Expired50% confidenceBenchmarkExact time
DeepSeek's hallucination-related score is only about 9%, while GLM 5.3 Flash scores as high as 72% (higher is better).
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
9/11/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/25/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedThe DeepSuite benchmark has a false positive rate of 44.9% and a false negative rate of 1.2%.67% similarUnverified在GPQA V2版本测试中，Glimmer的幻觉率高达82%65% similarUnverifiedQwen3.8 Flash Next has a sparsity rate of approximately 95%, using less than 5% of its parameters per inference.65% similarVerifiedDuring the autoregressive decoding phase, GPU compute utilization is often less than 10%, making it a memory-intensive operation.61% similarUnverifiedMuse Glimmer在Artificial Analysis第二版测试中幻觉率高达82%，知识工作和幻觉是其最大弱点61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/896150API
curl https://kongchang.com/api/v1/knowledge/claims/896150MCP
get_claim(id=896150)