Core i9-13900K & Ryzen 9 7950X Scaling Performance: CPU Short Form

For the compute side of our testing to determine how well the Core i9-13900K and Ryzen 9 7950X scale at different power levels, we've opted for a range of CPU-intensive benchmarks, particularly from the rendering and encoding section of our test suite.

To keep the playing field even, we are using the same SK Hynix DDR5-5600B 2 x 16 GB memory kit throughout all of our testing. We've separated the results within the same graph to outlay performance differences at different power levels so that users can see the differences and comparison in performance on offer from both the Core i9-13900K and Ryzen 9 7950X processors.

CineBench R23: Single and Multi-Threaded Performance

CineBench R23 Single Thread

CineBench R23 Multi-Thread

Focusing on performance in CineBench, it is worth highlighting that in the single-threaded test, Intel's Core i9-13900K displayed better single-core performance throughout. It didn't impact single-threaded performance on either processor despite restricting the power levels, which is exactly what we'd expect to find. While highly clocked CPU cores are very expensive from a power perspective, they are not so expensive as to consume the complete power budget of chips such as these.

Looking at multi-threaded performance in CineBench R23, this is where restricting the power levels makes the difference. Although Intel has the best performance in CineBench R23 MT at stock settings, it's AMD that scales better (i.e. loses less performance) as the power is restricted. Even at 65 W, the Ryzen 9 7950X is faster than the Core i9-13900 at 125 W, which is very impressive. Both processors take a massive hit in performance at 35 W, which is to be expected as we're now some 200 Watts below their stock power limits.

C-Ray 1.2: 4K, 16 Rays Per Pixel

C-Ray 1.2: 4K, 16 Rays Per Pixel

Looking at the results in our C-Ray benchmark, the results between stock settings to 65 W impacted our figures. Starting with the Ryzen 9 7950X, there was a marginal performance loss between stock settings at 125 W and 105 W. Going from stock settings to 65 W (2.5X power), there was a drop in C-Ray performance of around 16%.

Focusing on the Core i9-13900K, its performance was heavily power reliant when comparing stock settings to 125 W, 105 W, and 65 W. Even from stock settings to 125 W, there's a performance loss of around 21%, and even more so comparing stock settings to 65 W, which equates to around 38%.

Things tailed off massively when both set to 35 W, with the AMD Ryzen 9 7950X beating the Intel Core i9-13900K convincingly here.

POV-Ray 3.7.1: 

POV-Ray 3.7.1

In our POV-Ray benchmark, we saw some interesting behavior. Although the Core i9-13900K at default settings comfortably beat the Ryzen 9 7950X, the 7950X held its performance well when dropping down the power, with the 7950X's result at 65 W being similar to the 13900K at 105 W. This shows that the Ryzen 9 7950X and its 5 nm die is more scalable at lower power.

Blender 3.4: CPU Only Compute

Blender 3.4 BMW27: ComputeBlender 3.4 Classroom: ComputeBlender 3.4 Fishy Cat: Compute

At default settings, the Core i9-13900K and Ryzen 9 7950X was competitive in all of the Blender sub-tests, even when restricting the power. Once power was restricted, we saw that the 7950X held onto much of its performance, while the 13900K didn't fare so well. In the Fishy Cat subtest at 65 W, the 7950X was 62% faster than the 13900K, which is impressive scaling here by AMD.

x264 Encoding: 1080p and 4K Bosphorus

x264, Bosphorus 1080px264, Bosphorus 4K

The x264 benchmark focuses on encoding performance, and at default settings, AMD's Ryzen 9 7950X wins out. Even dropping down to 125 W, the 7950X only loses around 2% at 1080p and around 4% at 105 W. At 65 W, the 7950X is around 16% slower than at default settings.

Looking at Intel's Core i9-13900K, the 13900K loses around 15% performance by restricting power to 125 W compared to default settings. This is another example that the 5 nm Zen 4 architecture scales much better at lower power envelopes than Intel's 10 nm refresh; this isn't unexpected, however.

Exploring CPU Power Scaling On Core i9-13900K and Ryzen 9 7950X Core i9-13900K & Ryzen 9 7950X Scaling Performance: Peak Power/Temps & Gaming
Comments Locked


View All Comments

  • cbutters - Friday, January 6, 2023 - link

    Would be really cool to see this type of content for the GPU side of things... The 4090 seems to be VERY efficient and retains performance even when reducing the power drastically.
  • icoreaudience - Friday, January 6, 2023 - link

    These results should really be reported using an external power meter.
    The reports from internal probes can be incorrect, if not "doctored", and the "command" to enforce a given power limit can be widely interpreted, as evidenced by some of these tests.

    On this last point, AMD is the worst cheater, with > 30% difference between the "claimed" power limit and the reported one. This has worked well for them, since they can score "great" performance results at low TDP ... just by not respecting the TDP.

    This is an important point, because as long as news outlets continue to fall for this false reporting trick, there will be a direct incentive for chip manufacturers to cheat even more. Pretty soon, we'll have meaningless "TDP limit", and countless "tech expert" praising the efficiency of the one that cheats the most.
  • tygrus - Friday, January 6, 2023 - link

    You could spend more time ensuring the power caps can be the same in practice (your caps were in theory but not followed by CPU on average).
    It does show that Intel performance/power curve is flatter & rewards greater power usage. AMD perf/pwr curve is flatter so it doesn't pay to overclock it but does reward underclocking. Just imagine if AMD could keep its low freq efficiency but get Intel scaling on top.
  • Cooe - Friday, January 6, 2023 - link

    TL;DR = AMD's going to absolutely MURDER Intel in laptops this generation. Dragon Range-HX vs Raptor Lake-HX is going to be an absolute freaking bloodbath in AMD's favor...
  • corinthos - Sunday, January 22, 2023 - link

    why are the likes of ASUS dropping AMD and going Intel-only this next gen for their laptop lines then?
  • trenzterra - Friday, January 6, 2023 - link

    Is there a reason why Intel has such low temps compared to AMD at the same power usage? Seems like in a SFF PC or laptop using Intel would mean a cooler chassis despite drawing more power?
  • cyrusfox - Friday, January 6, 2023 - link

    Look at the actual power used, AMD seems to be sipping 30 watts more than advertised, that is likely one reason, the other has to be the IHS with the chiplets, probably not providing good equal contact as well as the IHS being much thicker, See derbauer's video on that from June 2022 "Very thick IHS and less Contact Area - some thoughts on Ryzen 7000"

    Harder to transfer that heat when the IHS is more insulating and slowing the transfer out of the chip into the heatsink. Intel will always win temp to temp comparison unless it is delidded.
  • HideOut - Friday, January 6, 2023 - link

    Or you can buy one of those newly announced non X varients of the AMD chips. Lower costs and lower power out of the box.
  • mirancar - Saturday, January 7, 2023 - link

    gavin, can you please also measure actual power usage from wall socket. from other reviewers there was a big obvious difference between amd’s tdp and intel’s tdp. then you should try to match the tdps to actual power. also would be nice to try and recomend best settings for both processors. i ordered a 13900k and i plan to run it on around 180-200w tdp, where i am hoping for max 75c on full load with a nh-d15
  • Hresna - Tuesday, January 17, 2023 - link

    I measured wall power for my 13900k using a self-reporting corsair PSU and hwinfo logging. My system has high idle power because of some power hungry components but it gives a more detailed view of how the power scaling metrics pan out. My results available here:

Log in

Don't have an account? Sign up now