Grok 4.5登顶AutomationBench-AA榜单
2026-07-09 07:36:20
Artificial Analysis的AutomationBench-AA榜单显示,Grok 4.5以51.4%的得分排名第一,单任务成本为0.34美元。据 NS3 报道,该模型在该榜单上超过Claude Fable 5和Claude Opus 4.8,但其防护栏违规次数高于最接近的竞争对手。
Disclaimer:
1. The information provided does not constitute investment advice. Investors should make independent decisions and bear all risks themselves.
2. The copyright of this content belongs to the original author. The views expressed herein are solely those of the author and do not represent the stance or position of this website.
Next article:
商务部:消费“三新”试点收集项目超6000个