Unverified50% confidenceBenchmarkExact time
In tests with five-minute segments of pure silence as input, Moshi exhibited inappropriate speech onset in 12 out of 40 tests, and PersonaPlex in 11 out of 40.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
Unverified运行10次测试置信区间宽度约±31%，100次收窄至±10%，400次进一步收窄至±5%，推荐关键测试用例至少运行20-50次65% similarUnverifiedThe user pointed out that these models achieve high scores on benchmarks yet frequently fail at the simplest tasks.64% similarUnverifiedIn the LongMemEval benchmark, BM25 and embedding solutions converge to approximately 95% accuracy at 20 chunks60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921846API
curl https://kongchang.com/api/v1/knowledge/claims/921846MCP
get_claim(id=921846)