Elon Musk· @elonmusk · X·· 2026-07-11AI 评分50
AI 导读
Elon Musk 发推称，Grok 在真实世界软件工程基准上排名第二，仅次于 Fable。xAI 的 Grok 4.5 在 APEX-SWE 排行榜上以 51.2% Pass@1（±6.0）位列第二，领先于 Fable 5（65.5% ±6.2）。Grok 4.5 在 Integration（集成）子项以 65.0% Pass@1 排名第一，在 Observability（可观测性）以 37.3% Pass@1 排名第二。该集成优势对应 Grok 4.5 专为与 Cursor 协作的多步骤编码智能体工作流而设计。一年内，Grok 模型在该基准上提升了 30.2 个百分点（从 Grok 4 的 21.0% 到 Grok 4.5 的 51.2%）。
正文 · 原文
Grok places second after Fable on real-world software engineering
Grok 4.5 from @SpaceXAI places #2 on the APEX-SWE leaderboard at 51.2% Pass@1 (±6.0), behind Fable 5 (65.5% ±6.2) on our benchmark for real-world software engineering work. It leads Integration (65.0% Pass@1) and places #2 in Observability (37.3% Pass@1), covering multi-step build tasks and diagnosis/debugging respectively. The Integration lead maps directly to the agentic workflows Grok 4.5 was built for: multi-step coding tasks run in collaboration with Cursor. Grok models have improved 30.2 pp in a year on this benchmark: Grok 4 (21.0% Pass@1) to Grok 4.5 (51.2% Pass@1). Congratulations to the xAI and Cursor teams.在 X 查看被引用的帖子
来源：Elon Musk · x.com