Skip to main content

Intel's Core i7-12700H Benchmarked Against Apple's M1 Max

Intel
(Image credit: Intel)

Intel's 12th Generation Core 'Alder Lake-P' processors for high-performance laptops are months away, but some people in the PC supply chain are just too impatient not to share benchmark results of the upcoming notebooks powered by these chips. But sometimes, early performance numbers fail to impress.

Alleged Geekbench 5 results obtained on Gigabyte's Aero 5 XE and HP's Omen 17 laptops with Intel's Core i7-12700H inside were added to the benchmark's database on Friday, revealing the performance of the upcoming mobile Alder Lake-P in this popular synthetic benchmark. The numbers demonstrated by both machines are really close, so we can assume that the readings are more or less accurate. Meanwhile, it looks like both machines are equipped with DDR4-3200 memory, which might have limited their performance in single-threaded workloads. 

Intel's Core i7-12700H CPU packs six high-(P)erformance Golden Cove cores and eight energy-(E)fficient Gracemont cores, so it should perform considerably better compared to Intel's existing mobile CPUs in multi-threaded workloads. Because Alder Lake-P officially lacks AVX-512 support, the processor will be slower than chips supporting these instructions in certain workloads. Since overall GB5 results are heavily impacted by cryptography, it makes sense to look at integer and float benchmark results of the new CPUs and compare them to respective numbers obtained on other processors. 

One thing to note: since Gigabyte's notebook scores 6% higher in multi-thread workloads, we are using its numbers in our table.

Core i7-12700HCore i7-11800HRyzen 7 5800HApple M1 MaxApple M1 ProApple M1
General specifications6P, 8E, 2.70 ~ 4.60 GHz, ?MB8P, 2.30 ~ 4.60 GHz, 24MB16P, 3.20 ~ 4.40 GHz, 20MB8P, 2E, up to 3.22 GHz6P, 2E, up to 3.22 GHz4P, 4E, up to 3.20 GHz
Single-Core | Integer115713311247163416181597
Single-Core | Float141315561617192419031896
Single-Core | Crypto327637843546282128632783
Single-Core | Score134015211473178017661746
Multi-Core | Integer10929823180811137087487013
Multi-Core | Float122518873923914017111048624
Multi-Core | Crypto718662725075223061713910137
Multi-Core | Score11138832683051271198747653
Linkhttps://browser.geekbench.com/v5/cpu/10963160https://browser.geekbench.com/v5/cpu/10958275https://browser.geekbench.com/v5/cpu/10959710https://browser.geekbench.com/v5/cpu/10964502https://browser.geekbench.com/v5/cpu/10964506https://browser.geekbench.com/v5/cpu/9496959

Quite surprisingly, Intel's Core i7-12700H 'Alder Lake-P' fails to beat the Core i7-11800H 'Tiger Lake-H' as well as AMD's Ryzen 7 5800H 'Cezanne' (Zen 3) in single-threaded workloads. Furthermore, it is considerably behind Apple's M1-series system-on-chips that have been single-thread performance leaders for about a year now. Perhaps, usage of faster memory would have given Intel's ADL-P an advantage, but we will need to run our own tests to find out.

In multi-threaded Geekbench 5 workloads, everything looks much better for the Core i7-12700H as it leaves behind both the Core i7-11800H and the Ryzen 7 5800H. Still, Apple's M1 Max with its 10 cores (eight high-performance cores, two energy-efficient cores) beats Intel's upcoming offerings in all GB5 multi-threaded tests.

There are two things to note about the current benchmark results. Firstly, since Gigabyte's notebook scores 6% higher in multi-thread workloads, we are using its numbers in our table. Secondly, since we are months away from commercially available laptops based on Intel's Alder Lake-P processors, take early benchmark numbers with caution since many things may get optimized and performance numbers in various benchmarks will get higher. 

  • abufrejoval
    Well with a sample of one non-retail system, these results may not be meaningful.

    I have consistently found a relatively high OS bias in Geekbench results, which I actually assume to be mostly a compiler bias given the nature of those benchmarks. Generally I observed much higher results with Linux or Android-x86 than Windows on the very same hardware.

    My Tiger Lake NUC i7-1165G7 single core results on Linux (1721) seem to imply much faster hardware than on Windows (1568). Actually it even puts it above my 5800X (1696) and 5950X (1690) single Windows scores while Linux will righten the balance with 1794/1784 on the Ryzens.

    For the multi-threaded benchmarks my 5950X will deliver 16619 on Linux while the top result on Windows is 15492.

    On the mobile 5800U I get 1431 single and 7900 on the 28Watts envelope with Windows while Linux will deliver 1412 and 8308. At 15Watts it's more like 1422 single and 6427 multi threaded (didn't test Linux at 15 Watts) which isn't that impressive when you compare it against the Tiger Lake's 5955 multi threaded score with only half the number of CPU cores: clearly Ryzen is starved for power at 15 Watts.
    Reply
  • -Fran-
    These results are really odd... And this is giving the benchers the benefit of the doubt and assuming all CPUs were 35W models. Alder Lake P cores (Golden Cove?) should be really good in single threading at the same clock speeds as Rocket Fail Lake, so those results don't make sense to me. I think the CPU is being held back or maybe it's not inside a properly cooled laptop or they used an ES.

    Regardless, if Laptop Alder Lake improves over Rocket Lake Laptop, it would be kind of lame.

    Regards.
    Reply
  • maik80
    Yuka said:
    These results are really odd... And this is giving the benchers the benefit of the doubt and assuming all CPUs were 35W models. Alder Lake P cores (Golden Cove?) should be really good in single threading at the same clock speeds as Rocket Fail Lake, so those results don't make sense to me. I think the CPU is being held back or maybe it's not inside a properly cooled laptop or they used an ES.

    Regardless, if Laptop Alder Lake improves over Rocket Lake Laptop, it would be kind of lame.

    Regards.
    The chip architecture is hot and uses too high frequencies, in a notebook the performance will drop a lot
    Reply
  • -Fran-
    maik80 said:
    The chip architecture is hot and uses too high frequencies, in a notebook the performance will drop a lot
    There are architectural improvements in IPC, so at the same clocks, it should show better performance, which is not in this case. Unless they're clocked lower than the competing Intel counterpart, which is the "sus" part.

    Regards.
    Reply
  • Krotow
    How about real game tests on M1?
    Reply