Unverified50% confidenceBenchmarkExact time
Context Mode's claimed 98% context reduction has no independent third-party verification; its self-tested Benchmark averages 96%, with a worst case of only 13%, and users generally perceive it as between 30% and 40%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
UnverifiedAfter introducing Feature Scope, the verified assertion output rate rose from about 20% to 95%, erroneous feature assertions dropped to 0, and model restraint reached 30/30.69% similarUnverifiedWhen users presented a wrong answer as a confident statement and pushed twice, the model persistence rate dropped from 94.4% to 84.0%.65% similarUnverifiedA global 99.9% availability figure often masks the fact that a particular model being called frequently fluctuates.65% similarUnverifiedThe churn rate during the user onboarding phase is typically as high as 40–60%.64% similarUnverified业界1-9-90法则指出只有1%的用户积极创作，9%偶尔参与，90%只是旁观63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1024496API
curl https://kongchang.com/api/v1/knowledge/claims/1024496MCP
get_claim(id=1024496)