Primate Labs Debuts New Geekbench Suite for AI-Centric Workloads - MacRumorsOpen MenuShow RoundupsShow Forums menuVisit ForumsOpen Sidebar
Skip to Content

Primate Labs Debuts New Geekbench Suite for AI-Centric Workloads

Following extended testing under the "Geekbench ML" name, Primate Labs is officially launching its new benchmarking suite optimized for AI-centric workloads under the name Geekbench AI. The tool seeks to measure hardware performance under a variety of workloads focused on machine learning, deep learning, and other AI-centric tasks.

geekbench ai
Geekbench AI 1.0 examines some of the unique workloads associated with AI tasks and seeks to encompass the variety of hardware designs employed by vendors to tackle these tasks, delivering a three-score summary as part of its benchmarking results to reflect a range of precision levels: single-precision, half-precision, and quantized data.

geekbench ai iphone
In addition to these performance scores, Geekbench AI also includes an accuracy measurement on a per-test basis, allowing developers to improve efficiency and reliability while assessing the benefits and drawbacks of various engineering approaches.

geekbench ai mac
Finally, the 1.0 release of Geekbench AI includes support for new frameworks and more extensive data sets that more closely reflect real-world inputs, improving the accuracy evaluations in the suite.

Geekbench AI is available for an array of platforms, including iOS, macOS, Windows, Android, and Linux.

Top Rated Comments

madmin Avatar
21 months ago
Does it measure for stupidity and hallucinations ?
Score: 4 Votes (Like | Disagree)
WarmWinterHat Avatar
21 months ago

It measures the performance of AI workloads, not the quality of LLM answers
Wish I could get measured like that at work. Do and say anything I want, great! It's all wrong and I'm killing patients, but I'd be fast!

:rolleyes:
Score: 3 Votes (Like | Disagree)
21 months ago

Does it measure for stupidity and hallucinations ?
It measures the performance of AI workloads, not the quality of LLM answers
Score: 3 Votes (Like | Disagree)
iF34R Avatar
21 months ago
1TB iPad Pro M4 didn't beat my my iPhone 15 Pro Max 256GB to death.

iPad M4
4701
7840
6814

iPhone 15 Pro Max
4046
6953
6065
Score: 2 Votes (Like | Disagree)
21 months ago

Are those results in these photos in the article real cuz all i got on my new Galaxy Fold 6 with all its AI features is this 😅

Edit: ok my 15 Plus does much worse besides in the Half Precision Score for some reason? At least Apple does not seem to be lying about its capabilities regarding Apple Intelligence support guess?
Apple intelligence is optimized for qunatized 3.5-4 bit. It may do worse with other precisions on iPhone 15. The scores don’t mean much unless the models are optimized for certain precision.
Score: 2 Votes (Like | Disagree)
21 months ago
Just a rename of geekbench ML, nothing new here. Clicking on the open button on the app store opens the ML app
Score: 2 Votes (Like | Disagree)
Related Apple News: Local News | Buyers Guide | Business | Travel | Health