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

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

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

Comparing AI reasoning abilities reveals OpenAI's o1 model surpasses DeepSeek's R1 in generating accurate, sentence-level ...

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

Metr, a frequent OpenAI partner, suggested in a blog post that it wasn't given much time to evaluate the company's powerful ...

AI models are numerous and confusing to navigate, but the benchmarks used to measure their performance are also challenging.

According to OpenAI’s internal testing, the new o3 model hallucinated in 33% of cases on the company’s PersonQA benchmark.

OpenAI’s newest reasoning models, o3 and o4‑mini, produce made‑up answers more often than the company’s earlier models, as ...

Wei and team don't directly offer any hypothesis about why Deep Research fails almost half the time, but the implicit answer ...

On Wednesday, OpenAI announced the release of two new models—o3 and o4-mini—that combine simulated reasoning capabilities ...

OpenAI’s o3 model is under scrutiny after third-party tests revealed far lower performance than previously claimed.