AMD Ryzen 5 9600X and Ryzen 7 9700X Review: Zen 5 brings upgraded gaming performance (Updated)

AMD Ryzen 5 9600X Productivity Application Benchmarks, the TLDR

We boil down productivity application performance into two broad categories: single- and multi-threaded. These slides show the geometric mean of performance in several of our most important tests in each of these categories, but be sure to look at the expanded results below for more granular analysis.

Image 1 of 2

The Ryzen 5 9600X and Ryzen 7 9700X deliver solid generational gains in single-threaded performance, matching or exceeding the price-comparable Intel models. The Ryzen 5 9600X is 8% faster in our cumulative measure of single-threaded performance than the prior-gen Ryzen 5 7600X and 4% faster than the Core i5-14600K. The Ryzen 7 9700X is 7% faster than the prior-gen Ryzen 7 7700X, and it trails the 14700K by a single point, or less than half a percent. That's close enough to call a tie. You'll also see plenty of examples in the benchmarks below where the Ryzen processors excel in mixed workloads (complex combined single- and multi-threaded workflows).

The Intel processors manage to keep their lead in our cumulative measure of heavily threaded productivity application performance, and often by large margins, but there are a few caveats of note (more on that below). The Core i5-14600K is 26% faster than the Ryzen 5 9600X in our cumulative measure of multi-threaded performance, while the 14700K is 41% faster than the Ryzen 7 9700X.

In threaded work, the Ryzen 5 9600X is 14% faster than the prior-gen 7600X, while the Ryzen 9 9700X is 7% faster than its prior-gen comparable, the Ryzen 7 7700X. Again, that's while consuming quite a bit less power, so the generational efficiency gains are even more impressive.

While the Ryzen 7 5800X3D and 5700X3D are exceptional in our gaming benchmarks, rivaling the Ryzen 9000 chips at a lower price point, pay attention to the huge disparities in application performance with these Zen 3 chips. Both Ryzen 9000 models are around 35% faster in single-threaded work than the 5800X3D. The 9600X is also 18% faster in threaded workloads than the 5800X3D, while the 9700X is 45% more performant. The deltas aren't quite as large with the 7800X3D, but even this Zen 4 gaming beast doesn't perform as well as standard chips in productivity apps.

We couldn't match AMD's guideline score for the multi-threaded Cinebench 2024 benchmark, lagging their reported score by roughly 5% for the 9600X and 9700X. However, our Cinebench 23 scores were within the expected variance. Cinebench 2024's sensitivity to memory throughput may impact the score — AMD's tests for the reviewer's guide use a DDR5-6000 EXPO profile for its 'stock' configurations. In contrast, we use the officially supported AMD spec of DDR5-5600. We retested with a DDR5-6000 EXPO profile and reduced the disparity to a more acceptable -2.5%, but the impact of the stock settings is included in the above geometric mean. As such, pay extra attention to the scores in the individual benchmarks below.

The slides above show the impact of the DDR5-6000 EXPO memory profile and the auto-overclocking PBO feature. Engaging this combo yielded a 9% improvement for the 9600X in the threaded benchmarks, bringing it within 15% of the stock 14600K config. The Ryzen 7 9700X also profits nicely from tuning, gaining 14% more performance in threaded work, reducing its deficit to the 14700K to 24%.

Intel's chips can overclock, too — at least normally. Unfortunately, given the current state of Intel's silicon, presenting overclocked benchmarks with the 14600K and 14700K could be misleading. However, be aware that the company intends to fix its issues with a microcode patch, at which time we will add overclocked test results.

The AMD chips also get an uplift in single-threaded work from PBO tuning — both chips get around 3% more performance from engaging PBO.

Rendering Benchmarks on AMD Ryzen 5 9600X

Image 1 of 14

We've included test results for Cinebench 2024 and R23. Both show distinct advantages for AMD's chips in single-threaded rendering, while the multi-threaded benchmarks favor Intel. Intel excels in both single- and multi-threaded POV-Ray and is also performant in C-Ray, Corona, and the various Blender workloads.

Encoding Benchmarks on AMD Ryzen 5 9600X

Image 1 of 8

Our tests include single-threaded encoding benchmarks, like LAME and FLAC, but the SVT-AV1 and SVT-HEVC tests represent a newer class of threaded encoders. AMD takes the win in LAME, the quintessential single-threaded benchmark, and also excels in the FLAC and SVT-AV1 encoders. Intel also carves out plenty of wins, taking the lead in SVT-HEVC and Handbrake.

Office Workloads on AMD Ryzen 5 9600X

Image 1 of 6

AMD scores substantial wins in the Procyon Adobe suite and also dominates the Microsoft Office and web browser benchmarks.

Compilation, Compression, AVX on AMD Ryzen 5 9600X

Image 1 of 18

This selection of tests spans from massively parallel molecular dynamics simulation code in NAMD to compression/decompression performance. Y-cruncher computes Pi with the AVX instruction set, making for an incredibly demanding benchmark. Many of these tests aren't very relevant to the target audience for this class of chip, but we include them for completeness.

Intel leads in the NAMD and LLVM compilation benchmarks, but as we've seen when AMD has made significant alterations to its core microarchitecture in the past, software tuning could yield big gains for Ryzen 9000 in the future.

AMD dominates the y-cruncher benchmarks, and we've now added the Pi-BBP y-cruncher benchmark. This variant of the benchmark isn't as sensitive to memory throughput as the standard threaded benchmark, making it better suited for testing the execution cores.

• MORE: Best CPU for gaming
• MORE: CPU Benchmark Hierarchy
• MORE: Intel vs AMD
• MORE: How to Overclock a CPU