Unverified50% confidenceFactExact time
A gap exists between high scores on internal evals and real-world performance; the Vercel team achieved 30% on evals but received poor real-user feedback.
1
Sources
50%
Confidence
Long-term
Relevance
9/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedResearch indicates that consumer satisfaction with customer service replies that are clearly AI-generated is on average 20%–30% lower than with human replies.66% similarUnverifiedThe same model may rank very differently across different evaluation platforms.63% similarUnverified当相关文档被放置在上下文中间位置时，模型正确回答率相比放在首尾位置下降高达20-30个百分点63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/924269API
curl https://kongchang.com/api/v1/knowledge/claims/924269MCP
get_claim(id=924269)