Claude Sonnet 4.6
ClaudeBalanced
ThinkingTool UseVisionStructured Output
About this model
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with...
Performance Tier
Balanced
Claude Sonnet 4.6 is a balanced model from Claude : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plansHigh
High pricing. Reserve this level for tasks that demand maximum quality.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $3.00 |
| Output (completion) | $15.00 |
| Cache read | $0.300 |
| Cache write | $3.75 |
Capabilities
Context Length1.0M
Max Output Tokens128K
TokenizerClaude
Inputtext, image, file
Outputtext
Release DateFebruary 17, 2026
Benchmarks
General Intelligence
MMLU
Not reported
GPQA Diamond
89.9%
Mathematics
MATH-500
Not reported
Programming
HumanEval
Not reported
SWE-bench Verified
79.6%
Reasoning
ARC-AGI-2
58.3%
Humanity's Last Exam
49%
Agentic
Terminal-Bench 2.0
59.1%
Where does Claude Sonnet 4.6 stand?
Compare its performance index against every other model.
Recommended Use Cases
CodingAnalysisResearchCreative Writing
Strengths
- Near-Opus performance at a fraction of the cost
- Exceptional agentic coding (SWE-bench 79.6%, close to Opus 80.8%)
- Strong graduate-level reasoning (GPQA Diamond 89.9%)
- 1M token context window for long-document tasks
Limitations
- Anthropic's published evaluation focuses on agentic and reasoning benchmarks — MMLU and HumanEval are not part of the official suite
- Slower than Haiku for simple, latency-sensitive queries
Frequently asked questions
Resources
This model may use your data for training