Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
So if performance is proportional...

MBA 2020
geekbench multi : 7433 (65% gain from A12Z)
cinebench R23 (estimated) : 7500ish

Devkit A12Z
geekbench multi native : 4510
cinebench R23 : 4530

Of course, one cannot compare thermally limited passive cooled MBA to a desktop with dedicated cooler.. I gather Mac Mini with M1 will yield better geenbench score, and hence much better cinebench R23 result for Mac Mini is expected.

So it’s obvious why Apple only introduced entry machines as to maximize comparative impact?
Anyway, it’s pretty phenomenal for 1st generation mac chip.
Can’t wait to see a real mac class chip unlike A14Z varient like chip like M1!
The Mac mini score was worse for some reason. We'll see what the numbers are after more tests are available though.


1682 / 7097
 
The OS matters too. In benchmarks, Linux boxes often do several % better than windows or macOS with the same hardware.
iOS, iPadOS and MacOS are all build on top of the same Darwin kernel. iOS doesn't swap out memory to an SSD but they are otherwise quite similar.
 
Windows 10 Home / AMD 3900X CPU (12c/24t) / 32GB RAM

18,823 multi-core

This was with Discord & three Firefox browser windows open at the same time, I did not run single core...
 
The MacBook Pro has hit over 1700 single-core. But this one test's multi-core speed isn't quite as amazing. This is not a huge surprise though, since there is quite a bit of variability.

1714 / 6802

iOS, iPadOS and MacOS are all build on top of the same Darwin kernel. iOS doesn't swap out memory to an SSD but they are otherwise quite similar.
I suspect macOS has a fair bit more overhead than iPadOS. Cuz when you run Linux on Macs, they are faster than when they are running macOS.
 
  • Like
Reactions: donth8
The MacBook Pro has hit over 1700 single-core. But this one test's multi-core speed isn't quite as amazing. This is not a huge surprise though, since there is quite a bit of variability.

1714 / 6802


I suspect macOS has a fair bit more overhead than iPadOS. Cuz when you run Linux on Macs, they are faster than when they are running macOS.
There are a lot of applications on MacOS that are large and even bloated compared to most iOS applications. iOS is very aggressive about terminating misbehaving apps and only allows apps to be installed from the App Store so I can see an iPad with the same or similar SoC seeming faster. I can't see that affecting benchmark times though.
 
There are a lot of applications on MacOS that are large and even bloated compared to most iOS applications. iOS is very aggressive about terminating misbehaving apps and only allows apps to be installed from the App Store so I can see an iPad with the same or similar SoC seeming faster. I can't see that affecting benchmark times though.
Services too etc. I guess.
 
I ran Cinema R23 against my i7-6700k edit: 4Ghz, 16Gb, Windows 10 desktop, and the results were about the same. The Apple Silicon was slightly slower in both multi and single core.

That said, the Apple Cinebench results are fairly impressive.
 
Last edited:
I ran Cinema R23 against my i7-6700k, 16Gb, Windows 10 desktop, and the results were about the same. The Apple Silicon was slightly slower in both multi and single core.

That said, the Apple Cinebench results are fairly impressive.
We don't have any scores for the M1 yet, just the a12z in the dev kit. I doubt the m1 is slower the the i7-6700
 
  • Like
Reactions: Stella
We don't have any scores for the M1 yet, just the a12z in the dev kit. I doubt the m1 is slower the the i7-6700
Oh OK, that was against the Dev Kit - still, knowing the performance of this desktop, which is good - combined with the GPU I have, the M1 is no slouch.

So, the GPU benchmarks around an nVidia 1060... not bad. Though in the real world, the 1060 is faster than the 970, but the 970 has benchmarked faster.... so this isn't translating into the real world, as what would be expected.

Still, it's good GPU performance...
 
Well it’s impressive for low power iGPU I guess.
Hopefully Apple’s secret GPU Project will bring out a true desktop/high mobile class GPU.
I hope so too, still don’t understand why the 4 core GPU in the iPad air 4 gets a 12,000 metal score. Really wanted the M1 to double that.
 
I just wonder why everyone is throwing out their multi-core scores on huge desktop computers and then saying the M1 isn’t all that impressive. Shouldn’t we be comparing this to the outgoing models? Seeing that the single core raw performance isn’t not only impressive, but indeed when we take the TDP/performance per watt into consideration, it is pretty much a paradigm shift game changing piece of hardware for the Mac.

Let’s keep some perspective. Apple has released its 1st gen, lowest powered and lowest performance Mac SoC that it will ever release, and has only replaced the lowest, entry level machines it sells with that SoC.

This SoC was not meant to slay the 65-85W Desktop behemoths. The fact that it is punching 2-3 tiers above its weight class anyway should tell the story about what we should expect to see when the mid-tier Macs get their turn in about 6 months time. (Hopefully!) An M1X variant of this SoC with another TB controller, double the P-cores, and 50% more GPU cores will be an extremely compelling piece of kit.
 
That “igpu” is on par with rx 570 ( a card that was used in the big imac,now the same perf sits under a macbook air)
We will see more in the weekend
 
Even the GPU seem to be competitive. At 10-15W, M1 performs the same as AMD/NVIDIA at much higher TDP. There would be no problem to add 32 core GPU for nearly 4X performance corresponding to a 5700XT even if the chips draw perhaps around 50W.

We already knew the M1 CPU is a winner, but the GPU may be as competitive. Also the neural engines will offload some compute from the GPU and there the gains are even larger. Seems good to me also on the GPU/compute department.

I wish benchmarks reporter performance per watt.
 
Very impressive numbers so far. Time for me to upgrade my 2016 Macbook!

But it still shows that Apple GPU competitiveness has a VERY long way to go. I wonder how they will cope with that, if they actually ditch AMD/NVIDIA for good.
 
I just wonder why everyone is throwing out their multi-core scores on huge desktop computers and then saying the M1 isn’t all that impressive. Shouldn’t we be comparing this to the outgoing models? Seeing that the single core raw performance isn’t not only impressive, but indeed when we take the TDP/performance per watt into consideration, it is pretty much a paradigm shift game changing piece of hardware for the Mac.

Exactly. The direct competitor to M1 is Intel Tiger Lake and the mobile 15W Ryzen CPUs. And it seems that all M1 scores so far outperform the median Ryzen 7 4800U and Intel i7-1165G7 in both single-core and multi-core, by a respectable margin.
 
  • Like
Reactions: MyopicPaideia
But it still shows that Apple GPU competitiveness has a VERY long way to go. I wonder how they will cope with that, if they actually ditch AMD/NVIDIA for good.

Don't know, the compute GPU performance seems to be quite good if you compare it to other 15W SoCs. Larger M chips with more GPU cores should do very well indeed. But we will need more data.
 
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.