BenchmarkXPRT Blog banner

Category: benchmark

Why we don’t control screen brightness during CrXPRT 2 battery life tests

Recently, we had a discussion with a community member about why we no longer recommend specific screen brightness settings during CrXPRT 2 battery life tests. In the CrXPRT 2015 user manual, we recommended setting the test system’s screen brightness to 200 nits. Because the amount of power that a system directs to screen brightness can have a significant impact on battery life, we believed that pegging screen brightness to a common standard for all test systems would yield apple-to-apples comparisons.

After extensive experience with CrXPRT 2015 testing, we decided to not recommend a standard screen brightness with CrXPRT 2, for the following reasons:

  • A significant number of Chromebooks cannot produce a screen brightness of 200 nits. A few higher-end models can do so, but they are not representative of most Chromebooks. Some Chromebooks, especially those that many school districts and corporations purchase in bulk, cannot produce a brightness of even 100 nits.
  • Because of the point above, adjusting screen brightness would not represent real-life conditions for most Chromebooks, and the battery life results could mislead consumers who want to know the battery life they can expect with default out-of-box settings.
  • Most testers, and even some labs, do not have light meters, and the simple brightness percentages that the operating system reports produce different degrees of brightness on different systems. For testers without light meters, a standardized screen brightness recommendation could discourage them from running the test.
  • The brightness controls for some low-end Chromebooks lack the fine-tuning capability that is necessary to standardize brightness between systems. In those cases, an increase or decrease of one notch can swing brightness by 20 to 30 nits in either direction. This could also discourage testing by leading people to believe that they lack the capability to correctly run the test.

In situations where testers want to compare battery life using standardized screen brightness, we recommend using light meters to set the brightness levels as closely as possible. If the brightness levels between systems vary by more than few nits, and if the levels vary significantly from out-of-box settings, the publication of any resulting battery life results should include a full disclosure and explanation of test conditions.

For the majority of testers without light meters, running the CrXPRT 2 battery life test with default screen brightness settings on each system provides a reliable and accurate estimate of the type of real-world, out-of-box battery life consumers can expect.

If you have any questions or comments about the CrXPRT 2 battery life test, please feel free to contact us!

Justin

We fixed two bugs affecting the WebXPRT 4 Preview results-page

We launched a preview of the WebXPRT 4 results viewer just before the new year, and have published over 75 results from a wide range of devices. We appreciate the results submissions we’ve received from independent testers so far, and will continue to populate the viewer with WebXPRT 4 Preview results from both our own testing and PT-curated external submissions.

If you’ve run the test and have tried to submit results, you may have encountered one or both of the following bugs, depending on the device type you’re testing:

  • You filled out the results submission form, but the Submit button didn’t seem to do anything.
  • The test automatically downloaded the results csv file multiple times.

We’ve identified the causes of the two bugs, and have instituted fixes. The bug fixes do not affect the benchmark’s workloads or scores. If you tested the WebXPRT 4 Preview and were frustrated by the results submission bugs, we apologize for the inconvenience, and invite you to retry the submitting your results.

If you have any questions or comments about the WebXPRT 4 Preview or the results viewer, please feel free to contact us!

Justin

Looking back on 2021 with the XPRTs

As 2022 gets underway, we want to take this opportunity to look back on 2021 and review another productive year for the XPRTs. Readers of our newsletter are familiar with the stats and updates we include each month, but for our blog readers who don’t receive the newsletter, we’ve compiled some highlights below.

Benchmarks
In the past year, we released the WebXPRT 4 Preview, CloudXPRT v1.1, and an updated CrXPRT 2 build that included a fix for prior issues with the battery life test.

XPRTs in the media
Journalists, advertisers, and analysts referenced the XPRTs thousands of times in 2021. It’s always rewarding to know that the XPRTs have proven to be useful and reliable assessment tools for technology publications such as AnandTech, Expert Reviews, Gadgets 360, Gizmodo, Hot Hardware, Laptop Mag, Legit Reviews, Notebookcheck, PCMag, PCWorld, TechPowerUp, Tom’s Hardware, and ZDNet.

Downloads and confirmed runs
In 2021, we had more than 23,600 benchmark downloads and 228,900 confirmed runs. Our most popular benchmark, WebXPRT, just passed 909,800 runs since its debut in 2013! WebXPRT continues to be a go-to, industry-standard performance benchmark for OEM labs, vendors, and leading tech press outlets around the globe.

Media, publications, and interactive tools
Part of our mission with the XPRTs is to produce tools and materials that help testers better understand the ins and outs of benchmarking in general and the XPRTs in particular. To help achieve this goal, we published the following in 2021:

We’re thankful for everyone who has used the XPRTs, joined the community, and sent questions and suggestions throughout 2021. We look forward to an exciting 2022!

