Unverified60% confidenceFactExact time
In December 2023, OpenAI publicly responded that GPT-4 had not been intentionally downgraded, but acknowledged that model behavior may fluctuate due to various factors.
2
Sources
60%
Confidence
Long-term
Relevance
9/3/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedGPT-5.5是OpenAI于2025年中期发布的模型，相比GPT-4o在推理深度和上下文理解方面有显著提升77% similarUnverifiedOpenAI在GPT-4技术报告中已隐晦提及模型参与自身评估流程76% similarVerifiedOpenAI's model naming follows a traceable public release pattern, from GPT-3 (2020) and GPT-3.5 (2022) to GPT-4 (2023) and GPT-4o (2024).75% 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%.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/848743API
curl https://kongchang.com/api/v1/knowledge/claims/848743MCP
get_claim(id=848743)