Geekbench 7 • Hacker News Board

Re: Geekbench 7

#51

Post by zamadatix » Fri, Jul 24, 2026, 1:56 PM UTC

wtallis wrote: post #13

zamadatix wrote: post #9

Earlier quoted context omitted.

It bothers me because there is no reason it can't just give 3 results: single, mixed/low thread, all core and yet there is often debate on which 2 numbers in such benchmarks instead. But, of all of the 2-pick-only options, choosing a custom mix and calling it multi-core requires guessing your actual workload on both the content of the mixed test suite as well as the scaling profile of the CPU to reason with. On the o…

> But, of all of the 2-pick-only options, choosing a custom mix and calling it multi-core requires guessing your actual workload on both the content of the mixed test suite as well as the scaling profile of the CPU to reason with. Yes, that's pretty much the whole point of Geekbench: to offer non-experts a way to measure CPU performance and produce scores that are relevant to a specific class of devices and users and…

It has nothing to do with whether it's an expert benchmark or not, even the dumpster fire that is UserBenchmark manages to show the three categories separately. It's just a bad practice among any kind of benchmark, basic or not. After all, the Geekbench is already doing the work needed during the tests.

Re: Geekbench 7

#52

Post by wtallis » Fri, Jul 24, 2026, 2:32 PM UTC

zamadatix wrote: post #51

wtallis wrote: post #13

Earlier quoted context omitted.

> But, of all of the 2-pick-only options, choosing a custom mix and calling it multi-core requires guessing your actual workload on both the content of the mixed test suite as well as the scaling profile of the CPU to reason with. Yes, that's pretty much the whole point of Geekbench: to offer non-experts a way to measure CPU performance and produce scores that are relevant to a specific class of devices and users and…

It has nothing to do with whether it's an expert benchmark or not, even the dumpster fire that is UserBenchmark manages to show the three categories separately. It's just a bad practice among any kind of benchmark, basic or not. After all, the Geekbench is already doing the work needed during the tests.

Geekbench is not just intended to be used to benchmark consumer systems, it is intended to be used by consumers to benchmark their systems and to have its scores interpreted by consumers. For that audience, the most important thing that a multi-core score needs to do is counteract the naive assumption that a 20-core CPU will be twice as fast as a 10-core CPU. Having one of the top-line scores be a perfectly-scaling multi-core score that you know will be widely misinterpreted by your audience and used by vendors to mislead consumers would be serious benchmarking malpractice.

Re: Geekbench 7

#53

Post by adrian_b » Fri, Jul 24, 2026, 3:30 PM UTC

aurareturn wrote: post #34

BoingBoomTschak wrote: post #23

Earlier quoted context omitted.

What you want exists, it's called SPECint/SPECfp.

Geekbench 5 and 6 both correlated with SPEC scores at nearly 1:1. SPEC is the industry standard for CPU benchmarks. So in a way, Geekbench does what OP suggests which is a general measurement of performance. If you want to see specific areas, Geekbench shows sub scores. Here's research done by Nuvia before they were bought by Qualcomm: https://medium.com/silicon-reimagined/performance-delivered-...

Yes, for single-threaded benchmarks Geekbench 5 and 6 are very well correlated with the SPEC scores and with other single-threaded CPU benchmarks.

On the other hand, whether the Geebench multi-threaded benchmarks are meaningful is questionable. Especially Geekbench 6 has a very poor scaling to many threads, which shows results that are quite uncorrelated with many practical workloads.

Moreover, the multi-threaded benchmarks are too short to reach a steady-state, so they show extremely optimistic throughputs for CPUs with poor cooling, like those from smartphones and laptops. Thus with Geekbench many smartphones and laptops appear to be competitive in multi-threaded performance with desktops or servers, while in real workloads their performance would be pathetic (because as soon as they would overheat, their performance would drop drastically).

Like any benchmarks, Geekbench can be gamed by CPU vendors.

For example, because already the older versions of Geekbench included secure hash computations, the Arm Aarch64 CPUs obtained good scores, because since 2012 they had special instructions and hardware for computing SHA-1 and SHA-256.

