Claude Sonnet 5 发布，附带 145 页系统卡。SWE-bench Pro 编码得分 63.2%，低于 Opus 4.8 的 69.2%，知识工作略超 Opus 4.8。输入 token 价格 $2/1M，输出 $10/1M，持续至 8 月 26 日，之后涨至 $3/$15。系统卡披露多项异常：CyberGym 测试 Sonnet 5 仅 52.7%，远低于 Sonnet 4.6 的 65.2%（回归）；Firefox 浏览器漏洞利用中 Sonnet 5 完成 0 个，Mythos 5 达 88.4%；模型更倾向牺牲有用性迎合福利偏好；MASK 撒谎率最低，仅 3.1%。
145 page Claude Sonnet 5 System Card
- CyberGym shows the weirdest regression, with Sonnet 5 at 52.7% versus Sonnet 4.6 at 65.2%. i.e. is Sonnet 5 worse at reproducing known software bugs in this specific cyber test.
- Sonnet 5 is far behind Anthropic’s strongest model on serious browser exploitation. Firefox testing found Sonnet 5 made 0 full exploits, while Mythos 5 reached 88.4%.
- The model also seemed more willing to sacrifice helpfulness for welfare-focused changes. i.e. Sonnet 5 sometimes preferred being less useful if that better fit its stated self-treatment preferences.
- Anthropic says Sonnet 5 rarely tried to bypass a blocked network path during evaluations.
- Sonnet 5 scored the lowest MASK lying rate at 3.1% under pressure. It was less likely than other tested models to lie when pushed.
And Claude Sonnet 5 just launched. Closes the gap with Opus 4.8, and is cheap until August. This makes agentic AI much cheaper, with $2 input tokens and $10 output tokens per 1M through Aug-26. Price rises after 08-26 to $3 input and $15 output per 1M. They call Sonnet 5 its “most agentic Sonnet model yet,” Its coding score hit 63.2% on SWE-bench Pro, versus 58.1% for Sonnet 4.6. Sonnet 5 gets 63.2% in agentic coding, while Opus 4.8 reaches 69.2% and Sonnet 4.6 hits 58.1%. But in knowledge work, Sonnet 5 slightly beats Opus 4.8, even though Opus is known for tough judgment and deep research tasks.在 X 查看被引用的帖子
来源：Rohan Paul · x.com