Expired50% confidenceBenchmarkExact time
Google DeepMind's FactScore shows that GPT-4's proportion of accurate factual statements in biographical generation tasks is approximately 73%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/12/2026
First Seen
Valid until: 10/10/2026(expired)
Sources
Zuckerberg Admits AI Progress Falls Short of Expectations: The Industry Truth Behind the Layoffs
bilibili小溪_YouTube搬运笔记本7/8/2026
Related Claims
Unverified谷歌DeepMind的研究发现GPT类模型在特定提示条件下可精确复现训练集中约1%的文本片段75% similarUnverifiedGPT-4在面对包含5个以上具体领域细节的提示时，任务完成率比模糊提示高出约40%74% similarUnverifiedOptimized prompts can improve GPT-4's accuracy on specific tasks from 60% to above 95%.72% similarUnverifiedGPT-5.4 scored 92.8% on Online Mind2Web using screenshot observation alone, while ChatGPT Atlas in agent mode achieved only 70.9%.72% similarVerifiedEven top-tier models like GPT-4 can have hallucination rates of 15%–30% in specific domains.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/489817API
curl https://kongchang.com/api/v1/knowledge/claims/489817MCP
get_claim(id=489817)