![3700x geekbench 3700x geekbench](http://media.redgamingtech.com/rgt-website/2019/12/ps4-geekbench.jpg)
Here, PBO is very insignificant on performance. Both CPUs have the same core and thread count, but regardless Ryzen 7 5800X is 18% faster than the Ryzen 7 3700X, once again holding up to that IPC improvement claim. In the graph above we have the multi-core performance. This benchmark tests overall CPU performance and can show us a result in both multi-core and single-core performance. Next up we have the latest version of Geekbench 5.
![3700x geekbench 3700x geekbench](https://www.hartware.de/wp-content/uploads/2020/07/AMD-Ryzen-Renoir-4000-Series-Launch.jpg)
Adding PBO adds about 1% more performance. This holds up to the claim of the 19% IPC increase AMD claimed with Zen 3. The performance difference is much larger in these office applications, the Ryzen 7 5800X is 20% faster than the Ryzen 7 3700X. We have found this test to be rather sensitive to clock speed instead of core count. This test is very specific, it tests the performance of Microsoft Office, using Excel, Word, PowerPoint, and even Edge. In this graph, we are looking at PCMark 10’s Applications Benchmark. Adding PBO does not improve performance much in this benchmark, only by less than 1%. In this graph, we can see that the AMD Ryzen 7 5800X is 14% faster than the AMD Ryzen 7 3700X.
![3700x geekbench 3700x geekbench](https://i.ytimg.com/vi/_GkBaqDmGbM/maxresdefault.jpg)
PCMark 10 runs a gauntlet of different office, content creation, and desktop workloads. In this first graph, we are looking at PCMark 10 standard benchmark test, which is an overall system test. The Ryzen 7 3700X is also tested at default, without PBO. Otherwise, AMD Ryzen 7 5800X represents default CPU performance without PBO. In the graphs, AMD Ryzen 7 5800X PBO indicates Precision Boost Override being enabled in the BIOS for a +200MHz official AMD PBO overclock. Gaming performance will be shown later on. We are going to start with synthetic system application benchmarks on this page.