He's just using the P4 because it has the longest mis-predict penalty of any recent mass produced CPU. I'd guess that the Mill is going to be clocked fairly slow given the cycle latency numbers I'm seeing so I wouldn't be surprised if the Mill's 5 cycle mis predict penalty came out to the same time delay as a 10 cycle penalty on a Sandy Bridge.

It was given for dramatic effect, as he adds, the Prescott had an extremely long pipeline.

It's not really relevant to compare to other more modern processors, because those both exist and have a traditional architecture. The Mill both does not exist and does not have a traditional architecture (at least in the prediction regard).