A discrepancy between first- and third-party benchmark results for OpenAI's o3 AI model is raising questions ... a challenging set of math problems. That score blew the competition away ...

Large artificial intelligence (AI) models may mislead you when pressured ... [a term for the most cutting-edge models] obtain high scores on truthfulness benchmarks, we find a substantial ...

But AI companies generally haven’t customized or otherwise fine-tuned their models to score better on LM Arena — or haven’t admitted to doing so, at least. The problem with tailoring a model ...

A discrepancy between first- and third-party benchmark results for OpenAI’s o3 AI model is raising questions about the company’s transparency and model testing practices. When OpenAI unveiled ...

Epoch AI, the research institute behind FrontierMath, released results of its independent benchmark tests of o3 on Friday. Epoch found that o3 scored around 10%, well below OpenAI's highest claimed ...