Tuesday, October 1st 2024
24-Core Intel Core Ultra 9 285 Falls Short of 8-Core Ryzen 7 9700X in Geekbench Leak
The leaks and rumors surrounding Intel's upcoming Arrow Lake desktop CPU line-up are starting to heat up, with recent rumors tipping the existence of the Core Ultra 9 285K as the top-end chip in the upcoming launch. A new set of Geekbench 6 scores spotted by BenchLeaks on X, however, suggests the Core Ultra 9 285 non-K variant of this CPU might lag its Ryzen 9 counterparts significantly.
The Geekbench 6 test results, which were apparently achieved on an ASUS Prime Z890-P motherboard, reveal performance that falls short of even the current-generation AMD Ryzen 7 9700X, never mind any of the Ryzen 9 variants. The Geekbench 6 multicore score came in at an unimpressive 14,150, while the single-core score was a mere 3,081, falling short of the likes of the AMD Ryzen 7 9700X, which scored up to 19,381 and 3,624 in multi- and single-core tests, respectively. However, there appears to be more to this story—namely an odd test configuration that could heavily skew the test results, since the "stock" Intel Core Ultra 9 285K scores significantly higher in the Geekbench 6 charts than this particular 285 seems to.
Apparent engineering samples of the Intel Core Ultra 9 285K that made it onto the Geekbench 6 charts have registered multicore scores as high as 21,447, which puts the K-SKU CPU with the same core layout and very similar clock speeds significantly ahead. Digging into the results a little, it appears that the ASUS test platform powering the Core Ultra 9 285 CPU only had 8 GB of DDR5 RAM running at 5586 MT/s, while Core Ultra 9 285K tests that scored much higher had up to 32 GB of DDR5 RAM running at up to 5598 MT/s.
That said, the listed base clock speeds of the Core Ultra 9 285's E-cores are also significantly lower than those of the top-scoring Core Ultra 9 285K, at just 2.5 GHz, compared to the 285K's 3.7 GHz base frequency. This could also explain some of the discrepancy.
Geekbench isn't known to be very RAM-dependent, with the benchmark's largest working set being on the order of 1.6 GB, so there may be some validity to this benchmark score, however it wouldn't be surprising to see the CPU perform significantly better in subsequent benchmarks. At the very least, this Geekbench score validates previous rumors about the expected hardware configuration of the Intel Core Ultra 9 285 and 285K CPUs:
Sources:
BenchLeaks, Geekbench browser, Geekbench 6 documentation (PDF)
The Geekbench 6 test results, which were apparently achieved on an ASUS Prime Z890-P motherboard, reveal performance that falls short of even the current-generation AMD Ryzen 7 9700X, never mind any of the Ryzen 9 variants. The Geekbench 6 multicore score came in at an unimpressive 14,150, while the single-core score was a mere 3,081, falling short of the likes of the AMD Ryzen 7 9700X, which scored up to 19,381 and 3,624 in multi- and single-core tests, respectively. However, there appears to be more to this story—namely an odd test configuration that could heavily skew the test results, since the "stock" Intel Core Ultra 9 285K scores significantly higher in the Geekbench 6 charts than this particular 285 seems to.
That said, the listed base clock speeds of the Core Ultra 9 285's E-cores are also significantly lower than those of the top-scoring Core Ultra 9 285K, at just 2.5 GHz, compared to the 285K's 3.7 GHz base frequency. This could also explain some of the discrepancy.
Geekbench isn't known to be very RAM-dependent, with the benchmark's largest working set being on the order of 1.6 GB, so there may be some validity to this benchmark score, however it wouldn't be surprising to see the CPU perform significantly better in subsequent benchmarks. At the very least, this Geekbench score validates previous rumors about the expected hardware configuration of the Intel Core Ultra 9 285 and 285K CPUs:
- 8 P-cores
- 16 E-cores
- 24 threads
- Base clock: 2.5 GHz (P-core base clocks will likely be higher)
- Boost clock: 5.586 GHz (likely only for the P-cores)
45 Comments on 24-Core Intel Core Ultra 9 285 Falls Short of 8-Core Ryzen 7 9700X in Geekbench Leak
Exciting times for CPUs though looking forward for reviews. They better all be tested on 24H2 not some older OS.
That said, i agree with the point of waiting for proper and hopefully, unbiased reviews.
But yes, these kind of articles shouldn’t be posted without more data or proof.
