精选理由
Cursor 推出了 Claude Fable 5.1，在编程基准测试中得分 73.4%，能独立完成复杂代码任务。
Claude Fable 5.1 已在 Cursor 平台上线。该模型在 CursorBench 3.2 基准测试中得分为 73.4%。Claude Fable 5.1 特别擅长验证自身工作，能够处理从开始到结束的复杂编程任务。
原文 · Cursor
Claude Fable 5.1 is now available in Cursor! It's the most capable model we’ve run on CursorBench 3...
Claude Fable 5.1 is now available in Cursor! It's the most capable model we’ve run on CursorBench 3.2, scoring 73.4% at max effort. We found it especially skilled at verifying its own work, allowing it to take on difficult coding tasks from start to finish. 💬 67 🔄 52 ❤️ 1058 👀 26694 📊 164 ⚡