CPU Benchmark Performance: Legacy Tests

In order to gather data to compare with older benchmarks, we are still keeping a number of tests under our ‘legacy’ section. This includes all the former major versions of CineBench (R15, R11.5, R10) as well as Geekbench 4 and 5. We won’t be transferring the data over from the old testing into Bench, otherwise, it would be populated with 200 CPUs with only one data point, so it will fill up as we test more CPUs like the others.

We are using DDR5 memory on the Core i9-13900K, the Core i5-13600K, the Ryzen 9 7950X, and Ryzen 5 7600X, as well as Intel's 12th Gen (Alder Lake) processors at the following settings:

  • DDR5-5600B CL46 - Intel 13th Gen
  • DDR5-5200 CL44 - Ryzen 7000
  • DDR5-4800 (B) CL40 - Intel 12th Gen

All other CPUs such as Ryzen 5000 and 3000 were tested at the relevant JEDEC settings as per the processor's individual memory support with DDR4.

Legacy

(6.1) CineBench R10 ST

(6.1b) CineBench R10 MT

(6-2) CineBench R11.5 ST

(6-2b) CineBench R11.5 MT

(6-3) CineBench R15 ST

(6-3b) CineBench R15 MT

(6-4) CineBench R20 ST

(6-4b) CineBench R20 MT

(6-6) Geekbench 5 ST

(6-6b) Geekbench 5 MT

In our older string of tests which are widely outdated, or they don't fit into a specific category, the Core i9-13900K takes the crown in some, competes for neck and neck with the Ryzen 9 7950X in others, or it goes the other way. In the single-threaded tests, there's some variance, but not much in the top end where things look to be very close.

CPU Benchmark Performance: Rendering And Encoding Gaming Performance: iGPU
POST A COMMENT

169 Comments

View All Comments

  • brucethemoose - Thursday, October 20, 2022 - link

    x264 is (more or less) the same thing as the handbrake test... and it kinda is legacy software at this point.

    Personally, I'd like to see a more modern encoding test, like av1an with x265+chunked encoding, or maybe Staxrip with some filters enabled.
    Reply
  • GeoffreyA - Thursday, October 20, 2022 - link

    Yes, some libaom would be fantastic. Reply
  • jakky567 - Monday, October 24, 2022 - link

    I wouldn't say handbrake/x264 are obsolete yet. We should be looking towards the future, but h264 is here to stay as at least a fallback codec. Reply
  • GeoffreyA - Tuesday, October 25, 2022 - link

    It is very much the MP3 of video and here to stay. Plus, its successors have not been indisputably better or have come with tradeoffs. Reply
  • Ashantus - Thursday, October 20, 2022 - link

    Comparing the performance of 7600X vs 13600k i see some overall advantage for the 13600K.
    But, i will defionitly go for the 7600X due one argue.
    Load Consumption of 134 Watt vs 238 Watt at almost same performance is something.
    Regarding the poweer costs in europe of 60 cent per Watt that is quiet some pricing argue at a 5 years lifetime.

    At anandtech:
    this argue should be mentioned in your closing thoughts. 100 Watt more powerconsumption at todays powerprices is a serious issue.
    Reply
  • Yojimbo - Thursday, October 20, 2022 - link

    I don't remember seeing power versus performance numbers. Did I miss them? Reply
  • CiccioB - Thursday, October 20, 2022 - link

    <blockquote>Load Consumption of 134 Watt vs 238 Watt at almost same performance is something.</blockquote>
    This thought is completely wrong. It is called "induction", as you were looking at something and then reported that on something else.
    You see a graph of power consumption for a "unlimited test" (where performance is not measured) and then you think that that measure is valid also for other tests.
    So you just think that for each bench those CPUs consume always those Watts (how can it be?) and that the performance are the same (where did you got that? In almost all benches the 13600K leaves the 7600X in the dust, but not knowing their power consumption for those test you cannot say which is the most efficient).
    Reply
  • Ashantus - Thursday, October 20, 2022 - link

    Just found another test, whereas a powerconsumption at action is recorded.

    At gaming (average out of 12 games tested) is:
    13600k = 88 W. 7600X = 60 W
    13990K = 144 W 7900X = 107W
    Reply
  • Yojimbo - Thursday, October 20, 2022 - link

    that looks more plausible. but it is also mostly useless except in the context of the specific workload. modern cpu performance testing is very complicated and performance versus power should be taken in the specific workload one is interested in, or at the very least an average of workloads of a similar type. Reply
  • Gastec - Sunday, October 23, 2022 - link

    Specific workload such as : 13990K produces 100 fps @ 144 W, while 7600X produces 100 fps @ 60 W? Reply

Log in

Don't have an account? Sign up now