Anthropic
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
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...
Introducing Claude SonnetModel Snapshot
ReleaseFeb 17, 2026
Context1,000,000
Overall
Rank #27 across 566
47.2
Coding
Rank #39 across 222
63.0
Blended Price
Rank #331 across 371
$6.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed72 tok/s
First Token67.16s
Max Output128,000
Pricing
Blended$6.00/M
Input$3.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 47.2 | #27 |
| Artificial Analysis Coding Index | coding | 63.0 | #39 |
| GPQA | reasoning | 87.5% | #57 |
| Humanity's Last Exam | reasoning | 30.0% | #52 |
| SciCode |