GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2, challenging the bigger-model dogma
GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2
The author benchmarks GPT-5.5, DeepSeek V4 Pro, and GLM-5.2 on the AA-Omniscience hallucination metric and a Python async coding prompt. GPT-5.5 hits 86% hallucination, DeepSeek V4 Pro 94%, while GLM-5.2 scores 28%. DeepSeek V4 Pro spent nearly 4 minutes and 7.7k reasoning tokens producing a confidently wrong solution; GLM-5.2 needed 12 seconds and ~800 tokens to flag the prompt as technically impossible under single-threaded, no-polling constraints. GLM-5.2 trails GPT-5.5 by only 4 points on the AA Intelligence Index and Claude Fable 5 by 9 points—Fable 5 was restricted by the US government three days post-launch over a single jailbreak. The post argues that scaling parameters and data makes models worse at saying “I don’t know,” and frames an unsolved trilemma: raw capability, hallucination calibration, and compute efficiency. The article does not disclose GLM-5.2’s training data size or exact release date.
Why it matters: A personal blog compares three models on the AA-Omniscience benchmark: GPT-5.5 hallucinates 86% of the time, DeepSeek V4 Pro 94%, and open source GLM-5.2 only 28%, giving one concrete side-by-side reference.