1. This site uses cookies. By continuing to use this site, you are agreeing to our use of cookies. Learn More.

Other Geekbench scores

Discussion in 'Hardware' started by Bloody_Pete, 14 Dec 2011.

  1. adidan

    adidan Guesswork is still work

    Joined:
    25 Mar 2009
    Posts:
    19,722
    Likes Received:
    5,485
    Do the Geekbench versions vary drastically? Not sure how to compare with that chart unless that version is still about.

    Was surprised how well the SC was on my stock 3770. Seems to be up there with the 1700x on that front at least.

    Edit: Maybe I should unbox the 930 I bought off you eons ago and get this up and running on the x58 system :)

    Oh hang on, can't, the backup psu is currently in my system after the other one died. :confused:
     
    Last edited: 14 Feb 2018
  2. Vault-Tec

    Vault-Tec Green Plastic Watering Can

    Joined:
    30 Aug 2015
    Posts:
    14,851
    Likes Received:
    3,654
    It's the most rubbish benchmark I've ever had the misfortune to run. It can't even keep my CPU fully clocked. The results also differ wildly. Not one to be taken seriously, IMO.
     
  3. Guest-44432

    Guest-44432 Guest

    Damn, I forgot about that CPU... :)

    I'm not sure how it will compare, so maybe it all needs to be updated. :)
     
  4. MLyons

    MLyons 70% Dev, 30% Doge. DevDoge. Software Dev @ Corsair Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    3 Mar 2017
    Posts:
    4,174
    Likes Received:
    2,732
    Just wait a few days until I get to play with some of the hardware we have downstairs and I'll fix that ;)
     
    Guest-44432 likes this.
  5. Guest-44432

    Guest-44432 Guest

    No LN2 or Phase changer as that's cheating... :D
     
  6. Guest-44432

    Guest-44432 Guest

    That's because you need to close down any background programs, and set power to high performance. :)
     
  7. MLyons

    MLyons 70% Dev, 30% Doge. DevDoge. Software Dev @ Corsair Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    3 Mar 2017
    Posts:
    4,174
    Likes Received:
    2,732
    lets just say threads might not be the only thing I'll be ripping and the scores may be EPYC
     
    The_Crapman likes this.
  8. Guest-44432

    Guest-44432 Guest

    Oh, only 64 cores... :D

    High speed memory takes advantage of this benchmark too. ;)
     
  9. MLyons

    MLyons 70% Dev, 30% Doge. DevDoge. Software Dev @ Corsair Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    3 Mar 2017
    Posts:
    4,174
    Likes Received:
    2,732
    I'll see if they let me use some of the good stuff we have.
     
  10. Guest-44432

    Guest-44432 Guest

    We want pic's and screenshots of this beast! - So then we can all sit back at our screens with :jawdrop: lol.
     
  11. MLyons

    MLyons 70% Dev, 30% Doge. DevDoge. Software Dev @ Corsair Lover of bit-tech Administrator Super Moderator Moderator

    Joined:
    3 Mar 2017
    Posts:
    4,174
    Likes Received:
    2,732
    Which version of geekbench should i use?
     
  12. Vault-Tec

    Vault-Tec Green Plastic Watering Can

    Joined:
    30 Aug 2015
    Posts:
    14,851
    Likes Received:
    3,654
    If I have to do that it's not worth bothering with. Seriously, the benchmark is crap. I scored more with the same CPU on OSX and the results from heavily threaded AMD CPUs are laughable.

    If you want a balls out benchmark run CB 15.
     
  13. Guest-44432

    Guest-44432 Guest

    Geekbench 2 with 32bit and 64bit was used back then, so maybe run that those and Geekbench 4 for comparison.

    Well, this thread was designed for people overclocking the crap out of their hardware, so if you was an enthusiast, then closing third party programs, and having your PC ready for benching is not really any hassle... :)
     
  14. adidan

    adidan Guesswork is still work

    Joined:
    25 Mar 2009
    Posts:
    19,722
    Likes Received:
    5,485
    Guess it depends on how long it's been since you last broke something :);)
     
  15. Vault-Tec

    Vault-Tec Green Plastic Watering Can

    Joined:
    30 Aug 2015
    Posts:
    14,851
    Likes Received:
    3,654
    Does a 14/28 core Broadwell E and Titan XP all under water make me an enthusiast?

    Not being funny but I think you just don't understand. Let me put it into something you may. This benchmark is about as bent (toward Intel) as a nine bob note. There, does that help?
     
  16. Guest-44432

    Guest-44432 Guest

    Not sure what your problem is dude?... This thread back in the day was all about overclocking... If you have such a CPU, then bench it, and post the screenshots. :)

    But stuff like this makes you an enthusiast. no. 2 (The good old days...) :D

    [​IMG]
     
  17. Vault-Tec

    Vault-Tec Green Plastic Watering Can

    Joined:
    30 Aug 2015
    Posts:
    14,851
    Likes Received:
    3,654
    I am aware of all of that. I have no idea why you think I am not. There are much, much better benchmarks for a CPU than Geekbench. Like I said, Cinebench is about the most accurate there is for grading/positioning a CPU.

    Why not start a Firestrike thread, or a Timespy thread? or a Cinebench thread?

    But seriously, with four PCs all under water you really don't need to explain to me what an enthusiast is.
     
  18. Guest-44432

    Guest-44432 Guest

    Because you said this:
    I replied with this:
    So any benchmark you run will vary, unless you do those simple things to maximize the results.

    Many of us had this issue with Heaven benchmark, that the benchmark would record results before your GPU and PCI-E lanes got up to max speed, leaving you with a bad minimum fps which effected your overall score. The way around it was to have something running to get the clocks up, and exit it as the benchmark began, given you true minimum frame rate results. :)
     
  19. Vault-Tec

    Vault-Tec Green Plastic Watering Can

    Joined:
    30 Aug 2015
    Posts:
    14,851
    Likes Received:
    3,654
    https://en.wikipedia.org/wiki/Geekbench

    Linus Torvalds, who is the creator and principal developer of the Linux kernel, criticized Geekbench versions 3 and earlier for showing partiality for ARM64 devices and being a bad performance measure of x86-based systems, he called GB as bad a benchmark as Dhrystone, which he and others have ridiculed for years. [3] When version 4.0 of Geekbench was released his comment was, "Looks much better."

    As I keep trying to explain to you Geekbench is an awful benchmark. It is also very easy to cheat. Maybe you have been out of the loop for a while but I would not use it to compare hardware at any level. As I tried to explain to you it is notoriously unreliable and not worth bothering with. So basically all benchmarks ran in this thread on version 3 or before (And I remember running it on my PC and thinking da fuq?) are literally not comparable to anything.

    If you want to compare CPU performance use CB15. It is a true indication of what a CPU can do, both stock and overclocked and the results are comparable across multiple vendors instead of just brown nosing Intel CPUs. That is why, after Ryzen released, Intel started producing Geekbench scores for their CPUs. In the past they would have bent the rules themselves, but they so heavily favour Intel CPUs without Intel getting their hands dirty (and sued, like they were in the past) that they don't need to worry about that.
     
  20. adidan

    adidan Guesswork is still work

    Joined:
    25 Mar 2009
    Posts:
    19,722
    Likes Received:
    5,485
    Well this little bit of fun has gone sideways.

    Why don't we just start different threads for different benches, people can just join in if they wish or ignore them.
     
    MLyons and Guest-44432 like this.

Share This Page