Conclusion
Intel Core Ultra 200S Series CPUs are launching now, on October 24th, 2024. In our review today we have taken a good hard look at the new Intel Core Ultra 9 285K for $589 suggested eTail, and the Intel Core Ultra 5 245K for $309 suggested eTail pricing.
The Intel Core Ultra 9 285K is Intel’s flagship desktop CPU sporting 8 P-Cores and 16 E-Cores for up to 5.7GHz boost, with 24 cores and 24 threads for $589. Then, at the more affordable $309 range sits the Intel Core Ultra 5 245K desktop CPU sporting 6 P-Cores and 8 E-Cores at up to 5.2GHz, with 14 cores and 14 threads. These CPUs are based on new Lion Cove P-Cores and Skymont E-Cores and use Intel’s new disaggregated tiled architecture with Intel packaging several tiles in their design.
How Do They Compare
In our performance testing today, we benchmarked the CPUs in several different workloads to look at multi-core/multi-thread performance and single-core/single-thread performance. We included gaming performance, using in-game manual run-throughs in 8 games.
We also tested the Arrow Lake CPUs in the “Balanced” Windows Power Mode profile and “Best Performance” due to the performance differences we experienced. This allowed us to give a comprehensive look at performance, and we also included the 14900K in the BIOS Extreme and Performance profiles as well.
If you are looking at the Intel Core Ultra 5 245K compared to the AMD Ryzen 5 9600X, it is clear that the new Intel Core Ultra 5 245K will offer substantially better multi-core performance. It may be the better CPU if you do workloads that require many cores, or you do a lot of multi-tasking. However, for gaming, the opposite is true. The AMD Ryzen 5 9600X is a much better, and more consistent, CPU for gaming with no thread scheduling issues thanks to its single-CCD nature.
The waters become more murky when you throw the AMD Ryzen 7 9700X into the comparison. It does do much better in multi-core performance a lot of the time and also has great success in allowing consistent gameplay performance with its single-CCD nature, i.e., no thread scheduling issues.
Either way, the 9600X and 9700X are the better CPUs for gaming performance, than the Intel Core Ultra 5 245K. For multi-threading, the 245K is better than the 9600X, but the 9700X challenges the 245K since it can do well in multi-threading and performs great in games, giving you both options.
If you are looking at the Intel Core Ultra 9 285K compared to the AMD Ryzen 9 9950X, you basically have to figure out what your main workloads will be. Overall, the Ryzen 9 9950X seems to offer great single-core/single-thread performance, and this can help a lot of office or productivity/multi-tasking workloads.
That said, in the right scenario the Intel Core Ultra 9 285K can do quite well in multi-threading performance, but in the right workloads. Because the Ryzen 9 9950X is better in single-core/single-thread performance it is also the better gaming CPU, even though it is a dual-CCD design. There are many inconsistencies with the Intel Core Ultra 9 285K when it comes to the gaming experience.
Power
In terms of power, the new Intel Core Ultra 9 285K does utilize less power than the previous generation, improves upon that design, and runs much cooler. The most impressive in this area is the Intel Core Ultra 5 245K, which does have noticeable power savings and temperature reduction.
In comparison to the competition, the AMD Ryzen 9000 CPUs (Zen 5) are overall more power efficient for the performance delivered. While the Intel Core Ultra 9 285K and Core Ultra 245K do use less power, they are also less performant in many scenarios compared to the previous generation. The AMD Ryzen 9000 series CPUs maintain this power efficiency and deliver performance as well.
Windows 11 Power Profile
Quite honestly, we are baffled as to why the Windows 11 Power Mode profile option is affecting single-core/single-thread performance so much. We would understand multi-core performance, and perhaps the CPU hitting a power cap, but that shouldn’t be the case in single-thread workloads. However, as a result of this degradation in performance gaming performance is drastically reduced in the Windows default “Balanced” Power Mode profile.
