Unverified50% confidenceBenchmarkExact time
The open-source judgment model's Chinese capability score is 20 out of a maximum of 64 points.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
Partially VerifiedA 2023 study by Stanford University's Nelson Liu and colleagues found that when key information is placed in the middle of a long context, model performance can drop by more than 20%.64% similarUnverifiedAccording to shared data, Shenzhen's government affairs Q&A system reduced the time needed to handle matters by more than half, with an answer accuracy rate exceeding 95%.62% similarUnverified一项统计显示全球顶尖20%的AI研究者中约47%出生于中国62% similarUnverifiedCompanies including DoorDash, Siemens, and Airbnb have begun adopting lower-cost Chinese open-weight models, and in some cases the share of queries directed at closed-source proprietary models has dropped from around 60% at the beginning of the year to one quarter.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/950985API
curl https://kongchang.com/api/v1/knowledge/claims/950985MCP
get_claim(id=950985)