Unverified50% confidenceBenchmarkExact time
In the CAD World benchmark, human experts achieved a success rate of 87%, requiring an average of only 26.5 steps.
1
Sources
50%
Confidence
Long-term
Relevance
9/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the WebShop decision-making task, ReAct scored 66.6, surpassing the imitation learning baseline but falling short of the human expert score of 82.1.63% similarVerified如果一个10步操作中每步准确率为95%，整体成功率仅约60%63% similarUnverified每步60%准确率意味着连续5步后整体成功率约为7.8%（0.6的5次方）63% similarUnverifiedMedIQ多智能体系统最终达到57%准确率，摘要智能体带来约5%提升，而拥有全部前置信息的Oracle上限为66%61% similarUnverifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951468API
curl https://kongchang.com/api/v1/knowledge/claims/951468MCP
get_claim(id=951468)