BenchmarkXPRT Blog banner

Tag Archives: benchmark

Chrome OS support for CrXPRT apps ends in June 2022

Justin Greene
By Justin Greene
on March 24, 2022

Last March, we discussed the Chrome OS team’s original announcement that they would be phasing out support for Chrome Apps altogether in June 2021, and would shift their focus to Chrome extensions and Progressive Web Apps. The Chrome OS team eventually extended support for existing Chrome Apps through June 2022, but as of this week, we see no indication that they will further extend support for Chrome Apps published with general developer accounts. If the end-of-life schedule for Chrome Apps does not change in the next few months, both CrXPRT 2 and CrXPRT 2015 will stop working on new versions of Chrome OS at some point in June.

To maintain CrXPRT functionality past June, we would need to rebuild the app completely—either as a Progressive Web App or in some other form. For this reason, we want to reassess our approach to Chrome OS testing, and investigate which features and technologies to include in a new Chrome OS benchmark. Our current goal is to gather feedback and conduct exploratory research over the next few months, and begin developing an all-new Chrome OS benchmark for publication by the end of the year.

While we will discuss ideas for this new Chrome OS benchmark in future blog posts, we welcome ideas from CrXPRT users now. What features or workloads would you like the new benchmark to retain? Would you like us to remove any components from the existing benchmark? Does the battery life test in its current form suit your needs? If you have any thoughts about these questions or any other aspects of Chrome OS benchmarking, please let us know!

Justin

Posted in Battery life, battery life, benchmark, Benchmarking, BenchmarkXPRT, Browser-based benchmarks, Chrome OS, Chromebooks, Chromium, Collaborative benchmark development, CrXPRT, Google Chrome, Performance benchmarking, What makes a good benchmark? | Also tagged , , , , , , , ,

WebXPRT 4 is live!

Justin Greene
By Justin Greene
on February 28, 2022

We’re excited to announce that WebXPRT 4 is now available! Testers can access the benchmark at WebXPRT.com. If you’ve already been using the WebXPRT 4 Preview, your Preview test results will be comparable with results from the current official build.

Longtime WebXPRT users will notice that WebXPRT 4 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 will continue to make WebXPRT 3 available for legacy testing.

If you missed earlier XPRT blog posts about WebXPRT 4, here is a quick overview of the differences between WebXPRT 3 and WebXPRT 4:

General changes

  • We’ve 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’ve 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’ve updated the base calibration system for score calculations, and adjusted the scoring scale. WebXPRT 4 scores should not be compared to scores from previous versions of WebXPRT.

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.

We’re thankful for all of the feedback we received during the WebXPRT 4 development process, and we look forward to seeing your WebXPRT 4 results!

Justin

Posted in benchmark, Benchmarking, BenchmarkXPRT, Browser-based benchmarks, Cross-platform benchmarks, Performance benchmarking, WebXPRT, WebXPRT 3, webxprt 4 | Also tagged , , , , ,

Updated system configuration recommendations for CrXPRT 2 battery life tests

Justin Greene
By Justin Greene
on February 3, 2022

Recently, we heard from a BenchmarkXPRT Development Community member who was testing Chromebooks in their lab. On a few of the Chromebooks, they saw sporadic CrXPRT 2 battery life test failures where CrXPRT 2 would successfully complete a battery life test and produce a result for the initial run, but then fail at the end of later runs.

After a considerable amount of troubleshooting, they determined that the issue seemed to be related to the way some systems automatically shut down before the battery is completely exhausted, and the way some systems will automatically boot up once the tester plugs in the power adapter for charging. This member found that when they added a few system configuration steps before battery life tests and made slight changes to their post-test routine, the systems that had previously experienced consistent failures would successfully complete battery life tests and produce results.

The added steps are quick and straightforward, and we decided to add them to the Configuring the test device and Running the tests sections of the CrXPRT 2 user manual. We hope this updated guidance will help to prevent future frustration for CrXPRT 2 testers.

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

Justin

Posted in battery life, benchmark, Benchmark metrics, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, Chrome OS, Chromebooks, CrXPRT, Google Chrome | Also tagged , , , , , , ,

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

Justin Greene
By Justin Greene
on January 27, 2022

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

Posted in Battery life, battery life, benchmark, Benchmark metrics, Chrome OS, Chromebooks, CrXPRT, What makes a good benchmark? | Also tagged , , , , ,

Looking back on 2021 with the XPRTs

Justin Greene
By Justin Greene
on January 6, 2022

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

Posted in Battery life, battery life, benchmark, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, CloudXPRT, Collaborative benchmark development, CrXPRT, data analytics, results, WebXPRT, webxprt 4 | Also tagged , , , , , ,

The WebXPRT 4 Preview is almost here

Justin Greene
By Justin Greene
on December 15, 2021

Last week, we provided readers with an overview of what to expect in the WebXPRT 4 Preview, as well as an update on the Preview’s release schedule. Since then, we’ve been working on UI adjustments and bug fixes, additional technical tweaks, and follow-up testing. We’re very close, but won’t be able to meet our original goal of publishing the Preview today. We believe it will be ready for release early next week.

As a reminder, 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 to features we do not expect to affect test scores.

If you have any questions about WebXPRT 4 or the Preview build, please let us know!

Justin

Posted in Benchmarking, BenchmarkXPRT, Browser-based benchmarks, Cross-platform benchmarks, Performance benchmarking, WebXPRT, webxprt 4 | Also tagged , , , ,

Check out the other XPRTs:

Forgot your password?
© Principled Technologies, Inc. 2025   |   Privacy policy

Cookie Notice: Our website uses cookies to deliver a smooth experience by storing logins and saving user information. By continuing to use our site, you agree with our usage of cookies as our privacy policy outlines.

x