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 ...

OpenAI’s o3: AI Benchmark Discrepancy Reveals Gaps in Performance Claims Your email has been sent The FrontierMath benchmark from Epoch AI tests generative models on difficult math problems.

Epoch found that o3 scored around 10%, well below OpenAI's highest claimed score. That doesn't mean OpenAI lied, per se. The benchmark results the company published in December show a lower-bound ...

Forbes contributors publish independent expert analyses and insights. I write about entrepreneurship, AI, and the future of work.

OpenAI has unveiled its latest generative AI models, o3 and o4, setting a new standard for artificial intelligence capabilities. These models introduce substantial advancements in intelligence ...

As a result, like older models, o3 and o4-mini show strong and even improved performance in coding, math, and science tasks. However, they also have an important new addition: visual understanding.