Verified75% confidenceFactExact time
Stanford University once published a research report documenting performance fluctuations of GPT-4 on specific tasks across different time periods.
5
Sources
75%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
Codex入门指南：与Claude Code的全面对比及选型建议
bilibiliai大模型-教程7/8/2026
Related Claims
VerifiedA 2023 Stanford University study found that GPT-4's performance on certain tasks showed a measurable decline over several months.85% similarUnverifiedA 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.79% 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%.77% 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.76% similarUnverified斯坦福的Alpaca以GPT-3.5蒸馏LLaMA，Microsoft的Orca系列以GPT-4蒸馏小模型，验证了高质量轨迹数据对小模型能力迁移的有效性74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/501087API
curl https://kongchang.com/api/v1/knowledge/claims/501087MCP
get_claim(id=501087)