[KongchangAI]
Unverified50% confidenceFactExact time

Jev's performance gap in the short name scenario does not follow writing system: Russian and Chinese are on par with English, while Latin-script languages such as German, French, Dutch, Hungarian, Finnish, and Turkish lag behind.

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/13/2026
First Seen
Valid until: 1/11/2027

Sources

Cheap AI Moderation Model Tested in 25 Languages: Holds Up on Long Text, Falls Apart on a Single Dirty Word

Related Entities

Jevmodel

Related Claims

UnverifiedIn the short name field test, Jev caught 21 of 27 verified terms in English, Spanish, Russian, Japanese, and Chinese, while gpt-5-mini caught 25; in the other 16 languages Jev caught only 15 of 80, while gpt-5-mini caught 53.71% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/1015390
API
curl https://kongchang.com/api/v1/knowledge/claims/1015390
MCP
get_claim(id=1015390)