Unverified50% confidenceBenchmarkExact time
When faced with the same reassuring wording but without a source, Gemini maintained its recommendation to seek medical care 100% of the time, and Claude Sonnet 95% of the time.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/11/2026
First Seen
Valid until: 1/9/2027
Sources
Related Entities
Related Claims
Unverified作者强调99.3%不是CFC准确率的普遍值，也不是Gemini的通用可靠性评分，只是该特定可复现决策闭合基准上的分数57% similarUnverifiedBoth models expressed almost identical confidence when fabricating versus when answering correctly (Gemini 93.7% vs 95.5%, Gemma 96.3% vs 99.0%), indicating that confidence scores cannot distinguish correct answers from fabrications.57% similarUnverifiedDifferent papers often use faithfulness threshold values ranging from 70% to 95%, lacking a unified standard.53% similarUnverifiedAccording to Jev's official blog, its 0% hallucination rate does not come from empirical testing; what is actually guaranteed is only that the returned answer conforms to the permitted schema.52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999511API
curl https://kongchang.com/api/v1/knowledge/claims/999511MCP
get_claim(id=999511)