PCMark 10 uses a modular approach to build relevant tests around common end-user scenarios. There are three levels to this approach:
- Test groups
Benchmarks are the top-level starting point in PCMark 10. A benchmark is a test designed to reflect the performance requirements of a defined user group. There are four performance benchmarks in PCMark 10.
|PCMark 10 benchmark|
The complete benchmark for the modern office. The ideal test for organizations that are evaluating PCs for a workforce with a range of performance needs.
|PCMark 10 Express benchmark||A shorter benchmark test focused on basic work tasks. It is a good choice when tendering for PCs for general office use.|
|PCMark 10 Extended benchmark||A longer benchmark test covering a wider range of activities. It provides organizations with a complete assessment of system performance beyond typical office work tasks.|
|PCMark 10 Applications benchmark||A benchmark for testing the performance of office PCs using Microsoft Office applications.|
Each benchmark contains one or more test groups. A test group is a collection of workloads that share a common theme or purpose. There are five test groups in PCMark 10.
|Test group||PCMark 10 benchmark||PCMark 10 Express||PCMark 10 Extended||PCMark 10 Applications|
|Digital Content Creation|
Workloads are the low-level unit in PCMark 10. A workload is a test designed around a specific activity, task, or application. For example, the Web Browsing workload is designed to test performance while carrying out a selection of typical web browsing tasks.
|Essentials||Productivity||Digital Content Creation||Gaming||Microsoft Applications|
Rendering and Visualization
|Graphics test 1|
Graphics test 2
Each benchmark run produces a high-level benchmark score, mid-level test group scores, and low-level workload scores. A higher score indicates better performance.
The precision of PCMark 10 benchmark scores is usually better than 3% when following the steps outlined in this guide. This means that running the benchmark repeatedly on a consistently performing system in a controlled environment will produce scores that fall within a 3% range.
A score may occasionally fall outside the margin of error since there are factors in modern, multitasking operating systems that cannot be controlled completely. There are also devices that simply do not offer consistent performance due to their design. In these cases, you should run the benchmark multiple times, and take an average or a mode of the results.