Early M2 Max benchmark scores appear to be leaking on Geekbench

Enlarge / The 2021 16-inch MacBook Pro. Samuel Axone
It seems that the first benchmarks of Apple's upcoming M2 Max chip have leaked in the Geekbench database.

When users run the standard version of the Geekbench 5 benchmarking tool, scores are stored in a public results database and tied to specific hardware inputs. In this case, the result (which was discovered by a Twitter user) is listed under a product titled "Mac14.6" running the as-yet-unreleased "macOS 13.2 (Build 22D21)" operating system. The entry also noted that the chip has 12 cores.
The chip in question is likely intended for the MacBook Pro and Mac Studio models that will be launched next year. As for the results: the single-core overall score is 1,853 and the multi-core score is 13,855. M1 Max.
While these results are both legit and representative of the end product, they might be a disappointment to some. Compared to our Geekbench 5 tests of a 16-inch MacBook Pro with the M1 Max, this represents about a 6% improvement in single-core performance and an 11% increase for multi-core.

This performance difference isn't too far off from the comparisons between the low-end M1 and M2 that have already been introduced, so it's not too surprising that they're accurate.

That said, there are several caveats to consider. First, these synthetic benchmarks may be good for a rough idea of relative performance between devices, but that doesn't mean they always reflect real-world performance. Second, the M2 Max results seen here may not represent the final product. Well, they might not be real at all.

So yeah, there are a lot of caveats. Ars readers will know to take this with a whole pound of salt, but it's interesting to see and speculate on any account.

Technology Dec 1, 2022 0 21 Add to Reading List

Early M2 Max benchmark scores appear to be leaking on Geekbench

The front of a closed silver-colored laptop on a table

It seems that the first benchmarks of Apple's upcoming M2 Max chip have leaked in the Geekbench database.

When users run the standard version of the Geekbench 5 benchmarking tool, scores are stored in a public results database and tied to specific hardware inputs. In this case, the result (which was discovered by a Twitter user) is listed under a product titled "Mac14.6" running the as-yet-unreleased "macOS 13.2 (Build 22D21)" operating system. The entry also noted that the chip has 12 cores.

The chip in question is likely intended for the MacBook Pro and Mac Studio models that will be launched next year. As for the results: the single-core overall score is 1,853 and the multi-core score is 13,855. M1 Max.

While these results are both legit and representative of the end product, they might be a disappointment to some. Compared to our Geekbench 5 tests of a 16-inch MacBook Pro with the M1 Max, this represents about a 6% improvement in single-core performance and an 11% increase for multi-core.

This performance difference isn't too far off from the comparisons between the low-end M1 and M2 that have already been introduced, so it's not too surprising that they're accurate.

That said, there are several caveats to consider. First, these synthetic benchmarks may be good for a rough idea of relative performance between devices, but that doesn't mean they always reflect real-world performance. Second, the M2 Max results seen here may not represent the final product. Well, they might not be real at all.

So yeah, there are a lot of caveats. Ars readers will know to take this with a whole pound of salt, but it's interesting to see and speculate on any account.