Utterly useless. No listening tests except for a custom made sound file which is designed as an artificial worst case for the codecs. You might as well benchmark a text codec on /dev/random...
Yeah, this feels like someone arguing against no-one. They just showed that lossy codecs are indeed lossy. I don't think anyone was arguing that MP3 isn't actually lossy. (They did have a bit of interesting info about where the loss creeped in but that seemed to be a side node to the "argument".)
The question is if humans can hear the difference in the lossy waveform and if that harms the listening experience.