CPU Performance

For my first two tests, I went with X264 HD benchmarks 4 and 5. These give us a look at encoding FPS. The first pass on both favors clock speeds and the second pass on 5.0 likes higher core counts. The i9-10900K has both so it isn’t a big surprise when it came in at the top for the first pass on 5.0 or on 4.0. The higher core count 3900X edges out the lead when it comes to the second pass in 5.0 however. The i5-10600K, on the other hand, is back a little farther. Running right with the Ryzen 5 3600X which is also a 6 core 12 thread CPU and in the older 4.0 test the 3600X beats the i5-10600K as well.





3D modeling is always popular and the open-source program blender is one of the best ways to get into it. I’ve run their standard benchmark on the quick benchmark setting. This test just times running through two files being rendered (BMW and Classroom). With the 10900K having crazy clock speeds on top of 10 cores it puts up a crazy score, significantly faster than anything else tested including the 3900X which took almost 3 minutes longer. The 10600K was slower than the 3600X but did come in a lot closer to the 9900K than I would have guessed.



Continuing with the video encoding theme I also have handbrake which is a which is an open-source transcoder. For this test I am taking a 4k video down to 1080p 30 FPS, the results are the average FPS of that task. Here the higher core counts did better and you can see most of the results sorted by core count.



For the always popular Cinebench, I ran the older R15 test which better fits a 4 core CPU and the new R20 for high core count CPUs. It's crazy how far out ahead the 3900X and the 10900K are compared to everything else tested in both multi-core tests. I wish we also had the 3950X to include here for a little better perspective, but for gaming-focused CPUs, they also have a lot of multi-threaded performance. The 3900X however with two more cores still stands out ahead. The 10600K is running with the 8 core first-gen Ryzen CPUs. The single-core tests, on the other hand, show off that boost clock speed getting out ahead of the 9900K by a lot as well which is crazy.









Ray tracing is picking up on the GPU side of things, but when it comes to rendering photos and sometimes videos it has been a thing for a while. I’ve run two benchmarks that check out the performance and in POV-Ray the higher core count CPUs still do better but nothing beats the 10900K in the single-core test. V-Ray is mostly sorted by core count as well but the 10900K is surprisingly close to the 3900X and the 10600K is a lot farther back from the 3600X than I would have expected.





Most people use CPUz to check out a few clock speeds, your BIOS version, and other information. But they do have a benchmark slipped in as well at the back and I like it because it does split up performance between multi-core and single-core. Now in the single-core results, the 10900K being way out ahead isn’t a shocker. The 10600K, on the other hand, wasn’t far behind. The multi-core test still has the 12 core 3900X out ahead as well as the older Core-X CPUs and with that, the newer Core-X CPUs as well that I haven’t had the chance to test simply with raw core counts. The 3600X did beat the 10600K there as well, but the gap was a lot closer that time around.





Going back to the basics I tested with wPrime which is an old overclocking favorite that takes a look at the time it takes to calculate prime out to 1024 million. Core count is still king here, but clock speed does help which is why overclockers have used this one. The i9-10900K is up near the top but the 3900X is ahead as well as the two high core count Core-X CPUs. The 10600K, on the other hand, is right with the 8086K and 8700K which is impressive considering they are based on the same architecture and same core count but have higher clock speeds.



7 Zip is another open-source program, this time for compressing and decompressing all of your files. Here I have run the benchmark and we have three results. The combined MIPS which is a combination of compressing and decompressing performance. Then I have it broken down between the two. This workload likes extra cores which can be seen with the Core-X CPUs and the 12 core 3900X still being ahead of the 10900K. The 10600K held its own but did still come in behind the 3600X but ahead of the 8700K and 8086K.



Jetstream 2 is a compilation benchmark which takes a long list of HTML5 and Java in browser tests and runs them all three times and puts together an overall score. I love this benchmark because let's be honest, most people are using their browser more than any other game or program. Jetstream gives some interesting results sometimes though. Both of the new CPUs ended up on top, but you can see how the 3300X is the fastest from AMD which doesn’t make much sense as well.



In Passmark Performance Test 9 I run the full CPU benchmark which favors core counts with the Core-X and 3900X out ahead. The 3700X here is a little unusual but the 10900K does have a significant jump up over the 9900K, The 10600K, on the other hand, is ahead of the 8700K/8086K but the 3600X is still way out in front.



PCMark 10 is a great test because it tests things like video calls, browser performance, excel and word performance to give an idea of real-world performance. It tends to like higher clock speeds and that is clear when you see that the 10900K and the 9900K are out in front. The 10900K did surprisingly well, coming in even well ahead of the 9900K. The 10600K was up near the top as well, right with the 8086K.



Dolphin 5.0 is a Wii emulator and like most emulators, it doesn’t care about high core counts at all. In fact, it only runs two in total. Clock speeds are king here, in addition to Dolphin favoring Intel in general. The 10900K completed the test in 265 seconds, 9 seconds faster than the 9900K, but the 10600K is the hidden gem here coming in third at a significantly better price.



Before diving into game testing I wanted to check out synthetic performance using 3DMark Fire Strike, focusing specifically on the Physics Score which is CPU dependent. The 10900K topped the chart here, out significantly on the 3900X and the 9900K as well. The 10600K was right with the 3600X and ahead of the older 8700K and 8086K.



For in-game performance testing on the i9-10900K and the i5-10600K, I ran them through a variety of new and old games. TF2, for example, is an oldie but a goodie which at this point is highly limited by CPU performance. The 5.3 boost clock for the 10900K did especially well here with the 9900K not far behind. The 10600K also did well, outperforming the 3600X as well. Deus Ex: Mankind Divided, Far Cry 5, and Shadow of the Tomb Raider all have the 10900K out ahead of everything else by a good margin. The 10600K did well on all but Far Cry 5 as well due to its 4.8 boost clock. Ashes of the Singularity was a little weirder, the 9900K had done well but the 10900K came in a little slower. Ghost Recon was similar as well.













I did also run the whole series of tests in AIDA64 which let us take a look at aspects like memory speeds, latency, and cache performance. There are so many results though I am unable to graph them all and keep them readable. The i5-10600K and the 3600X are right together with the L1 cache speeds but the 3600X is faster with the L2 and L4 cache results as well as with memory read speeds. The 10600K, however, has a much better memory latency. AES-256 calculations have the 3600X ahead again but then all of the 24/32/64 bit integer IOPS have the 10600K ahead. The i9-10900K rips through everything but the 3900X does run with it on the L2 cache numbers and especially L3 cache with that being over twice as fast on the 3900X. Memory speeds are faster on the 3900X but the 10900K has much better memory latency. Then like with the 10600K and the 3600X, the 10900K runs with the 3900X in single and double precision FLOPS, gets stomped in AES-256, and then had a big lead in all three of the integer IOPS tests.








Log in to comment

We have 1088 guests and one member online