Unverified50% confidenceFactExact time
当前最优模型在 WebArena、Mind2Web 等基准测试上的任务完成率通常在 20%-40% 之间
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
OpenAgent：基于LLM+RAG的开源AI个人助手深度解析
githubthe-open-agent6/10/2026
Related Claims
Unverified当前最先进的GUI Agent在WebArena等评测中的任务完成率通常在20%-40%之间77% similarUnverified研究表明高质量提示词相比随意撰写的提示词在同等模型条件下可带来20%-40%的任务完成率提升73% similarUnverifiedAccording to the OSWorld benchmark, the most advanced Computer Use models still achieve less than 40% task success rate71% similarUnverified有研究表明，针对同一任务精心设计的上下文可将任务完成率提升40%以上70% similarUnverified高质量的Prompt工程能在不增加模型参数的前提下将任务成功率提升20%~40%70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49344API
curl https://kongchang.com/api/v1/knowledge/claims/49344MCP
get_claim(id=49344)