Even bolder statement was made towards Lunar Lake iGPU being the most powerful iGPU in the industry. However, Strix Point's iGPU wins in most of modern games:
www.notebookcheck.net/Intel-Arc-8-Cores-iGPU-Benchmarks-and-Specs.782930.0.html
www.notebookcheck.net/Intel-Arc-Graphics-140V-Benchmarks-and-Specs.854991.0.html
www.notebookcheck.net/Intel-Lunar-Lake-iGPU-analysis-Arc-Graphics-140V-is-faster-and-more-efficient-than-Radeon-890M.894167.0.html
The thing is, Intel had been presenting this Lunar Lake as a sort of "everything-beating-and-with-battery-ever-lasting" premium laptop solution.
Boottom line:
Multicore performance is weak. iGPU average performance improvement over Arc 8 (in productivity tasks) is just around+13%, gaming performance on average is better by 26% over Arc 8 according the video above, by NotebookCheck it's better on average by only 10% over Arc 8. Previous bold promises were at first +50% over Arc 8, later +30% over Arc 8. Lunar Lake delivers great single core performance. Battery life and iGPU efficiency is a huge step forward compared to Intel Ultra 100H CPUs/iGPUs and AMD Strix Point. All in all, it's a mediocre product: promised iGPU performance not delivered, ARM battery life not beaten, AMD Strix Point not beaten in most games (tested at 28W = full speed for Lunar Lake).
To name a few even Cyberpunk 2077 ran like a$$ on AMD shortly after launch. That's how good AMD is. :D
90% of games are optimized for Intel and don't run well on multiple CCX. The single CCX you mention was like one midrange CPU from AMD's line in their previous gen. WoOw. Looking for more your brilliant thoughts. Please do share. :kookoo:
Let me tell you how it works: The 7800X3D have one single CCX, and not really mid range in terms of gaming performance.
Try google before posting next time lol
Say hi to 2019 from me! :love:Oh you mean the launch FOUR YEARS ago? I hope you're feeling better now. Maybe time to connect to internet and get those updates.
Runs like ass my ass.
Games don't give a f*** about modular design of a processor. They care about cores, they don't know which core will OS assign to them. That's CPU and/or OS scheduler's thing. It's ill-advised to optimize a game for particular MCM design. When you take into account a fact, that a chiplet will hold different amount of cores in the future, that would basically mean a never ending optimization nightmare for game developers.
Intel have been using chiplet design for almost 2 years now, started with Meteor Lake and Sapphire Rapids. On the contrary to monolithic approach, chiplets enable manufacturer to reuse partially defective clusters (CCX or tiles) for other purposes. Monolithic chip production was going well with small (up to 4 cores) CPUs, but as CPU size raises, so raises the production defect rate.
Yes, there comes a latency penalty with chiplet approach, but no one will care anymore. Chiplets generate more money than monolithics and money makes the world go round, not inter-chiplet latencies.
I dunno, but mobile CPU reviews are too heavily constained by individual laptop SKU characteristics. It's way too early to make a conclusion.
Just look at last generation. Now I'm not saying this is an apples to apples comparison, these three have an 8 core IGP, with two running at 2250 MHz (155h, 28W), and the other one is 2350 MHz (185H, 45W), different RAM speed, and last but not least, using different laptop chassis with different cooling and firmware. Also, I have no idea if they have the same power limitations.
That's not important, all I'm saying is that one single SKU can't tell us everything. Despite the minimal differences, one is 53% faster than the other, one is 29% faster. Yes, 45W is quite a lot more than 28W, I know. Keep focused on the two 155H models instead.
Chances are that something faster than the S 14 exists, just like the Magicbook is so much faster than the Galaxybook.
The fact is, Intel does this always. Just like Intel says that their 18A is healthy and already so smooth that it can run some RAM speeds out of the box and boot stuff, yet Broadcom sees things differently. Newest rumors speak about intel having set their goal too high to achieve, meaning the yield rate is very bad, like what's Samsung currently facing with its 3nm node.
Arrow lake was meant to be fully made on 20A and supposed to be already here (delivered in H1 2024), the reality is TSMC 3nm and October 2024.
Man, if I don't know what will come, I rather don't make bold statements again, and again, and again, and again.
There's a saying: Pride comes before a fall. I don't want for Intel to fall, but it would served them right.
Your "reality" is ONE laptop, and just like when Meteor launched, something faster might show up that we don't know about.
We can't conclude much from on SINGLE model like you do.
I'm not saying the review is wrong. Maybe this review is 99.9% correct on what that IGP can do. Maybe it isn't.