The results in the benchmark were misleading
The score is within margin of error if a Podman container is started with a init daemon / PID1 ($ podman run --rm --systemd=always -it archlinux:base /sbin/init):
# Arch Linux LXC (bash)
1.15user 0.25system 0:01.40elapsed 101%CPU (0avgtext+0avgdata 3840maxresident)k
1.13user 0.28system 0:01.40elapsed 101%CPU (0avgtext+0avgdata 3840maxresident)k
1.12user 0.29system 0:01.39elapsed 101%CPU (0avgtext+0avgdata 4096maxresident)k
1.13user 0.27system 0:01.39elapsed 101%CPU (0avgtext+0avgdata 4096maxresident)k
# Arch Linux Rootful Podman (bash) with init
1.12user 0.26system 0:01.37elapsed 101%CPU (0avgtext+0avgdata 4096maxresident)k
1.12user 0.25system 0:01.36elapsed 101%CPU (0avgtext+0avgdata 3840maxresident)k
1.13user 0.25system 0:01.36elapsed 101%CPU (0avgtext+0avgdata 4096maxresident)k
1.11user 0.26system 0:01.36elapsed 101%CPU (0avgtext+0avgdata 4096maxresident)k