Google Tensor is undoubtedly the most talked-about bit of the new Pixel 6 series. The chip has been marketed as going big on machine learning and supplying all the juice needed for stuff like Google’s improved computational photography and transcription abilities.

Pixel fans have thus been finding solace in thinking that where the Tensor stands weak in terms of performance, it makes up for it by its ML prowess. For the uninitiated, the Pixel 6 is outperformed by the latest Snapdragon 888 and Exynos 2100 phones, and of course, Apple’s A15 and even A14 Bionic chips.

However, in a new test performed by the folks at Notebookcheck, it was found that the Apple A15 Bionic chip even crushes the Google Tensor in the latter’s greatest strength – machine learning. The test was done on the new Geekbench ML app that has been developed specifically to measure machine learning performance.

The Google Tensor managed to score just 307 in the Geekbench ML TensorFlow Lite CPU test, which is under a third of the Apple A15’s impressive score of 939. The 307 figure isn’t terrible by any means but shows that it’s no match for Apple even after machine learning being the Tensor’s particular strength.

The test doesn’t end there though. The A15 scores 2727 in the neural accelerator test while the Tensor scores 1720. The Tensor closes the gap a tiny bit in the GPU test though scoring 1428 while the A15 responds with a higher score of 2727.

google tensor featured

All in all, the aggregate score of the A15 stands at 5,934 while Tensor gets 3,455. This means that the A15 is around 71% faster than the Google Tensor in machine learning tasks, at least in benchmark tests. Of course, the real-world performance can turn out to be a different story, but with the gap between the two chips this big, we doubt that will be the case.

We can cut the Tensor some slack here though considering that it’s actually Google’s very first self-developed chip. And for a first, it is rather impressive. Moreover, the chip actually managed to beat the Snapdragon 888, Exynos 2100, and Kirin 9000 in GPU benchmark tests as per a report.

Apple, on the other hand, has been shipping its custom-built chips in the iPhones for years now giving it a huge headstart.

RELATED: