Verified65% confidenceBenchmarkExact time
Stanford University published a 2023 study titled "How Is ChatGPT's Behavior Changing over Time?", experimentally demonstrating that different deployed versions of the same model can show significant fluctuations of 10% to 20% in pass rates on tasks such as code generation and logical reasoning.
3
Sources
65%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
Unverified该研究发现同一模型不同部署时间点在代码生成和逻辑推理任务上通过率可能出现10%至20%的显著波动，且方向不总是单向改善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.66% similarUnverified斯坦福大学2023年的研究表明，引入明确的需求分析和设计阶段后，LLM生成代码的功能正确率提升约30%63% similarUnverified斯坦福的一项研究发现，71%人们向ChatGPT提出的问题可以由本地运行的模型来回答62% similarUnverified2024年一项研究对GPT-4在Temperature=0下的代码生成任务进行100次测试，发现约8%的测试用例存在跨次运行的输出差异62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/593812API
curl https://kongchang.com/api/v1/knowledge/claims/593812MCP
get_claim(id=593812)