Skip to content
ThreadOut
ClaudeDevs@ClaudeDevs · May 28, 2026

Opus 4.8 is live in Claude Code today. A few things worth knowing: 🧵

6 tweets1 min read♥ 10.1Koriginal

Summary

Anthropic released Opus 4.8, a new version of Claude that improves code generation performance to 69.2% on SWE-bench Pro and is four times less likely to miss code flaws compared to Opus 4.7. The model defaults to high effort, supports an xhigh effort level for difficult tasks, and integrates with Claude Code's /goal feature and Outcomes for better long-horizon work.

Summarized by ThreadOut AI from the full thread. May miss nuance — read the thread below.

  1. #1

    Opus 4.8 is live in Claude Code today. A few things worth knowing: 🧵

    Claude@claudeai · May 28, 2026

    Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.

  2. #2

    Opus 4.8 hits 69.2% on SWE-bench Pro, up from 64.3% on Opus 4.7. Our evaluations show that Opus 4.8 is around four times less likely than Opus 4.7 to allow flaws in code it has written to pass unremarked.

  3. #3

    Opus 4.8 defaults to high effort. For coding tasks, it spends similar tokens to the 4.7 default while delivering better performance. For difficult tasks and long-running async work, use xhigh. We’ve increased rate limits in Claude Code to accommodate the increased token usage.

  4. #4

    Opus 4.8 is especially strong at long-horizon work. In Claude Code, pair it with /goal. If you're building on Claude Managed Agents, try it with Outcomes.

  5. #5

    We’ve updated Claude Code's built-in claude-api skill migration guidance for 4.8. Run "/claude-api migrate" to update your model strings and suggest prompt improvements that are tuned for Opus 4.8.

  6. #6

    See our prompting guide for more tips and best practices for working with Opus 4.8: platform.claude.com/docs/en/build-…