The first M1 Macs were out in the wild for almost three full months, and Intel is starting to fear. The company shared a detailed slideshow of benchmark results this week Tom’s hardware (over Six colors) to show that there are several ways Apple Silicon still has a head start … depending on how you look at things.
One focus of Intel is on what is known as “productivity”. The company compares its 11th generation Tiger Lake processors with Apple’s M1, for example to surf the Internet and use Microsoft Office. Intel says:
Comparison of Microsoft Office 365, which runs natively on Intel and Apple processors: The 11th generation system performs some functions, such as PDF export, up to 2.3 times faster (compared to Apple M1).
Comparison of the most popular web browser (Chrome) with native versions on Intel and Apple processors: The 11th generation system is more than 30% faster overall and almost three times faster in the online photo test subtest (compared to Apple M1).
Other Intel benchmarks also focus on things like content creation with software from Adobe and Topaz Labs, as well as games.
Intel also compared the M1 to Intel Evo, the “second generation upgrade to Project Athena to make the best portable devices.”
There are some bizarre results from testing between the M1 and Evo, with Intel claiming that the M1 in the MacBook Pro failed when using Zoom and PowerPoint, for example. Tom’s hardware explained:
Intel claims that the M1 in the MacBook Pro we tested failed eight out of 25 tests, including “Switch to Calendar” in Outlook, “Start Video Conference” in Zoom, and “Select Picture Menu” in PowerPoint. Intel’s workloads don’t explain how to do them, but they’re also simple tasks that work reasonably well on just about any modern processor. So you are an odd choice. (I had many Zoom conferences testing the MacBook Pro with no issues.)
There are several things to consider with these tests. Primarily, these tests were conducted by Intel and should therefore be treated with skepticism. Of course, the company will pick the specific tasks where Intel chips may do even better than Apple’s M1.
For example, Tom’s hardware points out some suspicious decisions Intel made while testing battery life:
During battery life, Intel switched to an Intel Core i7-1165G7 notebook, the Acer Swift 5, instead of sticking to the Core i7-1185G7 in the whitebook that was used for performance testing. A MacBook Air was also tested. They ran Netflix streams and tabs and found that the MacBook Air had a difference of six minutes.
Intel has not given the battery life for the MacBook Pro. In our tests, it beat Intel PCs for hours.
Intel’s timing in releasing this counter-argument for Apple Silicon is also fascinating. Jason Snell at Six colors points out that the M1 is a low-end chip for low-end systems and Intel “only has a small window” to be able to find cheap comparisons:
Inconsistent test platforms, changing arguments, left out data and the not-so-faint touch of despair. Today’s M1 processor is a low-end chip for low-end systems. Therefore, Intel has only a small window in which to compare itself to these systems before high-end Apple silicon Macs are shipped and make work considerably more difficult.
If interested, see Intel’s full slideshow presentation at Tom’s hardware.
FTC: We Use Income Earning Auto Affiliate Links. More.