Probing GPT-5 and Opus reveals their hidden training timelines

Exploring Claude/GPT Knowledge Cutoffs and Pre-Training Timelines

By quizzing frontier models on daily Wikipedia facts, I estimated the knowledge cutoffs of GPT-5.6, Opus 4.7+, and others. The results suggest Anthropic's Opus 4.7 through Opus 5 all share the same pre-training cutoff, while OpenAI's GPT-5.6 family comes from a separate, later checkpoint. I also asked models what date they think it is and what they think they're called, revealing that some Anthropic models self-identify as GPT-4 and that vertical bands in the data hint at training on past model outputs.