Sidebar Sidebar
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.

Primate Labs Launches Geekbench 6 Benchmarking Suite

MacRumors

MacRumors

macrumors bot
Original poster
Apr 12, 2001
67,708
38,185


Primate Labs today announced the launch of Geekbench 6, the newest version of the company's cross-platform benchmarking suite. Geekbench 6 is an upgrade from the existing Geekbench 5 that was introduced in 2019, and it includes support for new hardware standards along with results that better mimic real-world device performance.

geekbench-6.jpg

The updated software navigates away from heavy reliance on pure single-threaded CPU numbers, with machine learning and other workloads changing the way that benchmarks need to work. Testing datasets have been replaced to better "reflect modern hardware and applications."
  • Bigger photos in resolutions captured by modern smartphones (12 to 48MP)
  • HTML examples representative of modern web design standards
  • A larger library of images for import tests
  • Larger maps for navigation tests
  • Bigger and more modern PDF examples
  • An increase in Clang workload size.
Primate Labs says that the tests are able to better represent the file types customers are likely to use or interact with in 2023, and are closer to workloads used by apps. Geekbench 6 has been updated to take better advantage of the GPU for machine learning for more accurate cross-platform comparisons.

Multi-core benchmarking has been overhauled and is designed to measure how cores share workloads in true-to-life workload examples, and there are a number of new tests that measure how people use devices. Existing tests have been updated as well.
  • Background blur, as during video conferences
  • Photo filters, similar to those used by modern social media apps
  • Object detection for AI workloads
  • Photo library for importing and semantic tagging photos and metadata
  • Text processing for parsing and converting things like markdown and regex in Python (more true to real developer use cases)
Geekbench 6 is free for all non-commercial personal use, while the Pro version of the software is priced at $79 for the next two weeks thanks to a 20 percent launch discount. Pro functionality adds command-line automation, offline result management, and more. Geekbench 6 can be downloaded from the Geekbench website.

Article Link: Primate Labs Launches Geekbench 6 Benchmarking Suite
 
Article Link
https://www.macrumors.com/2023/02/14/primate-labs-geekbench-6/
  • Like
  • Wow
  • Love
Reactions: amartinez1660, DeepIn2U and sorgo †
I click on the links and it only shows me Geekbench 5, is it only me?

EDIT: Now I got version 6
 
Last edited:
Interesting. Can someone please explain how the new benchmarks can still serve as a valid comparison with older hardware that has only run the previous version(s), given that the tests have changed with the new version? Or can they? Doesn’t changing the test defeat the very purpose of a benchmark? Do we need to run the new benchmarks on old hardware before it can be compared with new hardware?
 
  • Like
Reactions: NightFox and DeepIn2U
walkin said:
Interesting. Can someone please explain how the new benchmarks can still serve as a valid comparison with older hardware that has only run the previous version(s), given that the tests have changed with the new version? Or can they? Doesn’t changing the test defeat the very purpose of a benchmark? Do we need to run the new benchmarks on old hardware before it can be compared with new hardware?
Click to expand...
I imagine it will no longer serve as a valid comparison, similar to when 5 came out to replace 4. We're starting a whole new database today onwards.
 
  • Like
Reactions: 23cam32, amartinez1660, TheRoadRunner and 2 others
My M1 MBP is significantly higher in scores than under Geekbench 5. so did they recalibrate (it says they used an i7 with a baseline of 2500 or something), or did they optimize the code better?
 
MauiPa said:
My M1 MBP is significantly higher in scores than under Geekbench 5. so did they recalibrate (it says they used an i7 with a baseline of 2500 or something), or did they optimize the code better?
Click to expand...
you can never truly calibrate results between different benchmarks.
same with Cinebench, Heaven etc...
 
  • Like
Reactions: l0stl0rd
Great. But can they PLEASE update VoodooPad 5??? The app has gone nowhere since Primate Labs bought it. It's a big let down for the VoodooPad community. Used to be such a great app and Primate Labs have sunk it.
 
MacBook Pro (14-inch, 2021)Apple M1 Pro 3220 MHz (10 cores) 16Go OS Monterey
Geekbench 5:
Single-Core 1770
Multi-Core 12561
OpenCL 38159
Geekbench 6:
Single-Core 2408
Multi-Core 12401
OpenCL 39863
Metal 56238

"Geekbench 6 scores are calibrated against a baseline score of 2,500 (which is the score of an Intel Core i7-12700)."
 
Last edited:
  • Like
  • Love
Reactions: DeepIn2U, ikjadoon, Tyler O'Bannon and 1 other person
At the end of the day, synthetic benchmarks can't compete with real world usage. 99% of Apple users would be more than happy with the base model, but we just like nice things.
 
  • Like
Reactions: AAPLGeek
Mr. Dee said:
At the end of the day, synthetic benchmarks can't compete with real world usage. 99% of Apple users would be more than happy with the base model, but we just like nice things.
Click to expand...
I'm not included in that 99% of Apple users. I also don't roll with the base models. From Apple, I want the BEST OF THE BEST. :p
 
  • Like
  • Love
  • Haha
Reactions: BigMcGuire, Leon Ze Professional, _Spinn_ and 7 others
You must log in or register to reply here.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Top Bottom
Back