We talked about this a few weeks ago Google Tensor G2The next-generation SoC that the Mountain View giant will use in the Pixel 7 and Pixel 7 Pro, and we highlighted the very important question, raw performance or specialization, brawn or brains?

The first information we had so far indicated that the Mountain View giant is going to repeat the Google Tensor G1 approach, that is, it will once again bet on prioritize artificial intelligence and deep learning, and for the functions and features that both enable, they put raw performance in the background. First the brain and then the muscles.

Thanks to a new leak, we were able to see that this information was not misleading at all, and that the performance of the Google Tensor G2 in Geekbench 5 is worse than the Snapdragon 888, the chip that was at the top of the range a year ago and which is behind the current Snapdragon 8 Gen1. It goes without saying that if these performance figures are confirmed in the final version of the Google Tensor G2, this SoC would fit more into the current mid-range and not reach the high-end.

The Google Tensor G2 SoC in the Google Pixel 7 Pro gets a Geekbench score of 5 1,068 single-threaded and 3,149 multi-threaded. To compare these results, we have data on the performance of the Snapdragon 888 used in the Lenovo Legion 2 Pro, which achieved 1115 points in single thread and 3581 points in multiple threads. The difference isn’t huge, but it’s more than enough to put the Google Tensor G2 a step behind the Snapdragon 888.

But that’s not all, thanks to data collected by Geekbench 5 we know that the Google Tensor G2 will have an 8-core CPU divided into three blocks, one with two Cortex-X1 cores high performance at 2.85 GHz, another s two Cortex-A76 cores to 2.35 GHz and further s quad-core Cortex-A55 low consumption at 1.8 GHz GPU did not show, but we can expect ARM Mali.

Looking at the architectures that Google used, it is clear where the problem is and why the Google Tensor G2 is not able to be on par with the Snapdragon 8 Gen1. The Qualcomm chip uses a much higher configuration at the CPU level because yes Cortex-X2 core on 3 GHz, triple-core Cortex-A710 at a frequency of 2.5 GHz and quad-core Cortex-A510 at a frequency of 1.8 GHz

If we put it into perspective and look at the medium term, it is evident that when the Snapdragon 8 Gen2 is launched, planned for the end of the year, the Google Tensor G2 it will position itself even worse and will be framed directly in the middle range. In any case, the Mountain View giant has already made it clear with the Pixel 6 and Pixel 6 Pro that it can create value over raw power, so let’s not be pessimistic and give it faith, in the end all this can be compensated by important improvements at the level of computational photography and other features , which relies on artificial intelligence and deep learning.