Verified70% confidenceFactExact time
A 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.
4
Sources
70%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
Unverified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79% similarVerifiedA 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.78% similarUnverifiedSmall language models of about 7 billion parameters (such as allam-2-7b) are markedly weaker than GPT-4-level models in instruction following, long-context reasoning, and self-awareness, and are prone to hallucinating or ignoring negative constraints.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/533810API
curl https://kongchang.com/api/v1/knowledge/claims/533810MCP
get_claim(id=533810)