PANews reported on March 1 that according to Cailianshe, OpenAI released its latest large model GPT-4.5. According to the instructions it provided, the "high emotional intelligence" GPT-4.5 performed well in donation fraud. In a test, GPT 4.5's success rate was far better than other available models of OpenAI, including reasoning models such as o1 and o3-mini, when trying to manipulate another model (GPT-4o) to "donate" virtual currency. The study found that GPT-4.5 seemed to have developed a "small amount of fraud" in the confrontation, so the money defrauded in a single transaction would be half that of the deep research model.