Image: Intel

The first benchmarks for Intel’s upcoming Core i9-12900HK mobile processor have leaked courtesy of Wccftech, and the results are pretty spectacular. This Alder Lake-P chip was able to score 1,851 and 13,256 in Geekbench 5.4.1’s single- and multi-core tests, respectively, placing it above Apple’s newly introduced M1 Max in both categories. Apple has been busy advertising the M1 Max as the fastest laptop CPU ever, but that marketing point might be short lived in the event that these numbers are accurate.

Image: Wccftech
Image: Wccftech

From Wccftech:

Almost all of us expected Intel to win on the single-threaded front because of high clock rates and some serious architectural improvements but what is surprising is that they even beat the Apple M1 Max on the multi-threaded front. The Alder Lake Core i9 12900HK mobility processor gets an astounding 13256 score which is followed by Apple at 12753 points. The Intel 11980HK (stock) is further into the horizon at 9149 points and AMD clocks in at 8217 points. This is a generation over generation increase of almost 45% in roughly the same TDP […]

Intel is expected to launch its first Alder Lake-P processors in early 2022. These benchmarks were performed on Windows 11, which means that some portion of the performance gains might be owed to the OS’ support of Intel’s new Thread Director technology.

Source: Wccftech

Don’t Miss Out on More FPS Review Content!

Our weekly newsletter includes a recap of our reviews and a run down of the most popular tech news that we published.

Join the Conversation

6 Comments

  1. Might be a tad faster, but the Apple chip won’t need a dgpu and uses half the power, assuming Intel is honest about its chips power draw.

  2. Wccf… sigh.

    And isn’t it amazing how all the leaks show Intel winning everything? Such leaks so great.

  3. It is notable that they are only comparing single core scores, which just so happens to be Intel’s biggest advantage. I tend to be a huge proponent of per thread performance, but you have to take a more holistic view. the M1 Max has 16-32 cores depending on model. The 12900hk has 14.

    Still, adding cores for multithreading benefits some things, single threaded performance increases benefit ALL things, so it is an important performance metric, just not in isolation.

  4. [QUOTE=”Zarathustra, post: 42960, member: 203″]
    the M1 Max has 16-32 cores depending on model. The 12900hk has 14.
    [/QUOTE]
    Those are GPU Core counts for the M1M. It has 10 CPU cores – 8 big, 2 little.

    Compared to the 12900HK, which is presumed to be 6 big, 8 little based on the benchmark results

    Power draw difference is I suspect will be significant too, as Nanobot said. [URL=’https://www.forbes.com/sites/antonyleather/2021/07/21/intel-leak-reveals-core-i9-12900k-with-16-cores/’]122900K is 125W[/URL], but “up to” 228W. — that isn’t the mobile-designated HK version though. The 11900H is 45W, but that’s a completely different architecture so I don’t know that we can draw any conclusion from that.

    M1Max isn’t reported officially, but was tested at full load to [URL=’https://www.anandtech.com/show/17024/apple-m1-max-performance-review/3′]pull 120W[/URL] — from the wall, with full CPU + IGP load, and self-reports a 92W package power.

    [URL=’https://www.anandtech.com/show/17024/apple-m1-max-performance-review’]Anandtech[/URL] did some testing – Apple didn’t claim any differences in CPU architecture from the previous M1, and it appears there haven’t been. The Firestorm/Icestorm cores in the newer M1P and M1M appear to be the same as the previous M1 – just the ratio and counts are different.

  5. [QUOTE=”Brian_B, post: 42961, member: 96″]
    Those are GPU Core counts for the M1M. It has 10 CPU cores – 8 big, 2 little.

    Compared to the 12900HK, which is presumed to be 6 big, 8 little based on the benchmark results

    Power draw difference is I suspect will be significant too, as Nanobot said. [URL=’https://www.forbes.com/sites/antonyleather/2021/07/21/intel-leak-reveals-core-i9-12900k-with-16-cores/’]122900K is 125W[/URL], but “up to” 228W. — that isn’t the mobile-designated HK version though. The 11900H is 45W, but that’s a completely different architecture so I don’t know that we can draw any conclusion from that.

    M1Max isn’t reported by itself, but was tested at full load to [URL=’https://www.anandtech.com/show/17024/apple-m1-max-performance-review/3′]pull 120W[/URL] — from the wall, with full CPU + IGP load, and self-reports a 92W package power.

    [URL=’https://www.anandtech.com/show/17024/apple-m1-max-performance-review’]Anandtech[/URL] did some testing – Apple didn’t claim any differences in CPU architecture from the previous M1, and it appears there haven’t been. The Firestorm/Icestorm cores in the newer M1P and M1M appear to be the same as the previous M1 – just the ratio and counts are different.
    [/QUOTE]

    My bad, looks like I read a little too fast on that one.

    I still can’t help but think Intel has the Big Little thing backwards.

    It would seem to me that ideally you’d have a small number of little cores to do background idle tasks, and a large number of big cores to do active “the user is waiting for this” type of tasks. I don’t quite understand how they went with more little than big cores. Apples 10+2 breakout seems to make much more sense to me than Intel’s 6+8 does.

    But there may be aspects to this I’m not quite up to speed on yet. Maybe windoes background housekeeping requires 8 little cores to work smoothly? I know there is a shit ton of stuff going on in the background these days (and I wish there weren’t)

Leave a comment