Justin

The WebXPRT 4 Preview is here!

We’re excited to announce that the WebXPRT 4 Preview is now available! Testers can access the Preview at www.WebXPRT4.com or through a link on WebXPRT.com. The Preview is available to everyone, and testers can now publish scores from Preview build testing. We may still tweak a few things, but will limit any changes that we make between the Preview and the final release to the UI and features we do not expect to affect test scores.

Longtime WebXPRT users will notice that the WebXPRT 4 Preview has a new, but familiar, UI. The general process for kicking off both manual and automated tests is the same as with WebXPRT 3, so the transition from WebXPRT 3 to WebXPRT 4 testing should be straightforward. We encourage everyone to visit the XPRT blog for more details about what’s new in this Preview release.

In addition, keep your eye on the blog for more details about the all-new WebXPRT 4 results viewer, which we expect to publish in the very near future. We think WebXPRT testers will enjoy using the viewer to explore our WebXPRT 4 test data!

After you try the WebXPRT 4 Preview, please send us your comments. Thanks and happy testing!

Justin

Here’s what to expect in the WebXPRT 4 Preview

A few months ago, we shared detailed information about the changes we expected to make in WebXPRT 4. We are currently doing internal testing of the WebXPRT 4 Preview build in preparation for releasing it to the public. We want to let our readers know what to expect.

We’ve made some changes since our last update and some of the details we present below could still change before the preview release. However, we are much closer to the final product. Once we release the WebXPRT 4 Preview, testers will be able to publish scores from Preview build testing. We will limit any changes that we make between the Preview and the final release to the UI or features that are not expected to affect test scores.

General changes

Some of the non-workload changes we’ve made in WebXPRT 4 relate to our typical benchmark update process.

  • We have updated the aesthetics of the WebXPRT UI to make WebXPRT 4 visually distinct from older versions. We did not significantly change the flow of the UI.
  • We have updated content in some of the workloads to reflect changes in everyday technology, such as upgrading most of the photos in the photo processing workloads to higher resolutions.
  • We have not yet added a looping function to the automation scripts, but are still considering it for the future.
  • We investigated the possibility of shortening the benchmark by reducing the default number of iterations from seven to five, but have decided to stick with seven iterations to ensure that score variability remains acceptable across all platforms.

Workload changes

  • Photo Enhancement. We increased the efficiency of the workload’s Canvas object creation function, and replaced the existing photos with new, higher-resolution photos.
  • Organize Album Using AI. We replaced ConvNetJS with WebAssembly (WASM) based OpenCV.js for both the face detection and image classification tasks. We changed the images for the image classification tasks to images from the ImageNet dataset.
  • Stock Option Pricing. We updated the dygraph.js library.
  • Sales Graphs. We made no changes to this workload.
  • Encrypt Notes and OCR Scan. We replaced ASM.js with WASM for the Notes task and updated the WASM-based Tesseract version for the OCR task.
  • Online Homework. In addition to the existing scenario which uses four Web Workers, we have added a scenario with two Web Workers. The workload now covers a wider range of Web Worker performance, and we calculate the score by using the combined run time of both scenarios. We also updated the typo.js library.

Experimental workloads

As part of the WebXPRT 4 development process, we researched the possibility of including two new workloads: a natural language processing (NLP) workload, and an Angular-based message scrolling workload. After much testing and discussion, we have decided to not include these two workloads in WebXPRT 4. They will be good candidates for us to add as experimental WebXPRT 4 workloads in 2022.

The release timeline

Our goal is to publish the WebXPRT 4 preview build by December 15th, which will allow testers to publish scores in the weeks leading up to the Consumer Electronics Show in Las Vegas in January 2022. We will provide more detailed information about the GA timeline here in the blog as soon as possible.

If you have any questions about the details we’ve shared above, please feel free to ask!

Justin

Thinking about experimental WebXPRT workloads in 2022

As the WebXPRT 4 development process has progressed, we’ve started to discuss the possibility of offering experimental WebXPRT 4 workloads in 2022. These would be optional workloads that test cutting-edge browser technologies or new use cases. The individual scores for the experimental workloads would stand alone, and would not factor in the WebXPRT 4 overall score.

WebXPRT testers would be able to run the experimental workloads one of two ways: by manually selecting them on the benchmark’s home screen, or by adjusting a value in the WebXPRT 4 automation scripts.

Testers would benefit from experimental workloads by being able to compare how well certain browsers or systems handle new tasks (e.g., new web apps or AI capabilities). We would benefit from fielding workloads for large-scale testing and user feedback before we commit to including them as core WebXPRT workloads.

Do you have any general thoughts about experimental workloads for browser performance testing, or any specific workloads that you’d like us to consider? Please let us know.

Justin

Check out the other XPRTs:

Forgot your password?