AI is making performance easier to measure than ever. Deciding what that performance is worth is still up to people.

Researchers behind a new study say that the methods used to evaluate AI systems’ capabilities routinely oversell AI performance and lack scientific rigor. Subscribe to read this story ad-free Get ...

You often hear chief compliance officers speak about benchmarking. CCOs often reveal their competitive streaks when they collect information about other companies’ compliance programs. It can easily ...

NIST evaluation reveals Chinese AI leader DeepSeek V4 Pro trails US frontier models by 8 months in performance benchmarks. The assessment marks the first concrete measurement of the US-China AI ...

WPP is shifting to a pay-for-performance revenue model. But there are many barriers to clear before PFP becomes the industry ...