I was going to test this project on a raspberry pi running Fedora. However I have had trouble getting the pi setup on my network. I will hopefully get it working in the next few days, however I will shift my benchmarking over to the aarch64 servers for now.
Because the provided test and benchmarks use large test data and perform a variety of tests, the changes between test runs are quite low. Running consecutive tests does not appear to have any noticeable increase in performance. Which means these tests are not getting effected by cache. Before each test run I checked top for the system usage to ensure nothing major was running.
In all the tests I ran on each system I did not see any noticeable variation from the results below. The differences between the benchmarks across systems is to be expected with the differences in core power.