CodeRabbit 官方最新动态：Claude Opus 5.5 for code review: More catches, different misses

来源：CodeRabbit 官方动态 | 发布日期：2026-09-18

核心更新概览

Anthropic just released Claude Opus 5.5, the first model in the Claude 5.5 family, and we put it through CodeRabbit's AI code review pipeline to see what changed. In our

详细内容记录

Anthropic just released Claude Opus 5.5, the first model in the Claude 5.5 family, and we put it through CodeRabbit's AI code review pipeline to see what changed. In our , higher precision came at the expense of catching fewer known bugs. Opus 5.5 produced a different result. It edged past our production baseline on bug coverage in the open-source test and made larger gains in both coverage and precision on a smaller set of harder cases. Those gains also brought more comments and higher reported token usage. The adoption question for teams is whether the additional catches justify the extra review work, and which bugs the model misses in return. We also explored Opus 5.5’s coding abilities through an overnight project and hands-on gaming experiments inspired by What's new in Anthropic's Claude Opus 5.5 Opus 5.5 brings lower token prices, changes to reasoning and tool use, and reported improvements in coding and communication. Compared with Opus 5, five changes are important for teams building code-review workflows: Stronger coding performance at lower effort. Opus 5.5 at medium effort matched or beat Opus 5 at high effort on multi-step coding tasks, using roughly half the tokens. Input pricing falls from $5 to $4 per 1 million tokens, and output pricing from $25 to $20, a 20% reduction. Cache reads drop 60%, to $0.20 per 1 million tokens. That lowers the price of equivalent usage, but the cost of a completed review still depends on how many tokens and calls it takes.

更多技术细节可访问官方原文：https://www.coderabbit.ai/blog/opus-5-5-model-review。