This is not typical on the previous Raptor Lake platform, or the AMD Ryzen/Zen 4 and 5 platform. As you can see in our testing, the performance of those parts on the default “Balanced” Power Mode profile is quite good, and as expected. In fact, AMD recommends “Balanced” for the best performance, this was heavily made clear during the Zen 5 launch when performance results were all over the place with that one. In fact, in Intel’s reviewer’s guide, Intel states this: “We generally leave operating system settings at their defaults as a typical end user will most likely not alter these settings.”
Our testing today has indicated that “Balanced” will show degraded performance on Arrow Lake CPUs. For comparison sake, we were also able to run a test between “Balanced” and “Best Performance” in Windows 11 23H2, and we experienced the same behavior, causing a performance difference in PCMark between the power settings. Therefore, this is a thing that is not restricted to the new 24H2 version of Windows. Users should be aware of this if you want the most potential out of your new Arrow Lake CPU.
Final Points
Much like AMD Zen 5, Arrow Lake may look better as it matures over time. BIOS updates to refine microcode, software updates, and perhaps Windows updates to refine thread management could occur, and we hope they do. With some maturity, Arrow Lake can be competitive, and with maturity can hopefully show its full potential.
When thread scheduling works well across the P-Cores and E-Cores, performance is competitive, but when it does not, then it suffers, and sadly Windows is terrible at managing this currently. Game performance can really suffer when game threads are thrown over to the E-Cores, and switch between P and E-Cores frequently, sadly, this happens, and the gaming experience is diminished because of it.
- Thread Scheduling Issues – There are potentially thread scheduling issues, or latency issues, causing performance variances, and inconsistencies. The result is degraded gaming performance and potentially odd application performance in certain Windows power modes.
- Frequency Reduction – The boost frequencies being lowered this generation seem to harm single-core/single-thread performance overall. The result of this is degraded gaming performance and certain day-to-day workloads that benefit from single-core boosts, or lightly threaded applications.
- Competitive Multi-Threading Performance – Arrow Lake can have competitive multi-core/multi-thread performance compared to the competition, it actually does quite well in this area despite not having SMT/Hyperthreading.
- Not Your Gaming CPU – Arrow Lake is not built well for gaming performance. The result is inconsistent gaming experience, and degradation in gaming performance due to single-core/thread and frequency. There are options from the competition, in the form of X3D 3D V-Cache parts if gaming is your goal.
- Intel Core Ultra 5 245K – Compared to the competition’s 9600X, the Core Ultra 245K is a worthy competitor specifically to that CPU given the pricing segments, and multi-thread performance offered on the 245K.
Are the Intel Core Ultra 9 285K and Intel Core Ultra 5 245K good CPUs? The CPUs have their place, for the right dollar amount. The Intel Core Ultra 9 285K and Core Ultra 5 245K are not bad multi-core/multi-thread performing CPUs, in fact, this is their strong suit. If you require workloads that are multi-threaded or do content creation, video rendering, or 3D rendering, they can be appealing for those tasks. What will be challenging will be new AMD holiday promotions that have been announced, which could eventually just become the norm in pricing. If that’s true, then the battle is very strong and there’s a hard road ahead for Arrow Lake.
Discussion (19 replies)
Join Discussion →Those are some dissapointing results for gaming, kinda leaves me at an annoying point, 9800X3D is only an 8 core providing it launches when it's rumoured to (early november) rest is early next year and I don't realy want to go previous gen.
Also like I said in the other thread, the ultra 9 and 5 are already sold out at some outlets around here. intel still going strong (or no stock to speak off)
There are people who will buy Intel even when they have no logical reason to do so. I work with a guy like that. He won't buy anything else because of the reputation non-Intel CPU's had in the 1990's.
Gotta know supply to gauge demand...
My take: This is a transitional product that lays the ground work for future releases. This isn't remotely the first time Intel has done this. The Wilamette Socket 423 Pentium IV's were such a product. It introduced RAMBUS memory and they were often out performed by their Pentium III counterparts, especially Tualatin CPU's. The socket Northwood Socket 478 stuff was a lot better. The Prescott core CPU's were also kind of transitional as these were built with even deeper pipeline stages to ramp the clocks up even more. Their EM64T extensions were present on the core but weren't enabled (excluding one model) until the transition to LGA sockets.
