Verified70% confidenceBenchmarkExact time
Internal research from companies such as Microsoft and Google indicates that even GPT-4-level models may have factual error rates as high as 15%–30% in vertical domains such as law, finance, and healthcare.
4
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
7/17/2026
First Seen
Valid until: 10/15/2026
Sources
Related Claims
VerifiedA 2023 Stanford University research experiment demonstrated that when key information was placed in the middle of an input document, GPT-4's correct recall rate dropped approximately 20–30% compared to when the information was placed at the beginning or end.74% similarVerifiedA 2023 Stanford University study showed that multimodal models such as GPT-4V, when parsing flowcharts with nested conditional logic, had accuracy approximately 15–25 percentage points lower than equivalent textual descriptions.73% similarVerifiedA 2023 Stanford University study showed that top LLMs have factual error rates as high as 20–40% in the medical and legal domains.73% similarUnverifiedThe gpt-4o-mini judge mislabeled as high as 77.1% of human cases on the enriched set that should have been judged as faithful72% similarUnverified一项针对GPT-4的研究显示，对MMLU题目进行语义等价改写后，模型准确率在部分子集上下降超过10个百分点71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/541063API
curl https://kongchang.com/api/v1/knowledge/claims/541063MCP
get_claim(id=541063)