If you will be using POV-Ray to generate CPU benchmarks, please be aware that there is a standard
scene, benchmark.pov, which is explicitly intended for benchmarking. It is included
with all distributions of POV-Ray v3.5, in the scenes\advanced directory. In case
the copy you have has been edited, or if you are unsure if it is the latest version, we have a
clean copy of the file here, plus an ini file
which sets the standard benchmarking options.
In case you are wondering what the benchmark image is supposed to look like (given that the
standard means of rendering it is to have output turned off ...), just click on the below
thumbnail for a PNG version of the scene rendered at the standard benchmark resolution.
We strongly recommend that you use benchmark.pov for benchmarking, as it uses many
of POV-Ray's internal features and is a heavy test of CPU ability. If you use other scenes you
run the risk of having a benchmark result that relies too heavily on one or another specific portion
of our codebase.
If you are using the Windows version, please note that there is a built-in benchmark command to be
found in the POV-Ray for Windows Render Menu. It runs a built-in copy of our standard benchmark file
using a specific set of switches (see below).
If you choose to quote your benchmark results publicly, it is essential that you include
the benchmark version and the exact version of POV-Ray that you ran it on. Changes to the
benchmark file itself, and optimizations to POV-Ray, may make comparisions between different
versions of the benchmark or different versions of POV-Ray meaningless, especially if it is
CPU performance that you are testing. The version of the benchmark file can be found at the
top of benchmark.pov.
There is an unofficial benchmark result site maintained by a POV-Ray user at
http://www.haveland.com/povbench/.
You can submit your own machine's figures there if you like.
