5.1 is astonishingly bad. Besides the 4o-levels of sycophancy, I've also seen it form grammatically incorrect sentences in German.
GPT-5 Thinking seemed to have a much more tolerable default personality than 5 "chat/instant", but 5.1 seems a bit broken across the board. Reasoning capabilities also seem somewhat weaker.
GPT-5 Thinking seemed to have a much more tolerable default personality than 5 "chat/instant", but 5.1 seems a bit broken across the board. Reasoning capabilities also seem somewhat weaker.