CPU Performance: Synthetic Tests

As with most benchmark suites, there are tests that don’t necessarily fit into most categories because their role is just to find the peak throughput in very particular coding scenarios. For this we rely on some of the industry standard tests, like Geekbench and Cinebench.

GeekBench4: Synthetics

A common tool for cross-platform testing between mobile, PC, and Mac, GeekBench 4 is an ultimate exercise in synthetic testing across a range of algorithms looking for peak throughput. Tests include encryption, compression, fast Fourier transform, memory operations, n-body physics, matrix operations, histogram manipulation, and HTML parsing.

I’m including this test due to popular demand, although the results do come across as overly synthetic, and a lot of users often put a lot of weight behind the test due to the fact that it is compiled across different platforms (although with different compilers).

We record the main subtest scores (Crypto, Integer, Floating Point, Memory) in our benchmark database, but for the review we post the overall single and multi-threaded results.

Geekbench 4 - ST OverallGeekbench 4 - MT Overall


The main tool for ordering the TOP500 computer list involves running a variant of an accelerated matrix multiply algorithm typically found from the LINPACK suite. Here we use a tool called LinX to do the same thing on our CPUs. We scale our test based on the number of cores present in order to not run out of scaling but still keeping the test time consistent.

This is another of our new tests for 2020. Data will be added as we start regression testing older CPUs.

LinX 0.9.5 LINPACK


Cinebench R20

The Cinebench line of tests is very well known among technology enthusiasts, with the software implementing a variant of the popular Cinema4D engine to render through the CPU a complex scene. The latest version of Cinebench comes with a number of upgrades, including support for >64 threads, as well as offering a much longer test in order to stop the big server systems completing it in seconds. Not soon after R20 was launched, we ended up with 256 thread servers that completed the test in about two seconds. While we wait for the next version of Cinebench, we run the test on our systems in single thread and multithread modes, running for a minimum of 10 minutes each.

Cinebench R20 Single ThreadedCinebench R20 Multi-Threaded

CPU Performance: Web and Legacy Tests CPU Performance: SPEC 1T


View All Comments

  • Gastec - Friday, May 22, 2020 - link

    "pairing a high-end GPU with a mid-range CPU" should already be a meme, so many times I've seen it copy-pasted. Reply
  • dotjaz - Thursday, May 21, 2020 - link

    What funny stuff are you smoking? In all actual configurations, AMD doesn't lose by any meaningful margin at a much better value.
    Anandtech is running CPU test where you set the quality low and get 150+fps or even 400+fps, nobody actually does that.
  • deepblue08 - Thursday, May 21, 2020 - link

    Intel may not be a great value chip all around. But a 10 FPS lead in 1440p is a lead nevertheless: https://hexus.net/tech/reviews/cpu/141577-intel-co... Reply
  • DrKlahn - Thursday, May 21, 2020 - link

    If that's worth the more expensive motherboard, beefier (and more costly) cooling, and increased heat then go for it. If you put 120fps next to 130fps without a counter up how many people could tell?Personally I don't see it as worth it at all. Nor do I consider it a dominating lead. But I'm sure there are people out there that will buy Intel for a negligible lead. Reply
  • Spunjji - Friday, May 22, 2020 - link

    An entirely unnoticeable lead that you get by sacrificing any sort of power consumption / cooling sanity and spending measurably larger amounts of cash on the hardware to achieve the boost clocks required to get that lead.

    The difference was meaningful back when AMD had lower minimum framerates, less consistency and -30fps or so off the average. Now it's just silly.
  • babadivad - Thursday, May 21, 2020 - link

    Do you need a new mother board with these? If so they make even less sense than they already did. Reply
  • MDD1963 - Friday, May 22, 2020 - link

    As for Intel owners, I don't think too many 8700K, 9600K or above owners would seriously feel they are CPU limited and in a dire/ imminent need of a CPU upgrade as they sit now, anyway. Users of prior generations (I'm still on 7700K) will make their choices at a time of their own choosing, of course, and not simply because 'a new generation is out'. (I mean, look at 8700K vs. 10600K results.....; looks almost like a rebadging operation) Reply
  • khanikun - Wednesday, May 27, 2020 - link

    I was on a 7700k and didn't feel CPU limited at all, but decided to get an 8086k for the 2 more cores and just cause it was an 8086. For my normal workloads or gaming, I don't notice a difference. I do reencode videos maybe a couple times a year. The only times I'll see the difference.

    I'll probably just be sitting on this 8086k for the next few years, unless something on my machine breaks or Intel does something crazy ridiculous, like making some 8 core i7 on 10nm at 5 ghz all core, in a new socket, then making dual socket consumer boards for it for relatively decent price. I'd upgrade for that, just cause I'd like to try making a dual processor system that isn't some expensive workstation/server system.
  • Spunjji - Friday, May 22, 2020 - link

    Yes, you do. So no, they don't make sense xD Reply
  • Gastec - Friday, May 22, 2020 - link

    Games...framerate is pointless in video games, all that matters now are the "surprise mechanics". Reply

Log in

Don't have an account? Sign up now