Geekbench creator John Poole has explained why switching to Mac led to him creating the benchmarking tool – and how it helped diagnose a cracked heatsink in a more recent Mac …
Poole told the story to ArsTechnica’s Andrew Cunningham.
Geekbench’s cross-platform compatibility is part of its appeal, which has been baked into the benchmark since its earliest versions. It began at the height of the PowerPC Mac era when Apple’s hardware was exotic and niche and apps that ran on Mac OS X were relatively rare.
“I just switched over to the Mac back in about 2002,” Poole told Ars. “So I was getting used to that ecosystem. And then the [Power Mac] G5 came out and I thought, oh, this looks really cool. I went out, bought one of the new G5s, and it felt slower than my previous Mac. And I thought, well, this is really strange; what’s going on. … So, you know, I grabbed what [benchmarks] I could download and ran them and got really confused, because what the benchmarks were saying wasn’t jiving with my experience.
“So I actually went and I reverse-engineered one of the popular benchmarks and found that the tests were, for lack of a better word, terrible,” said Poole. “They weren’t really testing anything substantial, you know, doing really simple arithmetic operations on really small amounts of data, not really testing anything. And so I thought, how hard can it be to write a benchmark? Maybe I should write my own.”
The original Geekbench (called “Geekbench 2006” and apparently lost to time) supported Windows and macOS at launch.
There have been endless debates about how relevant and meaningful Geekbench scores are, in large part because it’s a short test which effectively measures peak performance rather than accounting for things like thermal throttling, which kick in during demanding use over a sustained period.
The piece argues that, for everyday usage, peak performance is relevant.
Launching an app, opening a file, or installing an update requires a lot of speed for a little while, but once those tasks are done, your CPU can go back down to the near-idle state it spends most of its time in, and rendering windows and dialog boxes only requires tiny blips of performance from your computer’s GPU.
The latest version has also been updated with tasks more people are carrying out, like creating background blur in video calls.
Poole acknowledges that Geekbench is less relevant for heavy-duty graphics tasks, like gaming or video rendering, but says there are specialist tools available for that. There’s a compromise between ease of use and in-depth measurements, and he wanted to create a simple tool anyone could use.
“I think that’s one of the reasons why [Geekbench is] so popular is that, you know, you just download the app, click a button, and you’ve got a result three minutes later,” said Poole […]
“But when you get to a lot of other ones, the cross-platform ones that people hold up as the gold standards of CPU comparisons, they’re bears to run and, like, only a handful of people can do that.”
He says that Geekbench can also be used to tell whether or not you have a hardware problem.
“Back a number of years ago, I was talking to a friend of mine who said, ‘Oh, yeah, I just used Geekbench the other day because my Mac felt slow,’” said Poole. “And ran Geekbench, the numbers were half of what they should be. He took it into the Apple Store, they opened up the laptop, and his heatsink had cracked in half.”
The top image, for example, shows that both the single- and multi-core performance of my MacBook Pro is exactly as it should be. You can download the latest version, Geekbench 6, from the Primate Labs website.
FTC: We use income earning auto affiliate links. More.
