Is it real? Edit: How much better is Claude Fable 5 vs. Opus 4.8? (Anthropic’s launch benchmarks, June 9, 2026) • SWE-Bench Pro (agentic coding): 80.3% vs. 69.2% for Opus 4.8 • FrontierCode Diamond: 29.3% vs. 13.4% — more than double • Core pattern: the longer and more complex the task, the larger Fable 5’s lead; on short, well-scoped tasks the two are much closer In practice: noticeably better on long multi-step work (migrations, feature builds, complex pipelines); barely different for quick, simple tasks. Caveat: these are Anthropic’s own benchmarks — directionally correct, but vendor numbers.