Unverified50% confidenceFactExact time
In 35.5% of failure cases, the key facts needed to complete the task had already appeared in the model's last input before its cutoff time.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedIn long-chain tasks, if each step has an error rate of approximately 5%, the overall success rate may drop to below 36% after 20 steps.70% similarUnverified'99% 准确率'的模型在生产环境中仍可能频繁出错，因为剩余的 1% 往往对应现实中最关键的长尾细节场景69% similarUnverifiedEnd-to-end task completion rate is very likely to become a more practically valuable model evaluation metric than benchmark scores.68% similarUnverified根据SWE-RPG基准论文，46.7%的代理失败发生在规划和需求分析阶段68% similarUnverifiedThe oracle router knows in advance which cases the small model will get wrong, sends only the wrong requests to the large model, and achieves accuracy comparable to always using the large model at only 29% of the cost.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1078895API
curl https://kongchang.com/api/v1/knowledge/claims/1078895MCP
get_claim(id=1078895)