Unverified60% confidenceBenchmarkExact time
A 2023 Stanford University study found that GPT-4's accuracy on open-domain question-answering tasks was approximately 40 percentage points higher than that of traditional NLU systems.
2
Sources
60%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
Related Claims
UnverifiedWhen OpenAI's API endpoint names remain unchanged, the underlying model weights may be silently updated; a 2023 joint study by Stanford and UC Berkeley found significant performance differences in GPT-4's responses to the same prompts across different time periods, with accuracy on certain tasks dropping sharply from 97% to 2%.79% similarVerifiedStanford University once published a research report documenting performance fluctuations of GPT-4 on specific tasks across different time periods.79% 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%76% similarVerifiedA 2023 Stanford University study found that GPT-4's performance on certain tasks showed a measurable decline over several months.75% similarUnverifiedA 2024 study from UC Berkeley found that in complex multi-step tasks, GPT-4-level models exhibited tool-call hallucinations at a rate as high as 12%–18%.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/492616API
curl https://kongchang.com/api/v1/knowledge/claims/492616MCP
get_claim(id=492616)