Anthropic
Claude Sonnet 5.5 (Adaptive Reasoning, Max Effort, Default Fallback)
Claude Sonnet 5.5 is a step-change improvement over Sonnet 5 for well-scoped everyday work like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. It also writes more clearly than Sonnet 5.
Introducing Claude SonnetModel Snapshot
TypeLanguage
ReleaseSep 28, 2026
Context1,000,000
Tagsexplicit-caching, file-input, reasoning, tool-use
Overall
Rank #5 across 709
56.0
Coding
No rank
n/a
Blended Price
Rank #337 across 432
$4.00/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 Speed145.2 tok/s
First Token304.76s
Max Output128,000
Pricing
Blended$4.00/M
Input$2.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 56.0 | #5 |
| LiveBench Mathematics | math | 96.1% | #8 |
| Humanity's Last Exam | reasoning | 55.0% | #8 |
| SciCode | coding, reasoning | 61.0% | #5 |
| Output Speed |