Unfortunately, the only real benefit to these is that they shouldn't have any degradation and stability issues in games where as the 13th and 14th generation CPU's did prior to microcode updates and BIOS updates were created to mitigate them. Assuming your CPU wasn't degrading to start with.
Not competitive, high price, a short lived platform and Win 11 is a mess. Nothing ever works as intended at launch. What is wrong with these companies? Fumbling the ball at the 1-yd line seems to be the norm. Bush league overall...
@Brent_Justice - what I'm seeing about is that by decoupling the memory controller from the compute die, Intel has added latency to main memory access. Do we know if this is reflected in say AIDA64?
@Dan_D - looks like we're going to have to see if Intel can overcome the above latency issue the same way AMD did when they went to chiplets with Zen.
I think they can. How they would be able to mitigate this is unclear to me but this is the type of thing Intel is typically good at engineering their way through historically. Generally speaking, Intel's CPU's have not been effected by latency to the same degree as AMD's. AMD for one reason or another has always dealt with that to some degree. AMD's answer for the most part was simply to throw L3 cache at the problem which doesn't work in all scenarios.
Though throwing L3 cache at the problem is a simple fix, but its a costly one.
AMDs use of stacking for the L3 cache on a CCD, which in turn they can use for gaming SKUs as well as enterprise (which they originally created them for), is genius.
Imagine slow(er) Zen 3 and Zen 4 cores (both clockspeed and IPC vs. Alder/Raptor P-cores) not only outrunning them but also doing so at 1/2 the power draw for gaming.
Now imagine Intel P-cores backed up by enough L3 cache to make memory latency irrelevant.
I think Intel needs to copy AMD here (or emulate? imitate?) and find a way to get that cache in a die with broader market appeal (i.e. also usable in Xeons). Their chiplet setup should enable them to do so.
One thing that's been sticking in my mind with the Arrow Lake release is that this is the first time Intel has decoupled their memory controller from their compute dies since... Core 2? At least in the consumer space (so not talking about buffered DIMMs). AMD did with Zen 2 IIRC. Intel has been using IMCs since Lynnfield in the i7 870 from 2009, 15 years ago!
I'm not sure that this is even possible. I think there are probably scenarios where simply adding cache doesn't help.
Well, AMD had an integrated memory controller since the Athlon 64 days. However, Intel's Core 2 Duo/Core 2 Quad were the last CPU's to have an off-die memory controller. Though it was in the chipset at the time and not anywhere on the CPU itself.
I believe its two things:
1. Consumers buy products that suck on the promise that they will be fixed later
2. Development practices that involve the term: MVP (Minimum Viable Product)
Number 2 combined with number 1 just continuously lowers the bar for number 2.
Thanks, @Brent_Justice for the very detailed review of these CPUs and extra testing with both power modes. It's a shame that APO isn't supported for the games reviewed, especially since they are popular titles that users are likely to have in their libraries. I wonder if Intel will be able to provide updates later on which might improve those results. Really interesting how CB2077 has a prioritize P-core option that only further proved there are other potential gains to be had.
A lot to unpack with these and obviously Intel is experimenting with a number of strategies with them.
I will have more information in an upcoming review, but installing some DDR5 CUDIMMs 8400, but running at 8200 MT/s currently, AIDA64's Cache Mem latency result is 88ns this is at 8200MT/s CL40-50-50-128 CR2. I will have some memory comparison data in an upcoming article at 6400, 8200, 8400 and 8600 on this motherboard with this RAM kit, so stay tuned. But my first reaction is that this isn't bad latency, I think it was worse at the beginning of all this, but as new BIOS's have come out, latency has improved. MSI's fix notes state XMP and memory performance optimization with the new BIOS releases I'm using.
I really want an all P-Core option, an 8-Pcore only or 12-Pcore only CPU would be a great option for gaming.
I am NOT a fan of big.LITTLE / hybrid architecture on x86 desktops. Intel please give us P-core only options!
I would prefer only p-cores too, but due to the lack of HT would we not require like at least a 10 or12 core if you need 8 for games already.
I mean testing conditions is one thing, but a real everyday use system usually has more running in the background then just the bare minimum.