AMD Ryzen 5 9600X and Ryzen 7 9700X Review: Zen 5 Impresses, But 7800X3D Still Reigns for Gaming

AMD’s Ryzen 9000 CPUs have arrived, marking the debut of the more powerful and efficient Zen 5 architecture and a quartet of Dragon Ball Z meme-adjacent processor numbers: the 9600X, 9700X, 9900X and 9950X. Today we’re taking a look at the first two processors, the six-core 9600X at £269/$279 and the eight-core 9700X at £339/$359. These mainstream offerings are due to go on sale on August 8, with the 12- and 16-core Ryzen 9 models scheduled to arrive a week later.

With faster X3D variants in games rumored to be coming later this year and heavily discounted Ryzen 7000 parts already on the market, are the new Ryzen 9000 models worth picking up in the meantime? And how do these processors compare to the top-tier Ryzen 7 7800X3D, which we recommended as the best high-end gaming CPU?

To find out, we tested these processors and some of their closest AMD and Intel rivals in a range of demanding games from 1080p to 4K, as well as taking a look at synthetic and content creation benchmarks to get an idea of ​​whether these new Ryzen 9000 processors offer a noticeable improvement over their predecessors.

We expect a decent boost in most workloads, with AMD’s data showing an average 16 percent boost in IPC (instructions per clock, a measure of single-core power) at similar clock speeds to the outgoing Ryzen 7000X CPUs and on the same AM5 socket and 700-series motherboards. (AMD also announced X870 and X870E motherboards with USB 4 as standard and faster memory support, but we haven’t received those for testing yet.)

The speed gains here are achieved through a combination of architectural improvements (like an improved branch predictor, better AVX-512 support, and doubled data bandwidth between the L2 and L1 caches) and the move to a more efficient 4nm CCD. This means we should expect better power efficiency from the new cores, and indeed the parts are all rated at lower TDPs than their Ryzen 7000 predecessors (65W vs. 105W for the Ryzen 5/7).

Finally, the improved thermal resistance means that temperatures at the same TDP should also be lower: AMD claims a 7°C reduction at the same TDP, which is impressive.

We’re using a similar physical setup to our previous Ryzen 7000 tests, including the ASRock X670E Taichi motherboard, G.Skill Trident Z5 Neo DDR5-6000 CL30 RAM, and an Eisbaer Aurora 240mm AiO. The big difference is that our RTX 3090 has been swapped out for an RTX 4090 Founders Edition, providing a slew of extra graphics performance that should push modern CPUs even further.

While Ryzen 9000 is the star of the show, we also tested a selection of older Ryzen 3000 and 5000 processors as well as popular 14th Gen Intel processors. Our Intel CPU test was run on the Gigabyte Aorus Z790 Master using the same DDR5-6000 CL30 RAM, while the AM4 CPUs were tested on the classic Asus ROG Crosshair 8 Hero with a Trident Z Royal DDR4-3600 CL16 kit.

For storage, we use a 4TB Lexar NM790 PCIe 4.0 NVMe SSD and a 4TB Kingston KC3000. Our rig is rounded out with a Corsair RM1000x 1000W power supply. Testing was performed with the latest Windows updates (23H2), chipset drivers, and BIOS revisions (3.06 for the ASRock AM5 board) installed.

The content creation benchmarks serve two purposes here. First, they serve as synthetic benchmarks with useful differentiation between single-core and multi-core results, allowing us to see where the new CPUs are compared to their rivals and where they’re trying to squeeze their advantages. Second, they’re obviously useful for showing real-world performance in similar workloads, with Cinebench simulating the 3D modeling and animation program Cinema 4D, while Handbrake is literally just transcoding a raw DF Patreon video, a common task for anyone working with video.

Let's first look at the Cinebench 2024 results. This is the first time we've used this test, which runs for at least ten minutes to ensure that processors aren't able to quickly get a good score before thermal or power limitations kick in. This makes for a long total runtime, especially with the task assigned to a single CPU core, but it's a reasonable upgrade given the power of modern CPUs.

Here, the 9600X and 9700X do a good job of showing improvements of 16 percent and 18 percent over their last-gen predecessors in single-core scores, very close to the 16 percent IPC average AMD measured in their benchmarks. Multi-core performance is a bit more modest, with improvements of 11 percent and just four percent for the 9600X and 9700X, respectively.

I noticed that in these tests the CPU only maxed out at 62°C, so I ran the test with a higher TDP of 105W using PBO in the BIOS, which gave me more performance at the expense of temperature.

Cinebench R20 is a legacy test for us, having run it in a huge number of previous CPU reviews, so we thought it was worth running in case you wanted to go back and compare results. We saw similar margins here gen-over-gen (+14 percent single-core for both Ryzen 9000 CPUs), but it’s worth noting the Intel threat as well.

The 14600K offers a multi-core score of 9420, which the 14700K bumps up to 13614, and Intel's best Ryzen 7 is only 7851 at the stock 65W TDP, or 8908 after the TDP caps are increased to 105W. This is due to a few factors, most notably higher core counts for Intel's CPUs, including 14 cores for the 14600K (6P+8E) and 20 for the 14700K (8P+12E) compared to the six- and eight-core 9600X and 9700X. Intel motherboards are also typically more aggressive when it comes to power delivery at stock settings, which is especially helpful for these types of all-core workloads, but it comes at the cost of higher power consumption and more heat to dissipate.

Our final test is the Handbrake transcoding test, where we convert an 822MB 4K video file using the H264 and H265 codecs using the Production Standard preset set to CRF 18. Here we are using the latest version of Handbrake, 1.8.1.

These transcoding results show the first slightly worrying signs of underperformance, with the H264 benchmark running just three percent faster on the 9600X than the 7600X, though the H265 benchmark speeds up by around eight percent, perhaps due to those AVX architectural improvements. The 9700X is even stranger, actually losing nearly three percentage points to the 7700X in the H264 test, something that has remained unchanged across multiple retests. Normalcy is restored in the HEVC test, though only by one percent.

Raising the 9700X's TDP to 105W in the BIOS results in a more significant 14 percent improvement over the stock 7600X, but at higher temperatures, between 80 and 90 degrees Fahrenheit, compared to the 60 degrees Fahrenheit we saw with the stock power limits.

With the content creation benchmarks completed, let's move on to the main event: the gaming benchmarks.

Analysis of AMD Ryzen 5 9600X and Ryzen 7 9700X