Learn about the technologies behind the Internet with The TCP/IP Guide!
NOTE: Using robot software to mass-download the site degrades the server and is prohibited. See here for more.
Find The PC Guide helpful? Please consider a donation to The PC Guide Tip Jar. Visa/MC/Paypal accepted.
View over 750 of my fine art photos any time for free at DesktopScenes.com!

[ The PC Guide | Systems and Components Reference Guide | Video Cards | Video Card Performance ]

Benchmarking Video Cards

It is very easy to be misled by video card benchmark scores. As discussed in the other topics in this section, there are many factors involved in video card performance, and boiling down a video card's speed to a single number can be very misleading if it is done incorrectly. There are many video benchmarks in use today and it is common for people to compare a video card to another one using one of these numbers. I feel that with the exception of a few people who really know what they are doing, these benchmarks are misleading and often do more harm than good.

The only really reliable, safe way to benchmark video performance is to do a comparative benchmark. This requires two cards that can run in the same system (if they can't be used in place of each other, why compare them directly anyway?) Then, you set up a test system and run a benchmark suite or test application with one card, record its score, replace with the second card and run the test again. Then repeat two times with each card, and average the scores. At least this way, you have eliminated most of the external effects that affect benchmark scores but really have nothing to do with the video card: the speed of the processor and other system components in particular.

Even this sort of a test, however, only gives you part of the picture unless you run a large suite of tests. Since every card has strengths and weaknesses, if you only run one sort of test, you may hit something that is a strength of "card A" but a weakness of "card B". Run a different test and the results may be reversed, especially if they are close overall in the first test. A comprehensive benchmark that examines many different modes of use and aspects of video performance lessens this problem. The most important benchmark to use is to run the application you want to use. No matter how good a benchmark program is, it doesn't replace the "real world" of the actual application, not even close--no matter what the benchmark fanatics say.

Next: The Importance of Drivers

Home  -  Search  -  Topics  -  Up

The PC Guide (http://www.PCGuide.com)
Site Version: 2.2.0 - Version Date: April 17, 2001
Copyright 1997-2004 Charles M. Kozierok. All Rights Reserved.

Not responsible for any loss resulting from the use of this site.
Please read the Site Guide before using this material.
Custom Search