精选理由
Claude Fable 5新版被砍了，调试分从86掉到26，重构分从73掉到38，你该看看这个评测。
BridgeMind对Claude Fable 5（7月1日版本）在BridgeBench上重新测试，发现调试得分从86.2降至25.9，重构得分从73.6降至38.4，幻觉得分从75.9降至61.7。新护栏导致过多任务回退到Opus 4.8。用户质疑该模型与最初被禁用的版本不同。
原文 · AI Will
源：https://t.co/eedCPtGJfm
源： x.com/bridgemindai/s… BridgeMind @bridgemindai FABLE 5 CAME BACK NERFED. We re-ran the July 1st version of Claude Fable 5 on BridgeBench. The results are brutal: Debugging: 86.2 → 25.9 Refactoring: 73.6 → 38.4 Hallucination: 75.9 → 61.7 The new guardrails are kicking in on way too many tasks and falling back to Opus 4.8. This is not the model that got banned. Anthropic owes everyone an explanation. 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 457 ⚡