The x86-64 CPUs did not have such instructions, so they had bad scores. This prompted Intel to add a SHA ISA extension, but they added it only to the Atom CPUs, because only those competed with Arm CPUs and people compared their Geekbench scores.

For many years, among the Intel CPUs only the small and cheap Atom CPUs had SHA instructions, while their big and expensive desktop/laptop/server CPUs did not have SHA instructions, because at that time nobody compared their Geekbench scores.

This has changed only after the launch of AMD Zen, which included the SHA extension. Then, eventually, after the years during which Intel failed to progress beyond the Skylake derivatives, Intel finally added the SHA extension to all its CPU series, starting with Ice Lake, and since then all the x86-64 CPUs have it.

Re: Geekbench 7

#54

Post by adrian_b » Fri, Jul 24, 2026, 4:09 PM UTC

wtallis wrote: post #3

geerlingguy wrote: post #2

I've run it on a couple Macs, and it looks like one of the issues they're trying to fix is poor multi-core scaling that affected Geekbench 6 on bigger multicore systems (with 32, 64, or 128+ CPU cores). I'll hopefully get time to test on my Ampere Altra Max systems later, to see how scaling works. Geekbench 5 is famously much better than Geekbench 6 for benchmarking these workstation-class CPUs (though many other ben…

Please stop framing the multi core scaling issue as a matter of the benchmark being good or bad. Geekbench 5 scores scale better than Geekbench 6 scores because Geekbench 5's multicore test runs N independent copies of the same workload while Geekbench 6 runs one workload that has to be split across the available cores, with non-zero coordination between threads. The Geekbench 5 approach of pretending Amdahl's Law do…

While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware.

If they use inefficient thread synchronization methods, like those offered by the C++ compiler, or by the pthreads library on Linux, or by some of the older Win32 functions, their results will be much too pessimistic for the CPUs with many cores, creating the wrong impression that they are not much better, or not better at all, than CPUs with less cores.

For Geekbench 6, I have seen enough results where CPUs that are much better for real multi-threaded workloads appeared to be almost the same as clearly inferior CPUs.

For multi-threaded benchmarks, if they are embarassingly parallel the quality of the implementation does not influence the results, but otherwise it is not possible to trust the results without having access not only to the source program of the benchmark, but also to the compilers used by it.

I have seen a lot of benchmarks of locking methods used for thread synchronization, where the results could not be interpreted correctly without seeing the assembly language instructions generated by the compiler for the locking sequences, because a bad assembly generation could matter more than the high-level algorithms whom the benchmark was supposed to compare.

Re: Geekbench 7

#55

Post by wtallis » Fri, Jul 24, 2026, 4:36 PM UTC

BoingBoomTschak wrote: post #49

aurareturn wrote: post #34

Earlier quoted context omitted.

Geekbench 5 and 6 both correlated with SPEC scores at nearly 1:1. SPEC is the industry standard for CPU benchmarks. So in a way, Geekbench does what OP suggests which is a general measurement of performance. If you want to see specific areas, Geekbench shows sub scores. Here's research done by Nuvia before they were bought by Qualcomm: https://medium.com/silicon-reimagined/performance-delivered-...

What compiler is used by GB? Why can't I change it? Imagine an ICC-like scandal. Trusting binary-only benchmarks to compare hardware simply is foolish.

I don't think you've put forth a coherent argument here.

SPEC CPU is distributed in source form, to be compiled by the end user. There are restrictions on what kind of compiler options and other games you can play when making an official submission to SPEC, which Intel (and others) get around by publishing "estimated" SPEC scores and using those for marketing claims. In practice, the amount of bullshit in Intel's claimed SPEC scores is constrained only by what Intel's legal department is willing to risk getting sued over.

Geekbench is distributed in binary-only form with all binaries for all platforms originating from the author of Geekbench. All the major chip designers pay to see the source code and participate in the development, but the final decisions about what code goes in and how it's compiled are made by the author of Geekbench, not by the chip vendors. They just get to lobby, and AMD has every opportunity to call out Intel and Geekbench should the compiler options for the x86 builds be unfair.

