When it’s time to buy a new PC, upgrade your graphics card, or replace your storage, you’ll see one word repeatedly: benchmarks. But how representative are the actual performance benchmarks?
What is a reference?
A benchmark is a test or series of tests designed to improve the performance of your system or component to see what it is capable of. For graphics cards, this usually means a graphics scene from a video game, or what could be in a video game. The latter is called a synthetic reference, and there are many options, such as Unigine paradise, 3dmark, and Average.
For CPUs, benchmarks relate to the workload and how quickly it can execute instructions. Since there are so many operations that a PC can perform, you will find that different processors perform better at one task than others. Some may be better at running productivity software, while others are great at 3D rendering, etc.
There are standard reference suites for testing processors, such as PCMark 10, which runs your computer through a series of tests. For example, it tests how your system handles the use of spreadsheets, as well as tasks such as editing photos, making video calls, physical calculations for games, and browsing the web. Another popular tool for seeing how a processor handles video rendering is CineBench.
CPU performance testing can also involve specific real-world tasks, such as compressing a large folder into a ZIP file or loading an application with a large file.
Finally, for testing SSDs and hard drives, this is how quickly a drive can read and write (write) data to the drive. This is typically done with a reference program that performs sequential and random read and write tests.
Sequential means that a large chunk of data is read or written from contiguous locations on the disk, while random is the opposite. There are also large file tests (around 50 GB) where the drive’s internal cache is strained (running out of cache tends to slow a drive down to crawl).
Context is everything
When considering benchmarks, you need to keep the context in mind. This includes the performance of one processor or graphics card compared to another, the tests performed and under what conditions.
Common issues, such as the amount of RAM a system has, the type of cooling it uses for the processor and GPU, or a case’s ability to absorb cold air and expel heat, can all have an impact on performance. Heat is a big deal for PCs because components decrease in performance as they get hot as a survival mechanism.
This is a good thing! You wouldn’t want components that drive on their own until they melt or damage sensitive internal parts.
Speaking of heat, even the test room itself can impact performance. A gaming PC performs best in a room that stays around 72 degrees Fahrenheit in the summer. It is much more difficult to keep a PC cool in a warm room.
These are the basic issues to consider for the hardware. However, each benchmark needs a comparative context to understand the results.
Graphics card benchmarks
AMD Radeon RX 5700 XT graphics card. AMD
Typically, gamers are looking for graphics cards that can achieve up to 60 frames per second. This is the “golden zone”, where the games run smoothly and the graphics are really good. Anything below that, and you’ll encounter stuttering, nervous character movements, and low-res rendering.
There are two general considerations to take into account when it comes to graphics card performance: resolution and settings. A graphics card might not perform well at 4K resolution, but could be an absolute monster at 1080p. This is why, when considering benchmarks, it is essential to consider the resolution.
When it comes to graphics settings, there are four general automatic presets for video games: Ultra, High, Medium, and Low. It can get much more complicated if you manually change the settings. However, these four categories are how games are automatically defined according to the capabilities of a system. Most advisories use the Ultra setting for performance testing, unless otherwise noted.
An ideal graphics card can pump around 70 frames per second or more in 4K at Ultra settings on graphics-hungry AAA games. Cards with this type of performance are generally expensive, however.
Anyone looking for cards on a budget will want to consider performance versus price. This will vary based on personal preference and budget.
When reading a review, it is also important to know what games or synthetic cues were used. Synthetic benchmarks can be useful for comparing one graphics card to another because the test will be consistent from system to system. The problem is, synthetic benchmarks don’t necessarily provide a real-world view of current video games or what you can expect in real-world gaming conditions.
Built-in video game benchmarks aren’t a perfect alternative either. Many (but not all) games provide their own benchmarks. However, some of them are unreliable because they are not very active and do not reflect typical gameplay.
Other benchmarks are better because they use scenes you are likely to see in the game. Other than trial and error, there is no real way to know which game benchmarks are ideal and which are not. not.
Moreover, a single game reference is not enough to understand how good a card is. You need several benchmarks to get a full picture of the kind of performance you can expect.
Let us take a concrete example. Based on recent reviews, the Nvidia 2080Ti graphics card achieves 150 to 160 fps in the Middle-earth: Shadow of War game at 1080p resolution on the Ultra graphics setting. This tells you that the 2080 Ti is an excellent graphics card that performs well for this type of game. That doesn’t mean every game will hit those frame rates, however.
For example, based on some reviews, the 2080Ti does not exceed 90 FPS over the more intensive Ghost Recon Wildlands with the same resolution and graphics settings.
Watching a variety of games and tests will give you a more general picture of what to expect from a graphics card before installing it in your system.
Benchmarks of processors and storage drives
Processor benchmarks are important, but they make the most sense compared to other processors. Unlike graphics cards, there is no real “golden zone” for processor performance.
Processors are workhorses that have to do all kinds of operations, including playing games, editing photos, reading large spreadsheets, or just launching large programs. When you look at benchmarks for processors, you want to compare them to what other processors are doing.
If the processor you want to use for work doesn’t perform as well in productivity apps, its gaming chops won’t matter. When it comes to processors, compare them based on what you intend to do with your PC.
The same goes for storage drives. Examine the read-write performance speeds, and then compare them to other drives measured in the same exam. Also pay attention to large file transfer tests, especially if you are moving lots of photos or videos between the external storage and your PC.
Finally, keep in mind that references in reviews tend to use stock settings, not overclocking. Once you start overclocking a CPU or GPU, you can get more performance. However, the improvement varies depending on a number of factors, right down to the individual build quality of the component you want to overclock.
If you get a processor that performs great when overclocking, for example, it’s common to call it “winning the silicon lottery”. Indeed, this unlocked the potential that another processor with the same model number might not have.
A useful guide
Benchmarks can be a useful guide to computer component performance, but context matters. Compare your components and examine a wide variety of well-designed tests.
If you always keep in mind how you plan to use your PC, you can get a good idea of what to expect when you pop this precious new kit into your setup.