Note: The instructions on this page refer to benchmarking with version 3.6 of POV-Ray. If you are not
using version 3.6, please see the current benchmark page.
If you will be using POV-Ray to generate CPU benchmarks, please be aware that there is a standard
benchmark.pov, which is explicitly intended for benchmarking. It is included
with all distributions of POV-Ray 3.5 and 3.6, 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. Note that you cannot compare POV-Ray 3.5 and 3.6 benchmark results
due to improvements to anti-aliasing quality and photon performance in POV-Ray 3.6. The benchmark
results can only be compared if you are using the exact same version of POV-Ray and the benchmark on
all systems you are testing!
Please also note that due to internal changes this file is not suitable for benchmarking with the
current version of POV-Ray. Please use the version provided with each release to benchmark that release.
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. If you are using the 3.6 Macintosh version, you will
also find a command to run the benchmark in the Render menu. Both run 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