Claude Opus 5.5 性价比超越 Fable
Claude gave out a banked reset yesterday. If you want your usage to last longer…
提供了具体的模型切换理由、基准数据对比以及详细的 Claude Code 配置代码示例，结构清晰且具备实操参考价值。
Claude gave out a banked reset yesterday. If you want your usage to last longer this time, you can switch your main model straight to Opus 5.5.
Claude 昨天发布了一个银行重置。如果你想让你的使用量持续更长时间，你可以直接将主模型切换到 Opus 5.5。
I used to suggest keeping Fable as your main model and handing the grunt work to Opus subagents, to save Fable usage. Now Opus 5.5's listed price is only 40% of Fable 5.1's, and it's ahead on benchmarks too: 58 vs 53 on the Artificial Analysis Intelligence Index, both at max effort.
我以前建议将 Fable 作为主模型，并将繁琐的工作交给 Opus 子代理，以节省 Fable 的使用量。现在 Opus 5.5 的标价仅为 Fable 5.1 的 40%，而且在基准测试中也领先：在 Artificial Analysis Intelligence Index 上得分为 58 vs 53，两者都达到最大努力。
When Opus 5 came out, I also said it had caught up with Fable, and before long I was back on Fable. This time the benchmarks and actual use agree. For my own writing, it's the most comfortable model since Opus 4.6. Even Fable doesn't match it.
当 Opus 5 发布时，我也说过它已经追上了 Fable，不久之后我又回到了 Fable。这次基准测试和实际使用情况一致。对于我自己的写作来说，这是自 Opus 4.6 以来最舒适的模型。即使是 Fable 也无法与之匹敌。
I'd run the main session on high with /effort high.
我会将主会话设置为高 /effort high。
Your subagents should switch too. I'd make Opus 5.5 at medium effort your default subagent: on the official coding eval, medium scores as well as max at less than a fifth of the cost. It's the most balanced setting in this release. Reading code, looking up docs, and running tests usually don't need more. Raise it for the ones that do.
你的子代理也应该切换。我会将 Opus 5.5 在中度努力下作为默认子代理：在官方编码评估中，中度努力的得分与最大努力相当，但成本不到五分之一。这是本次发布中最平衡的设置。阅读代码、查找文档和运行测试通常不需要更多。对于那些确实需要的，再提高难度。
Environment variable:
环境变量：
CLAUDE_CODE_SUBAGENT_MODEL=opus
CLAUDE_CODE_SUBAGENT_MODEL=opus
In each subagent definition:
在每个子代理定义中：
model: opus effort: medium
model: opus effort: medium
Anything using the opus alias upgrades automatically. Hard-coded model IDs don't. Hand this to Claude Code and have it review everything before changing anything 👇
任何使用 opus 别名的都会自动升级。硬编码的模型 ID 不会。将此交给 Claude Code，并在更改任何内容之前让它审查所有内容 👇
"Check this project, plus the settings, agents, and skills under ~/.claude:
"检查这个项目，以及 ~/.claude 下的设置、代理和技能：
1. For every subagent definition, change model to the alias opus and set effort to medium. List any subagents that need a higher effort level separately, with the reason. 2. Find hard-coded model IDs in AGENTS.md, CLAUDE.md, skills, and scripts, like claude-opus-5 and claude-fable-5-1. Switch the ones that can use the opus alias. Go through anything hard-coded to Fable one by one, and flag the ones you're unsure about for me to decide. 3. Check whether environment variables like CLAUDE_CODE_EFFORT_LEVEL are set. They override a subagent's own effort setting.
1. 对于每个子代理定义，将 model 改为别名 opus，并将 effort 设置为 medium。单独列出需要更高努力级别的任何子代理及其原因。 2. 在 AGENTS.md、CLAUDE.md、技能和脚本中找到硬编码的模型 ID，如 claude-opus-5 和 claude-fable-5-1。切换可以使用 opus 别名的那些。逐一检查硬编码为 Fable 的任何内容，并标记你不确定的那些让我决定。 3. 检查是否设置了 CLAUDE_CODE_EFFORT_LEVEL 等环境变量。它们会覆盖子代理自身的努力设置。
Show me the list and proposed changes first. Don't edit any files until I confirm. Finally, add a rule to AGENTS.md: if the same problem fails twice in a row, stop and tell me what you tried and why it failed, and I'll decide whether to switch to Fable."
先向我展示列表和拟议的更改。在我确认之前不要编辑任何文件。最后，在 AGENTS.md 中添加一条规则：如果同一个问题连续失败两次，停止并告诉我你尝试了什么以及为什么失败，我会决定是否切换到 Fable。"
After the changes, run /tasks to check which model each subagent is actually running.
更改后，运行 /tasks 以检查每个子代理实际运行的模型。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力