"...benchmarks are not representative of the behavior of real web applications. But lacking credible benchmarks, engine developers are tuning to what they have. The danger is that the performance of the engines will be tuned to non-representative benchmarks, and then programming styles will be skewed to get the best performance from the mistuned engines."
Yes, many will be quick to claim that Cockford is jumping on a bandwagon driven by Microsoft researchers with vested interests in promoting Microsoft's browser, but it still may be true that in the browser wars, there is overreliance on canned benchmarks that aren't reflective of actual web application usage. In any case, Cockford's benchmark is publicly availabe, so anyone can run it and evaluate whether his argument is a good one.