Verified70% confidenceFactExact time
A 2023 Stanford University study found that GPT-4's performance on certain tasks showed a measurable decline over several months.
4
Sources
70%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
VerifiedStanford University once published a research report documenting performance fluctuations of GPT-4 on specific tasks across different time periods.85% similarVerifiedA 2023 study by Chen et al. at Stanford University confirmed that GPT-4 exhibited significant fluctuations in mathematical reasoning ability over the course of several months.82% similarUnverifiedWhen 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% similarUnverifiedResearchers including Tal Ullman at New York University found that GPT-4's performance dropped sharply when classic theory-of-mind tests were modified slightly, suggesting the model may be performing surface-level pattern matching.77% similarVerifiedStanford University published a paper in July 2023 titled "How Is ChatGPT's Behavior Changing over Time?" finding that GPT-4's behavioral performance underwent significant and quantifiable changes between March and June 2023.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/538871API
curl https://kongchang.com/api/v1/knowledge/claims/538871MCP
get_claim(id=538871)