Intel Alder Lake Mobility CPU Benchmarks Leaked: Faster Than The Apple M1 Max, Smokes AMD 5980HX, 11980HK

[P4-630]

Intel Core i9 12900HK mobility CPU benchmarked: faster than the Apple M1 Max, 11980HK and AMD 5980HX​

Read more on:

Intel Alder Lake Mobility CPU Benchmarks Leaked: Faster Than The Apple M1 Max, Smokes AMD 5980HX, 11980HK

So we have something very interesting for our readers today. We were able to exclusively get our hands on the first-ever benchmarks for Intel's upcoming Alder Lake mobility processors - which are going to go head to head against the Apple M1 Max processors clawing away market share as well as...

wccftech.com

 

[Fouquin]

So here's the fun thing about GeekBench: You can game it. Hard.

A custom kernel, malloc, or VM environment can swing the score hundreds of points on the same system with very minor tweaking. So as cool as this all looks I'll be here with the jar of salt for you all to take a pinch from.

 

[WhoDecidedThat]

11980HK beats 5980HX in multi core score? The only way that is even possible is if both were consuming over 70 watts of power (*see below) or if Intel chips are being allowed to consume more power than AMD and Apple chips. See my post, 2 posts down below for more on this.

So no, without showing us how much power these chips were consuming during the benchmark, these numbers are simply unreliable.

For all I know, M1 Max was consuming 40 (**see below) watts while 12980HK was consuming 80 watts during the test.

* Zen 3 is more efficient at lower power levels but its performance doesn't scale with power as much, Tiger Lake is less power efficient at lower power consumption but scales better than Zen 3 with power and there is a cross over around 70 watts - Jarrod made a YT video about this.

To put it simply. If both 5980HX and 11980HK are limited to 40-50 watts, AMD gives more performance, if both are allowed to consume 100 watts, Intel gives more performance.

** According to Anandtech, Apple's High Performance cores consume around 5 watts per core. So 8 of those performance cores would consume around 40 watts of power.

Intel, is notorious for pushing their chips to the limit and allowing them to consume upto 100 watts (in workstation laptops) and 200 watts (in desktops) to eke out as much performance as possible. Makes for great marketing, but horrible for using in a portable, lightweight laptop.

 

[yotano211]

So here's the fun thing about GeekBench: You can game it. Hard.

A custom kernel, malloc, or VM environment can swing the score hundreds of points on the same system with very minor tweaking. So as cool as this all looks I'll be here with the jar of salt for you all to take a pinch from.

No thanks, I cant eat sodium.

11980HK beats 5980HX in multi core score? The only way that is even possible is if both were consuming over 70 watts of power (*see below) or if Intel chips are being allowed to consume more power than AMD and Apple chips.

So no, without showing us how much power these chips were consuming during the benchmark, these numbers are simply unreliable.

For all I know, M1 Max was consuming 40 watts while 12980HK was consuming 80 watts during the test.

* Zen 3 is more efficient at lower power levels but its performance doesn't scale with power as much, Tiger Lake is less power efficient at lower power consumption but scales better than Zen 3 with power and there is a cross over around 70 watts - Jarrod made a YT video about this.

To put it simply. If both 5980HX and 11980HK are limited to 40-50 watts, AMD gives more performance, if both are allowed to consume 100 watts, Intel gives more performance.

The 5980hx was never release to any known laptop. I think I only saw 1 test of the 5980hx on notebookcheck.net

 

[WhoDecidedThat]

While I do believe that Golden Cove (Alder Lake) is more performant than Willow Cove (Tiger Lake), I am very suspicious about Golden Cove's power efficiency. I think it's not as good and that's why Intel is focusing on providing Gracemont cores.

Attaching screenshot for Geekbench 5.3 numbers for reference - Source Notebookcheck.net

11980HK scores around 8800-9800
5980HS scores 8600 despite being a HS/less TDP chip

According to the original post -
11980HK scores around 9200 (matches with notebookcheck's data, allowed to consume 70+ watts of power)
5980HX scores around 8200 (slightly lower score than data for 5980HS, which isn't allowed to consume more than 45 watts of power)

 

[yotano211]

here's my with a i7 11800h processor

 

[WhoDecidedThat]

here's my with a i7 11800h processor

any idea what power consumption looks like in the multi core test?

 

[yotano211]

any idea what power consumption looks like in the multi core test?

My laptop's processor can go upto 82w at 4.3ghz, running with a .060mv undervolt and liquid metal TIM.

 

[thesmokingman]

"Leaked" my ass... right.

 

[yotano211]

"Leaked" my ass... right.

Every tech company does it, its too draw up hype on new products.

 

[thesmokingman]

Every tech company does it, its too draw up hype on new products.

No doubt. It's especially hilarious and disingenuous from the company that claimed benchmarks don't matter though, lol.

 

[yotano211]

No doubt. It's especially hilarious and disingenuous from the company that claimed benchmarks don't matter though, lol.

no comment

 

[outpt]

move along nothing to see here.