System Performance: UL and BAPCo Benchmarks

Our 2022 Q4 update to the test suite for Windows 11-based systems carries over some of the standard benchmarks we have been using over the last several years, including UL's PCMark. New additions include BAPCo's CrossMark multi-platform benchmarking tool, as well as UL's Procyon benchmark suite. BPACo recently updated their SYSmark benchmark suite - while operational at a basic level, it is missing key features such as energy consumption measurement. We will start including SYSmark 30 once the open issues are resolved.

UL PCMark 10

UL's PCMark 10 evaluates computing systems for various usage scenarios (generic / essential tasks such as web browsing and starting up applications, productivity tasks such as editing spreadsheets and documents, gaming, and digital content creation). We benchmarked select PCs with the PCMark 10 Extended profile and recorded the scores for various scenarios. These scores are heavily influenced by the CPU and GPU in the system, though the RAM and storage device also play a part. The power plan was set to Balanced for all the PCs while processing the PCMark 10 benchmark. The scores for each contributing component / use-case environment are also graphed below.

UL PCMark 10 - Performance Scores

The productivity workload sees the Ryzen 7-5800U system come out on top (thanks probably to the presence of 8 high performance cores), but that system loses steam in other components. The overall scores are along expected lines - the Intel RPL-P system is ahead of the ASRock Industrial RPL-P one, which in turn is a bit in front of the Alder Lake-P systems.

UL Procyon v2.1.544

PCMark 10 utilizes open-source software such as Libre Office and GIMP to evaluate system performance. However, many of their professional benchmark customers have been requesting evaluation with commonly-used commercial software such as Microsoft Office and Adobe applications. In order to serve their needs, UL introduced the Procyon benchmark in late 2020. There are five benchmark categories currently - Office Productivity, AI Inference, Battery Life, Photo Editing, and Video Editing. AI Inference benchmarks are available only for Android devices, while the battery life benchmark is applicable to Windows devices such as notebooks and tablets. We presents results from our processing of the other three benchmarks.

UL Procyon - Office Productivity Scores

With similar processors and RAM, the NUCS BOX-1360P/D4 and the NUC13ANKi7 perform very similarly across all four components, getting on top in two each. The recorded scores are within the margin of run to run variations.

The Arena Canyon NUC forges ahead on the energy consumption front, though. In fact, the ASRock Industrial system comes way beind at 11.25 Wh compared to the Arena Canyon NUC's 9.06 Wh. These numbers can be due to different BIOS optimization targets.

Moving on to the evaluation of Adobe Photoshop and Adobe Lightroom, we find the Arena Canyon NUC come out comfortably on top, but it guzzles a lot more energy in the process compared to the 4x4 BOX-5800U.

UL Procyon - Photo Editing

UL Procyon evaluates performance for video editing using Adobe Premier Pro, with the GPU playing a major role.

UL Procyon - Photo Editing

The aggressively clocked iGPU in the Core i7-1360P helps the Arena Canyon NUC and the NUCS BOX-1360P/D4 to deliver similar scores, with the former coming out on top. However, the energy consumption number is significantly higher despite the faster processing.

BAPCo CrossMark

BAPCo's CrossMark aims to simplify benchmark processing while still delivering scores that roughly tally with SYSmark. The main advantage is the cross-platform nature of the tool - allowing it to be run on smartphones and tablets as well.

BAPCo CrossMark - Sub-Category Scores

The relative performance seen in PCMark 10 translate to CrossMark also, as expected. The responsiveness ratings vary significantly due to differences in the default BIOS settings for options such as PCIe ASPM etc. We see the ASRock Industrial units emerge with high responsiveness ratings (ASPM disabled by default), while Arena Canyon opts to optimize for power efficiency by enabling ASPM. Overall, we see the Arena Canyon NUC score very similarly to the NUCS BOX-1360P/D4, and well ahead of the rest of the pack.

Setup Notes and Platform Analysis System Performance: Miscellaneous Workloads
Comments Locked


View All Comments

  • lemurbutton - Monday, March 27, 2023 - link

    M2 Mini is only $599.00. It pretty much blows any Intel NUC out of the water.
  • Uncached486 - Monday, March 27, 2023 - link

    M2 and mobile Raptor Lake are fairly even matched in single threaded performance, with the desktop parts slightly ahead. M2's efficiency is definitely impressive, but performance-wise it certainly doesn't blow Intel out of the water.
  • meacupla - Monday, March 27, 2023 - link

    oh, but it doesn't straight up blow NUC out of the water? because that $599 mac mini comes with 8GB ram and a slow 256GB SSD.
    That is anemic in 2022, let alone 2023, and you can't upgrade it, unless you fully replace it.
    No thanks.
  • Affectionate-Bed-980 - Tuesday, March 28, 2023 - link

    Yes there are concerns about the Mac Mini's paper specs but the slower SSD has zero impact on daily use and is completely unnoticeable outside of benchmarks. I agree 256gb is a bit small for any general use, but if you're running a server or HTPC tasks, I think a Mac Mini is more than well specced for the task. Not to mention M2s are just freaking power efficient. I don't have one, but my M1 Pro Macbook basically maintains its battery level doing office level tasks on an 18W charger. Yes over the course of a long day or so it might lose a few % but that's mostly because there will occasionally be a few power spikes depending on what I'm doing, but it plays YouTube 4K just fine sipping power.

    Admitteldy I have an older NUC but it's not like CPU power has exponentially grown or anything on the Intel side, but an i5 Broadwell seems to completely struggle to even have a lag free desktop experience despite wiping it fully.
  • Fenturi - Tuesday, March 28, 2023 - link

    That small SSD is not replaceable. The OS reads and writes to it all day long, smaller the SSD the lower the lifespan. When it fails, you throw it away.
  • Affectionate-Bed-980 - Friday, March 31, 2023 - link

    Most people are not going to wear out their SSDs, especially Mac Mini users. And I do agree 256gb is not a whole lot, but if all you're doing is buying this for a retiree who just surfs the web and watches videos and views photos of their grandkids, a Mac Mini 256gb might be totally enough.
  • Affectionate-Bed-980 - Friday, March 31, 2023 - link

    This argument you're making is no different than early SSD concerns. SSDs are a mature product and we've seen even in using lower cost cells, average users are not wearing out QLC NAND either.
  • block2 - Tuesday, April 4, 2023 - link

    Agree. 2TB also would not be enough for anyone who is doing any machine will need external storage anyhow. 8gb seems to be plenty for apple OS and apps. 16gb would tempt me though. The problem I see with these mini PCs is that a laptop doesn't cost much more. I have a very old desktop that I built and have been looking at cheap micro (UCFF?) computers (beehive brand?) and laptops.
    (been following Anand since he was in high school!)
  • TheinsanegamerN - Monday, March 27, 2023 - link

    To get a 32GB mac mini to match this NUC, you must spend, at minimum, $1700. If you want multi gig ethernet, add another $100.

    Oh, and you cant upgrade RAM or storage later.

    And you can only run mac software

    And after 7 years you dont get updates anymore.

  • block2 - Tuesday, April 4, 2023 - link

    Don't need nearly as much memory to run apple OS and apps...maybe that's partly why it's faster per watt. Can emulate windows...can Intel/AMD PCs emulate IOS?

Log in

Don't have an account? Sign up now