Unverified50% confidenceBenchmarkExact time
In tests across six languages—English, Chinese, Hindi, Arabic, Japanese, and Korean—prediction loss drops from an initial ~8 bits/byte to 0.9–2.4 bits/byte after reading one million bytes.
1
Sources
50%
Confidence
Long-term
Relevance
10/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModels exhibit significant performance degradation on East Asian languages (such as Chinese, Japanese, and Korean) when faced with distorted statements, with cross-lingual performance gaps of up to 28 percentage points and relative drops as high as 49%68% similarUnverifiedCharacter sets such as Chinese and Japanese appear less frequently in training sets dominated by English corpora, and often consume 1–2 tokens per character.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/980592API
curl https://kongchang.com/api/v1/knowledge/claims/980592MCP
get_claim(id=980592)