Anthropic
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) is an Anthropic Claude Sonnet model, a balanced Claude tier commonly aimed at strong coding, reasoning, and agent workflows with practical latency and cost. The local profile shows whether this specific reasoning mode is a better fit for quality, speed, or value-sensitive use cases.
Introducing Claude SonnetOperational Metrics
Output Speed68 tok/s
First Token55.54s
Blended Price$6.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseFeb 17, 2026
Context Windown/a
Modalitiesn/a
Strength: Coding
Rank #11 across 410 models.
50.9
Strength: Overall
Rank #14 across 500 models.
51.7
Strength: HLE
Rank #23 across 474 models.
30.0%
Watch Area: TTFT
Rank #286 across 293 models.
55.54s
Watch Area: Blended $
Rank #295 across 325 models.
$6.00/M
Watch Area: Input $
Rank #295 across 325 models.
$3.00/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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 51.7 | #14 |
| Artificial Analysis Coding Index | coding | 50.9 | #11 |
| GPQA | reasoning | 87.5% | #28 |
| Humanity's Last Exam | reasoning | 30.0% | #23 |
| SciCode |