The FrontierMath benchmark from Epoch AI tests generative models on difficult math problems. Find out how OpenAI’s o3 and ...

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

A discrepancy between first- and third-party benchmark results for OpenAI's o3 AI model is raising questions about the ...

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

OpenAI released upgraded versions of its advanced reasoning models. These new models, named o3 and o4-mini, offer ...

OpenAI unveiled o3 and o4-mini, its latest AI models. Both of them have advanced image analyzation capabilities – and excel ...

OpenAI touts o3 as a smart AI model with the ability to reason (meaning it can recursively check its answers before giving ...

When ChatGPT first arrived towards the end of 2022, it felt like a seismic shift in tech. Then came GPT-3, 3.5, 4o, and so ...

The rumored product centers on ChatGPT's new image generator, and could bring in much-needed data and subscription revenue.