x264 HD Benchmark 4.0
by graysky
updated by Adrian Wong & Dashken

What Is x264 HD Benchmark?

Simply put, it is a reproducible measure of fast your machine can encode a short HD-quality video clip into a high quality x264 video file. It's nice because everyone running it will use the same video clip and software. The video encoder (x264.exe) reports a fairly accurate internal benchmark (in frames per second) for each pass of the video encode and it also uses multi-core processors very efficiently. All these factors make this an ideal benchmark to compare different processors and systems to each other.

What's x264? It's more or less the next generation Xvid/DivX codec.

You'll notice that the whole thing is pretty simplistic since I have no programming skills to speak of. The test simply consists of the needed executables and the video file all driven by a batch file that'll kick off the x264 encode and write a "results.txt" that you can upload along with your machine specs for comparison purposes (see reporting results below).

What's New In Version 4.0?

For starters, we updated the benchmark with revision 1913 of the x264 encoder, and CPU-Z 1.57. The new x264 encoder supports the following features :

• 8x8 and 4x4 adaptive spatial transform
• Adaptive B-frame placement
• B-frames as references / arbitrary frame order
• CAVLC/CABAC entropy coding
• Custom quantization matrices
• Intra: all macroblock types (16x16, 8x8, 4x4, and PCM with all predictions)
• Inter P: all partitions (from 16x16 down to 4x4)
• Inter B: partitions from 16x16 down to 8x8 (including skip/direct)
• Interlacing (MBAFF)
• Multiple reference frames
• Ratecontrol: constant quantizer, constant quality, single or multipass ABR, optional VBV
• Scenecut detection
• Spatial and temporal direct mode in B-frames, adaptive mode selection
• Parallel encoding on multiple CPUs
• Predictive lossless mode
• Psy optimizations for detail retention (adaptive quantization, psy-RD, psy-trellis)
• Zones for arbitrarily adjusting bitrate distribution

Do note that we intend to "freeze" this version to use only revision 1913 of the x264 encoder so that all results using this benchmark can be compared with each other. Changing the x264 encoder every time there is a new update will skew the results as each version performs differently.

However, we will periodically update the compilation with the latest CPU-Z to allow for more accurate reporting of the CPU features as CPU-Z does not affect the results.

We will perform another major update of the benchmark when improvements in the x264 encoder are significant enough to warrant a new revision, and a new slew of results.

Download The Benchmark Here!

Want to see how your machine scores and/or contribute data? Download a copy here ->

Be sure to download and install AviSynth 2.5.8 as well!

Important : To avoid third-party tampering with the benchmark files, please do NOT modify or redistribute this benchmark on any other websites or forums. Please advice your readers and friends to check this page for the latest official copy.

Important - If you are using an Intel Core i7 or Core i5 processor (or their Xeon brethren), please be sure to turn off Intel Turbo Mode in the BIOS for accurate results! Similarly, if you are using an AMD processor that supports Turbo Core, please disable that as well.

Reporting Results (x264 HD Benchmark 4.0)

Results will be published at the x264 HD Benchmark CPU Performance Comparison Guide for all to view. A more concise list of results will be made available in this article later. If you would like to contribute your results, simply post the contents of your results.rtf (or whatever you name your results file) to this forum thread.

Important - If you are using an Intel Core i7 or Core i5 processor (or their Xeon brethren), please be sure to turn off Intel Turbo Mode in the BIOS for accurate results! Similarly, if you are using an AMD processor that supports Turbo Core, please disable that as well.

Since the output is merely a text file, you can recognize the potential for people to cheat by simply making up their own results, or skewing the real data.

I don't know of a way to eliminate this (as I said, I really have no programming experience). All I can say about this is please don't. No one will think you're cool because you have faster numbers and I am not publicizing results with your name by it (data is anonymous) so there are no bragging rights, etc.

Enjoy and thanks for participating!

-gs

Support Tech ARP!

Help support our work by visiting our sponsors, participate in the Tech ARP Forums, or even donate to our fund. Any help you can render is greatly appreciated!

Questions & Comments

Please feel free to post your questions or comments here!