Intel has a long history of cheating on SPEC, but cheating on Geekbench is more difficult because of the necessity of runtime binary patching and they didn't publicly try until this year, with limited success and lots of negative press: https://www.geekbench.com/blog/2026/03/geekbench-6-and-intel...

Re: Geekbench 7

#56

Post by adrian_b » Fri, Jul 24, 2026, 4:43 PM UTC

osti wrote: post #5

wtallis wrote: post #3

Earlier quoted context omitted.

Please stop framing the multi core scaling issue as a matter of the benchmark being good or bad. Geekbench 5 scores scale better than Geekbench 6 scores because Geekbench 5's multicore test runs N independent copies of the same workload while Geekbench 6 runs one workload that has to be split across the available cores, with non-zero coordination between threads. The Geekbench 5 approach of pretending Amdahl's Law do…

I agree. For me personally I mostly only care about single thread geekbench variant, I believe it's an excellent proxy for general performance of a CPU. Multi thread geekbench (or other benchmarks) for most purposes and for most people, it's kinda useless. You just need to know that you have a quite a few cores on your computer and that it will have enough concurrency for what you do. But single thread will make what…

There are plenty of things for which the results of single-threaded benchmarks are completely irrelevant, like the compilation of a big software project.

There are also things that are well-correlated with the single-threaded Geekbench result, like how responsive will appear an Internet browser, but for many professional uses the multi-threaded performance is much more important than the single-threaded performance.

For many CPUs, and depending on the computers in which they are installed, the single-threaded and multi-threaded results are completely uncorrelated, because during the multi-threaded benchmark the clock frequency in some computer may drop even 4 times (there are Intel CPUs with a so big ratio between the maximum turbo frequency and the base frequency), while in another computer it might drop only by 20%.

Re: Geekbench 7

#57

Post by wtallis » Fri, Jul 24, 2026, 4:43 PM UTC

adrian_b wrote: post #54

wtallis wrote: post #3

Earlier quoted context omitted.

Please stop framing the multi core scaling issue as a matter of the benchmark being good or bad. Geekbench 5 scores scale better than Geekbench 6 scores because Geekbench 5's multicore test runs N independent copies of the same workload while Geekbench 6 runs one workload that has to be split across the available cores, with non-zero coordination between threads. The Geekbench 5 approach of pretending Amdahl's Law do…

While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware. If they use inefficient thread synchronization methods, like those offered by the C++ compiler, or by the pthreads li…

> While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware.

You're contradicting yourself. Do you want realistic scaling, or the kind of highly-tuned hand-optimized scaling that almost no real-world applications (especially in the consumer space) ever get?

In both of your comments here, you make very narrow assumptions about what constitutes a "real" workload, and you're excluding ordinary everyday consumer PC software from what you consider "real". Highly optimized software running on large servers aren't the only "real" workloads, and they're not the kind of "real" workload that Geekbench is trying to represent. For the kind of hardware and use cases that Geekbench actually targets, using the platform/compiler default synchronization primitives and doing work in short bursts interspersed with significant idle time is reasonable and realistic.

Re: Geekbench 7

#58

Post by adrian_b » Fri, Jul 24, 2026, 5:05 PM UTC

wtallis wrote: post #57

adrian_b wrote: post #54

Earlier quoted context omitted.

While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware. If they use inefficient thread synchronization methods, like those offered by the C++ compiler, or by the pthreads li…

> While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware. You're contradicting yourself. Do you want realistic scaling, or the kind of highly-tuned hand-optimized scaling th…

A very frequent real-world workload is the compilation of a software project, which scales almost perfectly with the number of cores.

For the other multi-threaded tasks, like running certain CAD/EDA applications, I use well-optimized programs, either by others or by myself.

What I do is typical for a professional use of a computer.

The Geekbench multi-threaded results do not provide any useful information about how a computer will behave for such applications.

