Anthropic
Claude 4.5 Sonnet (Reasoning)
Claude 4.5 Sonnet (Reasoning) 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 Speed43.8 tok/s
First Token7.72s
Blended Price$6.00/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseSep 29, 2025
Context Windown/a
Modalitiesn/a
Strength: MMLU-Pro
Rank #8 across 345 models.
87.5%
Strength: SciCode
Rank #42 across 472 models.
44.7%
Strength: Overall
Rank #53 across 500 models.
43.0
Watch Area: Blended $
Rank #294 across 325 models.
$6.00/M
Watch Area: Input $
Rank #294 across 325 models.
$3.00/M
Watch Area: Output $
Rank #292 across 325 models.
$15.00/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 | 43.0 | #53 |
| Artificial Analysis Coding Index | coding | 38.6 | #54 |
| Artificial Analysis Math Index | math | 88.0 | #38 |
| MMLU-Pro | reasoning | 87.5% | #8 |