16:11
2026-06-19
arrowtsx.dev
large-language-models
GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2
New benchmarks reveal that larger AI models like GPT-5.5 and DeepSeek V4 Pro hallucinate significantly more than smaller open-weight models, with GLM-5.2 achieving a 28% hallucination rate compared to…