Unverified50% confidenceFactExact time
在OSWorld 2.0最长的工作流中AI完成率几乎降至0，完成率对任务长度极其敏感
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
Unverified主流AI代理完成OSWorld 2.0每个任务平均需要超过300步，而1.0版本只需30步左右72% similarUnverifiedTypical failure patterns of AI Agents on complex tasks include: performing well in the first ten minutes, drifting off target after half an hour, and producing completely unusable output after two hours.70% similarUnverified以Mythos Preview为例，成功率在4小时任务节点开始显著下滑，且在15分钟内的短任务中某些类别模型也无法稳定完成66% similarUnverifiedThe generation speed of an MVP (Minimum Viable Product) in AI-assisted development has been compressed from days to minutes.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/338180API
curl https://kongchang.com/api/v1/knowledge/claims/338180MCP
get_claim(id=338180)