Google has launched its much-awaited smartphones Pixel and Pixel 6 Pro powered by Tensor chip. Following the launch, many smartphone vendors started to compare this newly launched SoC. Although Google is highlighting the ML capabilities of the Tensor chip, synthetic benchmarks like GeekBench ML are not showing promising results.
Getting the latest comparison, the Apple A15 Bionic chip gives an amazing result and it is powerful than Google’s first in-house chip on the machine learning front as well.
Apple A15 Bionic vs Google Tensor Chip: GeekBench ML Scores
According to the Twitter user, Max Weinbach on Twitter and corroborated by Notebookcheck, Apple’s A15 Bionic shows better results on GeekBench ML across TensorFlow Lite CPU, GPU, and ML tests. While Tensor scored 313, 1359, and 1722 in CPU, GPU, and NNAPI, A15 Bionic scored 945, 2061, and 2212 in CPU, GPU, and Core ML categories.
Pixel 6 Pro Geekbench ML scores.
These interest me so much since, a, this is the first Google designed chip and Google designed mobile TPU. And b, in usage Google’s AI is faster, more accurate, and just better. Numbers don’t mean everything. #teampixel #giftfromgoogle https://t.co/y2gkPDovp2 pic.twitter.com/fcOMj2qxav
— Max Weinbach (@MaxWinebach) October 25, 2021
“We ensured different subsystems inside Tensor work really well together, rather than optimizing individual elements for peak speeds. Peak CPU and GPU speeds look great in benchmarks, but they don’t always reflect real-world user experience,” said Google Product Manager Monika Gupta at the Pixel Fall launch event keynote.
Did some benchmarking of the @Google #Tensor #SoC inside of the #Pixel6 and #Pixel6 Pro this weekend, here are some of the results… Do keep in mind that the Pixel 6 is running Android 12 while the others are running Android 11. First up, @Geekbench and GeekbenchML
— Anshel Sag (@anshelsag) October 25, 2021