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

abufrejoval

Reputable
Jun 19, 2020
321
222
5,060
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.
 
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.
 

maik80

Commendable
May 21, 2021
70
20
1,535
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
 
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.