Saturday, February 8th 2025
Intel Core Ultra 9 275HX Defeats Core i9-14900HX In Cinebench R23 Multi-Core, While Losing Out in Single-Core
The Intel Core Ultra 9 275HX was unveiled by Big Blue at CES 2025, packing 8 Lion Cove performance cores and 16 Skymont efficiency cores for a total of 24 cores and 24 threads, thanks to Intel doing away with Hyper-Threading support. As such, we already had quite low expectations for multicore performance from Arrow Lake-HX, although a recently listed Cinebench R23 run appears to confirm the contrary. However, considering the nature of leaks, be sure to accept this information with a fair amount of skepticism until more information comes our way.
To be honest, this result is quite a doozy, for the aforementioned reason. Like its predecessor, the Core Ultra 9 275HX will also boast the same number of performance and efficiency cores, without Hyper-Threading support. But somehow, the result indicates that the 275HX handily outperforms the Core i9-14900HX in multicore performance by ~11%, despite losing out in single-core performance by the skin of its teeth. Of course, there are plenty of desktop-replacement laptops that can pull off higher multicore scores, although it would be best to stick to median figures considering that the details of the tested system are not known. Clearly, something is going on here, that I am unable to wrap my head around. It is possible that Intel has massively improved multicore scaling, but that is not what we witnessed with a recent Passmark result, where the Core Ultra 7 255H portrayed healthy improvements over its predecessor in single-core, but not quite so in multicore.
Sources:
@94G8LA, Notebookcheck
To be honest, this result is quite a doozy, for the aforementioned reason. Like its predecessor, the Core Ultra 9 275HX will also boast the same number of performance and efficiency cores, without Hyper-Threading support. But somehow, the result indicates that the 275HX handily outperforms the Core i9-14900HX in multicore performance by ~11%, despite losing out in single-core performance by the skin of its teeth. Of course, there are plenty of desktop-replacement laptops that can pull off higher multicore scores, although it would be best to stick to median figures considering that the details of the tested system are not known. Clearly, something is going on here, that I am unable to wrap my head around. It is possible that Intel has massively improved multicore scaling, but that is not what we witnessed with a recent Passmark result, where the Core Ultra 7 255H portrayed healthy improvements over its predecessor in single-core, but not quite so in multicore.
60 Comments on Intel Core Ultra 9 275HX Defeats Core i9-14900HX In Cinebench R23 Multi-Core, While Losing Out in Single-Core
Regarding the removal of HT, is Intel using the "rentable units' tech with these ?
Note: In HPC world a difference greater than 5% is considered as a good improvement. On a Big Data set it will reduce processing time.
GGforever says 18%
Vya Domus says 12%
ScaLibBDP says 10%
Does anyone want to show math for 5%? 25%?
The result depends on what number is used as a base to compare with another number. So two possible cases:
...31,854 is lower than 35,481...
or
...35,481 is greater than 31,854...
Both results are Valid!
...
[ ScaLibBDP ] Calculate for how many percent 31,854 is lower than 35,481
[ Copilot ]
To find how much percent 31,854 is lower than 35,481, you can use the following formula:
Percent Lower=DifferenceOriginal Number×100\text{Percent Lower} = \frac{ \text{Difference} }{ \text{Original Number} } \times 100
Let's plug in the values:
\text{Difference} = 35,481 - 31,854 = 3,627 $$ $$ \text{Original Number} = 35,481
Now, use the formula to calculate the percent lower:
Percent Lower=3,62735,481×100≈10.22%\text{Percent Lower} = \frac{3,627}{35,481} \times 100 \approx 10.22\%
So, 31,854 is approximately 10.22% lower than 35,481
...
[ ScaLibBDP ] Calculate for how many percent 35,481 is greater than 31,854
[ Copilot ]
To find how much percent 35,481 is greater than 31,854, you can use the following formula:
Percent Greater=DifferenceOriginal Number×100\text{Percent Greater} = \frac{ \text{Difference} }{ \text{Original Number} } \times 100
Let's plug in the values:
\text{Difference} = 35,481 - 31,854 = 3,627 $$ $$ \text{Original Number} = 31,854
Now, use the formula to calculate the percent greater:
Percent Greater=3,62731,854×100≈11.39%\text{Percent Greater} = \frac{3,627}{31,854} \times 100 \approx 11.39\%
So, 35,481 is approximately 11.39% greater than 31,854
Those 10% we're not even sure of because both Intel CPUs can scale from 45W to 160W, so unless both CPUs run at the same power limits with similar cooling it's not a useful comparison for laptop chips.
ThrottleStop is great btw, I use it to disable bd_prochot on my MBP (dead battery, lol).. can't help the igpu though...
However...Because they aren't doing the math properly. This is basic 5th grade math people.
www.calculatorsoup.com/calculators/algebra/percentage-increase-calculator.php
To the find the percent increase, first subtract the initial value from the final value. Then take the difference and divide it by the initial value. Finally, multiply this number by 100 to convert the number to a percentage. This final result will represent the percent increase between the two values. So;
35481 - 31854 = 3627
3627 / 31854 = 0.1138632511
0.1138632511 * 100 = 11.38632511
The difference is 11.38% aprox.
EDIT:
All that said. 11.3% is a solid increase gen on gen.
So, 100 is 25% faster than 80 <=> 80 is 20% slower than 100 i.e. simple math :slap: