Unverified50% confidenceBenchmarkExact time
Research shows that even the most advanced current models can still have hallucination rates reaching double-digit percentages in certain domains
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/22/2026
First Seen
Valid until: 12/21/2026
Sources
Related Entities
Related Claims
VerifiedResearch shows that even the most advanced models have hallucination rates in factual question-answering tasks that still fluctuate between 5% and 20%.79% similarUnverified早期模型在某些领域的事实幻觉率高达15-25%，尤其在长尾知识领域幻觉率更高71% similarUnverifiedResearch data indicates that when generated text exceeds 2,000 tokens, the hallucination rate may be 2–3 times higher than in short responses.71% similarUnverified研究人员发现部分幻觉包名在10%以上的测试中反复出现，同一模型在相似提示下往往产生相同幻觉71% similarUnverifiedIn multiple benchmarks, even the most advanced models can have hallucination rates of 15%–30% in specialized technical domains.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/940171API
curl https://kongchang.com/api/v1/knowledge/claims/940171MCP
get_claim(id=940171)