I agree that the Geekbench multi-threaded results may be representative for how a smartphone will behave if it will have small bursts of multi-threaded activity caused by casually written applications, interspersed between single-threaded execution.

This would be fine, if it would be more clearly specified when the Geekbench benchmark is distributed.

I know that I should trust only the single-threaded Geekbench results and for multi-threaded I should search other published benchmarks.

But others appear to not be aware of this and I have seen frequently erroneous claims on the Internet that some laptop or even some smartphone would match or exceed the performance of a desktop or of a bigger laptop, even one with a CPU with more cores, based on the published Geekbench multi-threaded results, while in reality that desktop or big laptop has a much greater throughput.

Re: Geekbench 7

#59

Post by adrian_b » Fri, Jul 24, 2026, 5:18 PM UTC

aurareturn wrote: post #42

jchw wrote: post #40

Earlier quoted context omitted.

I dunno why people are downvoting at all. I don't get what nerve this is striking so hard. The real truth is that if consumers don't benefit from knowing how well multicore workloads scale, then they can just look only at the single-core score. Skewing it on purpose by including things that genuinely only use ~1 core doesn't seem to serve to add value but only obfuscate the truth about how well a CPU is able to scale…

Given that Geekbench is a consumer workload benchmark, it makes sense to factor in Amdahl's Law. Period. Now the question is whether having a 3rd CPU score for embarrassingly parallel work makes sense for Geekbench. It probably does since many professionals also use Geekbench nowadays.

Amdahl's law is one thing, and an inefficient implementation of a concurrent program is another thing.

We do not know how much of the bad scaling of Geekbench 6 was due to Amdahl's law and how much was caused by an inept implementation.

Moreover, Amdahl's law is really important only for very short computational tasks, i.e. which do not need more than a few seconds or minutes for completion.

The bigger is the job that must be accomplished, the more likely it is that it can be reorganized in a way that tends to be embarassingly parallel, so that Amdahl's law has little importance.

So for jobs as big that they need hours, days or weeks to be completed by a computer, if they are well planned it is frequent to reach scaling factors not much lower than the number of available cores, even if that may be much more difficult to achieve for short jobs.

Re: Geekbench 7

#60

Post by wtallis » Fri, Jul 24, 2026, 6:59 PM UTC

adrian_b wrote: post #58

wtallis wrote: post #57

Earlier quoted context omitted.

> While it would be nice to have a multi-threaded benchmark that demonstrates a realistic scaling towards many threads, I have no reason whatsoever to trust that the Geekbench implementers are capable to optimize the inter-thread communication well enough for reaching the limits imposed by the hardware. You're contradicting yourself. Do you want realistic scaling, or the kind of highly-tuned hand-optimized scaling th…

A very frequent real-world workload is the compilation of a software project, which scales almost perfectly with the number of cores. For the other multi-threaded tasks, like running certain CAD/EDA applications, I use well-optimized programs, either by others or by myself. What I do is typical for a professional use of a computer. The Geekbench multi-threaded results do not provide any useful information about how a…

> A very frequent real-world workload is the compilation of a software project, which scales almost perfectly with the number of cores.

Geekbench has that as a subtest.

> For the other multi-threaded tasks, like running certain CAD/EDA applications, I use well-optimized programs, either by others or by myself.

Those seem pretty clearly out of scope. You want a workstation benchmark, not a consumer benchmark.

> This would be fine, if it would be more clearly specified when the Geekbench benchmark is distributed.

The descriptions of what Geekbench is are adequate. You're asking for Geekbench to exhaustively list what it isn't to stop you from imagining it to be a one-size-fits-all benchmark, which couldn't possibly exist.

> But others appear to not be aware of this and I have seen frequently erroneous claims on the Internet that some laptop or even some smartphone would match or exceed the performance of a desktop or of a bigger laptop, even one with a CPU with more cores, based on the published Geekbench multi-threaded results, while in reality that desktop or big laptop has a much greater throughput.

Again you seem to be unable to stop asserting that workstation or server use cases are the only ones that are real.