智譜推出新一代旗艦模型GLM-5,參數規模擴展至744B,預訓練數據達28﹒5T
,集成DeepSeek稀疏注意力機制。其引述內部評估顯示,其編程任務性能較上代提升超
20%,真實體驗逼近ClaudeOpus4﹒5;在BrowseComp等三項
Agent評測中均獲開源
Please share this article if you like it!
Our site uses cookies. By using this site, you agree to the Privacy Policy and Terms of Use.