GPT-5.5 hallucination rate reaches 86%, GLM-5.2 only 28% -- larger models are less reliable
GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open arrowtsx.dev original