Anthropic 发布 Claude Sonnet 5，号称"最有智能体特性的 Sonnet 模型"。编码得分 SWE-bench Pro 达 63.2%（Sonnet 4.6 为 58.1%，Opus 4.8 为 69.2%），知识工作略超 Opus 4.8。定价优惠：每百万 token 输入 $2、输出 $10，持续到 8 月 26 日，之后涨至 $3/$15。但升级并非全技能均匀提升，在 CyberGym（漏洞发现与利用测试）上弱于 Sonnet 4.6。Anthropic 明确表示未针对网络任务专门训练，该表现来自通用推理而非定向优化。
Claude Sonnet 5 upgrades are not uniform across every skill.
e.g. its weaker than Sonnet 4.6 on CyberGym 🤔
Here, CyberGym is testing vulnerability discovery and exploit-finding behavior, not general reasoning or normal coding.
Anthropic also explicitly said in its announcment blog that Sonnet 5 was not deliberately trained for cyber tasks, so its cyber ability likely comes from general intelligence rather than targeted optimization.
So Sonnet 5's performance on CyberGym comes from general reasoning rather than specialized exploit skill.
---
From System Card of Claude Sonnet 5
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