Dankpods used 12 computers with different hardware to test the performance of 5 games in 1080p and 4K, comparing the average fps results of the games' built in benchmarks to determine which OS ran the game better across the same hardware: Windows or Bazzite.
Some notes on methodolgy under this spoiler
Each game uses the same in game graphics settings in Windows and in Linux. The Linux distro used was Bazzite, using the version specific for the graphics card hardware fpr each individual machine. To be clear, this means that he installed the Bazzite version for (legacy) nVidia as appropriate.
Each bazzite install was fresh, no copying installs or swapping around a drive with it pre-installed. After install, it was updated using system update and rebooted, repeated until no updates remained.
Screenshots of some of Dankpods's comments to this effect:
There are many comments under the youtube video pointing out that in many of the Linux runs, it was not actually using the correct driver, comments about the experience using other distros, and comments about various potential fixes and workarounds.
This misses the point. Dankpods intentionally tested this way, and used Bazzite, to try and show what this would be like for the average gamer schmuck without a ton of technical skill interested in switching to Linux. Out of box experience matters in this situation, even though it's not quite fair to compare that between free opens source distros and an OS created by a megacorp. To the average end user, it won't matter. They just want it to work.
Prepare to be upset. With this particular testing methodology, Linux doesn't really win overall.
I'm interested to hear the community's thoughts on this.
He certainly claims to have used the correct Bazzite images:
He also mentions that he used the "Nvidia (GTX 9xx-10xx Series)" image for the 1080 Ti system.
Of course, it could be that he messed up, but it could also be that Bazzite didn't work as intended. It certainly wouldn't be the first time that Nvidia drivers broke on a Linux distro.
And in case this was indeed user error, perhaps it would be a good idea to have a mechanism to let users know that they chose the "wrong" image.
This was said only about the Linux side. Apparently he did install the drivers manually on Windows, but not on Linux. (Windows doesn't come with drivers for the 1080ti either and they have to be manually installed, e.g.) So it isn't comparing oobe. One system was tinkered with and the other wasn't.
Also, there's a hypothesis that he downloaded bazzite images during a very brief period when they weren't included in the legacy image yet. The drivers went out of support in December and there was a window of adjustment in the packaging. If he were to do it all again today, the results would be radically different. This was an exercise in futility and an utter waste of time.
It's definitely a waste of time that he should have stopped after the first one or two where they obviously weren't working.
I still think it's an important demonstration of where things could (and should) be made clearer to the end user.
Like a lot of technical stuff, there's kind of an absurd expectation that caveats can be completely omitted and it's on the end user to figure out. I make tons of documentation at my job as a sysadmin. I get that you can't possibly catalog every edge case and caveat, but from what I can tell, this issue with the Bazzite images was known and happens often enough that the cause is well known. It's a failing by the maintainers that they don't have a basic warning mechanism built in for this scenario.
A warning on the download page. A warning in the updater. Better controls in the release tools so the nVidia release can stay on the last supported version until the new drivers work.
Anything besides just expecting the end user to magically know that the thing labelled as working for their situation does not in fact work at the moment.