Puget Systems print logo
Read this article at https://www.pugetsystems.com/guides/588
Article Thumbnail

Core i7 5960X vs. 4960X Performance Comparison

Written on August 29, 2014 by Matt Bach


Typically, a new CPUs is faster than it's predecessor - it is just a question of whether is it by a little or a lot. The new Intel 5960X, however, is not typical because it sacrifices clock speed in order to add more cores. More cores is definitely better from a forward-thinking standpoint, but currently there is a lot of software that is not coded very well for multithreading so the drop in clock speed may cause a drop in performance.

The Intel Core i7 5960X is an eight core 3.0GHz CPU that has a maximum turbo boost of 3.5GHz. This means that while it has two more cores than the Core i7 4960X, it also has a .5-.6GHz drop in clock speed.

CPU Specifications 5960X 5930K 4960X
Cores/Threads 8/16 6/12 6/12
Clock Speed 3.0GHz 3.5GHz 3.6GHz
Max Turbo Boost 3.5GHz 3.7GHz 4.0GHz
L2 Cache  8 x 256KB 6 x 256KB 6 x 256KB
Smart Cache 20MB 15MB 15MB
PCI-E Lanes 40 PCI-E 3.0 40 PCI-E 3.0 40 PCI-E 3.0

In this article we want to run a wide variety of benchmarks to find out what applications benefit from the additional cores and which suffer from the drop in clock speed. In order to provide another point of comparison, we will also be including the new Intel Core i7 5930K in our testing. It doesn't have quite as high of a clock speed as the 4960X, but it is high enough that with the other improvements in Haswell-E and X99 it may actually outperform the 4960X.

It's worth pointing out that while we are primarily focusing on the CPU, Haswell-E uses the new X99 chipset which includes many improvements including DDR4 support. So in addition to the CPU itself, the chipset and DDR4 RAM may very well affect our benchmarks. For more information on what is new in Haswell-E and X99 we recommend reading our X79 vs X99: What is new in X99 and Haswell-E article.

Test Setup

To benchmark these CPUs, we used the following hardware:

For the majority of our testing, we used two systems to expedite our testing. For the thermal and power draw portions, however, we used the exact same CPU cooler, chassis, and power supply to remove as many variables as possible. For the duration of our testing, the CPU fan was set to the standard QFan profile and the chassis fans were run at 5v.

All Windows, driver, and software updates were applied prior to testing.

Next >
Tags: X99, Haswell-E, X79, Ivy Bridge-E, 5960X, 5930K, 4960X, Benchmark