Nice refutation. The problem about doing language comparisons for speed is that they generally require a non-trivial example, so you have to be an excellent programmer in all the languages you've compared.
Of course, language speed charts are generally as useful as PC spec charts and YouTube videos of Nürburgring laptimes when you're buying a new car.
well, what about an existing piece of software, and compare on more than just speed, but ease of maintenance (meaning, how quickly you can add features or fix a bug)?
There seems to be a myriad of window managers and web frameworks. Someone should do an unbiased comparison.
Same thing again, it depends entirely on really specific domain logic. How easy it is to add a new feature on a C based web browser versus one built on Haskell is mostly useless, it just tells you how quickly one person added one feature on one specific thing.
Languages aren't inherently comparable, you can get useful benchmarks but they shouldn't be taken as gospel.
Of course, language speed charts are generally as useful as PC spec charts and YouTube videos of Nürburgring laptimes when you're buying a new car.