[KongchangAI]
Unverified50% confidenceFactExact time

OSWorld 2.0团队自托管了31个任务相关网络服务以确保测试环境可复现

1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen

Sources

OSWorld 2.0测评:最强AI Agent完成率仅20%,长流程是致命短板
bilibili熊二等兵7/1/2026

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/338171
API
curl https://kongchang.com/api/v1/knowledge/claims/338171
MCP
get_claim(id=338171)