The Decoder· Matthias Bastian·· 10d agoSelectedAI score78
Claude Sonnet 5.5 多项基准接近 Opus 5.5,单任务成本最多低 30%
Anthropic's Claude Sonnet 5.5 nearly matches Opus 5.5 on benchmarks while costing up to 30 percent less per task
AI brief
Anthropic 发布 Claude Sonnet 5.5,基准接近 Opus 5.5,输出快逾 30%,单任务成本最多低 30%。
Why it matters
Sonnet 5.5多项基准接近Opus 5.5且单任务成本最多低三成,编码成绩相对前代抬升尤其明显。
Source: The Decoder · the-decoder.com