Deutsch
Español
Français
Italiano
Nederlands
Polski
Português
Русский
Türkçe
Svenska
Chinese
MagyarNvidia RTX 4070 Laptop GPU in purported Galaxy Book 3 Ultra 36% faster than Apple M2 Max with 38-core GPU in Geekbench OpenCL
Apple M2 Max-powered MacBook Pros have just become available with the top configuration offering 12 CPU cores, 38 GPU cores, and up to 96 GB of unified memory. Apple did not provide any particular benchmark numbers for the M2 Max and while our review is en route, a new Geekbench score of the device is now available comparing it with the unreleased Nvidia RTX 4070 Laptop GPU.
According to the Geekbench entry, the Mac14,6 system features the 38-GPU core M2 Max with 64 GB of unified RAM and manages a score of 75,139 in the Geekbench OpenCL test. On the other hand, a Samsung laptop powered by an Intel Core i9-13900HK and Nvidia RTX 4070 Laptop GPU has amassed a score of 102,130 in the same test — a 36% increase.
Although Geekbench scores are comparable across platforms, these numbers are just from one sample each and don't tell the whole story. It is not clear how the performance of the Mac system, likely the new MacBook Pro 16, is overall and whether there's any thermal throttling. Going by past experiences with Apple silicon, thermal throttling is unlikely in a quick benchmark such as Geekbench, but this needs to be confirmed during testing.
Also, the TGP configuration of the Samsung laptop with RTX 4070 is not evident from the Geekbench database. The listed model number of the notebook, NP960XFH, indicates that this could likely be a Galaxy Book 3 Ultra, which Samsung is expected to unveil alongside the Galaxy S23 lineup on February 1.
Geekbench scores aren't exactly representative of real-world performance either. We've seen how Apple cherrypicked the M2 Max's performance to show it is better than even a Quadro RTX 6000 and an RTX 3080 Ti Laptop GPU.
Ultimately, it depends on specific workflows and how they have been optimized for the given hardware. Nevertheless, these scores do help in understanding relative positioning of these GPUs for an overall picture.
