OpenAI delivered advanced ChatGPT reasoning models this month that are more capable than o1, but they also hallucinate more.

OpenAI released its new o3 and o4-mini reasoning models, which perform significantly better than their o1 and o3-mini ...

OpenAI says its latest models, o3 and o4-mini, are its most powerful yet. However, research shows the models also hallucinate ...

By OpenAI 's own testing, its newest reasoning models, o3 and o4 -mini, hallucinate significantly higher than o1.

You would think that the number of hallucinations would decrease over time, but according to internal tests from Open AI, the ...

OpenAI's latest AI models tend to make things up — or "hallucinate" — substantially more than earlier versions.

OpenAI's reasoning AI models are getting better, but their hallucinating isn't, according to benchmark results.

OpenAI unleashed a flurry of new ChatGPT variants over the week, each featuring interesting new features and very confusing ...

Historically, each new generation of OpenAI's models has delivered incremental improvements in factual accuracy, with ...

OpenAI's o3 and o4-mini models introduce breakthrough image reasoning for enhanced performance in reasoning, visual, and ...