The Tensor G3 debuted in Google’s Pixel 8 and Pixel 8 Pro last year, and while the company introduced a range of improvements, the chipset turned out to be significantly slower than the competition. As is typical of successive releases, the Tensor G4 is expected to bring various upgrades, but how extensive will they be? Here, we look at all the differences between the two SoCs so you can decide if upgrading to any of the forthcoming Pixel 9 models is worth it.
Tensor G4 vs Tensor G3 - Specification differences show a downgrade in the total number of cores
On paper, it would appear that the Tensor G4 is slightly downgraded compared to the Tensor G3, as a leaked CPU configuration of the upcoming SoC revealed that it features a ‘1 + 3 + 4’ cluster. In contrast, the Tensor G3 has a ‘1 + 4 + 4’ configuration, which means that the Tensor G4 will potentially deliver lower multi-core performance, right? Not exactly, because Google relies on faster cores to complete the job. For instance, instead of the Cortex-X3 and Cortex-A715, which were a part of the Tensor G3, the upcoming silicon should get its performance boosted thanks to the inclusion of the Cortex-X4 and Cortex-A720.
As for the low-power cores, the Cortex-A520 will boast better capabilities than the Cortex-A510, assuming the Tensor G4 can keep its thermals in check. Coming to the GPU side of things, future buyers wanting to get their hands on any Pixel 9 model will be disappointed to learn that the Tensor G4 and Tensor G3 share the same ARM Mali-G715 GPU, with the only difference being that the newer SoC’s graphics processor is clocked at a slightly higher 940MHz.
Based on a multitude of tests that we have seen in the past, a slightly overclocked GPU does little to bump real-world performance, so the actual benefit will likely be witnessed when running synthetic benchmarks. For those wanting the entire configuration of both chipsets, the details are given below:
Tensor G4 - One Cortex-X4 running at 3.10GHz, three Cortex-A720 running at 2.60GHz, and four Cortex-A520 running at 1.95GHz. ARM Mali-G715 GPU running at 940MHz.
Tensor G3 - One Cortex-X3 running at 3.00GHz, three Cortex-A715 running at 2.45GHz, and four Cortex-A510 running at 2.15GHz. ARM Mali-G715 GPU running at 890MHz.
To be honest, with the Tensor G3 previously rumored to be based on Samsung’s unreleased Exynos 2300, Google missed an opportunity to adopt the Exynos 2400’s 10-core configuration for the Tensor G4, which would deliver some meaningful performance in the multi-core department. Unfortunately, it appears that the advertising giant has other plans, but customers who view the Pixel 9 lineup just by looking at these specification differences will probably get the impression that the latest flagship models are just a stop-gap launch.
Initial benchmark results show that the Tensor G4 obtains different scores based on which Pixel 9 it is found in
The interesting bit that we found in the past few days, and that too before Google officially announces the Pixel 9 series and the Tensor G4, is that the latter does not perform the same in every flagship. In an earlier performance comparison, we found that the base Pixel 9 actually performs worse than the Pixel 8, but the Pixel 8 Pro is up to 11 percent faster than the Pixel 8. In a separate AnTuTu test, it was found that the top-end model, the Pixel 9 Pro XL, was 33 percent faster than the Pixel 8, with the performance barrier closing when compared with the Pixel 8 Pro.
The obvious question to ask is why such a performance disparity exists. Unfortunately, there is not one correct answer. Perhaps it could be that Geekbench 6 and AnTuTu are not yet updated to recognize the Tensor G4’s performance. It is also possible that the Pixel 9 Pro and Pixel 9 Pro XL are equipped with a better cooling solution, such as a vapor chamber, that allows the chipset to maintain its performance for more extended periods. It may be likely that there are two versions of the Tensor G4, one that has adopted the FOWLP or ‘Fan out Wafer Level Packaging’ and one that has not.
It is obvious that the Tensor G4, which uses superior packaging, will be incorporated into the premium Pixel 9 models, whereas the base version will be treated to the regular variant. For those who do not know, FOWLP employs more I/O connections, so electrical signals can pass through the chipset faster and more efficiently. This type of packaging also helps in heat resistance, allowing the SoC to maintain higher levels of multi-core performance since its temperature can be controlled.
Google introduced these differences with the Pixel 8a release, which arrived with a slower version of the Tensor G3, so who is to say that the company will not bring differences to the Tensor G4 later this year? Unfortunately, we will only find out during a thorough analysis of the chipset, but rest assured, we are prepared for such events to materialize.
What is the actual benefit of upgrading to any Pixel 9 model if the Tensor G4 is such a minor upgrade over the Tensor G3?
Even if the Tensor G4 is not compelling enough to warrant an upgrade over the Tensor G3, it is not only the silicon that must be watched closely regarding improvements. The Exynos 5400 5G modem is expected to be a part of the package, with the baseband chip said to bring satellite connectivity support, along with up to a 50 percent improvement in power consumption. Google is reportedly bringing increased on-device capabilities that are baked into the Tensor G4, but given its lack of raw processing power, we still believe that the majority of those functions will be cloud-based.
Remember that we will be revisiting the Geekbench 6 and AnTuTu results to see if a future update better represents the Tensor G4’s performance. Even then, two benchmarks do not conclude that a silicon is slower than the competition and there will likely be a myriad number of tests run to provide an impartial overview. Then again, based on what we know so far, our impression is that if the efficient 5G modem and improved on-device AI capabilities impress you, then make an upgrade, but we are confident that it is not on the checklist for most buyers. Regardless, please participate in our poll below and let us know your thoughts.
About the author: Omar Sohail is a reporter and analyst for Wccftech's mobile section, specializing in the technology and business of the mobile industry. His expertise lies in the intricate hardware supply chain, covering developments in semiconductor manufacturing, chip lithography, and camera sensor technology.
Follow Wccftech on Google to get more of our news coverage in your feeds.
