Anthropic: Claude 3.7 Sonnet (thinking)?
Anthropic: Claude 3.7 Sonnet (thinking) is developed by Anthropic and was released on February 24, 2025.
