IMHO, any benchmark should run with Turbo disabled. And come with additional tests about how much turbo brings, and how long it can stay on within a given thermal setup. Otherwise all you have is garbage, not data.
Complex devices need complex benchmarking, unfortunately. You won't get a simple, single number that shows how powerful a cpu is.
This is the gist of my comment (see after the first phrase), so I think we agree.
Good CPU reviews include long render and compile benchmarks that would suffer if the turbo performance couldn’t be sustained. If a CPU can sustain high performance, then it doesn’t matter if it’s using a turbo mode.
In addition, recent CPUs will use this thermal headroom to the limit.