iPhone 13 A15 benchmarks reveal 21% CPU speed gain over iPhone 12

Posted:
in iPhone edited September 17
More data from Apple's unreleased iPhone 13 lineup has made its way to the Geekbench Browser, offering a sneak peek at the performance users can expect from the next-generation handset and, by extension, the new iPad mini.

A15


According to CPU statistics uploaded by Geekbench users, iPhone 13's average single-core score is 1730, a roughly 10% increase from iPhone 12's score of 1575. Multi-core scores average out to 4621, or nearly 21% higher than the 3832 put in by iPhone 12.

If accurate, the figures represent a decent bump in computing performance for the entire iPhone 13 line. While Apple includes an additional GPU core and more memory in the A15 Bionic deployed in iPhone 13 Pro and iPhone 13 Pro Max models, all iPhone 13 models share a common six-core CPU design with two performance cores and four efficiency cores.

It should be noted that only six devices with designations ranging from "iPhone14,2," "iPhone14,3" and "iPhone14,5" have run the benchmarking suite and uploaded corresponding data as of this writing, and the early information cannot be corroborated as legitimate. That said, the results are consistent and the data sheds light on hardware specifications Apple has yet to detail.

As noted by MacRumors, which spotted the Geekbench results earlier today, the iPhone 13's Metal score of 10608 is much lower than corresponding 14216 score put in by an iPhone 13 Pro, again a result of one less GPU core. Still, the A15 in iPhone 13 and, presumably, iPhone 13 mini puts in a Metal score that is about 15% higher than that of last year's A14 Bionic.

Apple failed to detail A15's CPU performance in its "California Streaming" event on Tuesday, saying only that the chip is 50% faster than the competition. The ambiguity led some to believe that the decision not to include direct comparisons was intentional.

Read on AppleInsider
«1

Comments

  • Reply 1 of 33
    entropysentropys Posts: 3,198member
    The pro has a fifth GPU core though.
    williamlondonwatto_cobra
  • Reply 2 of 33
    KITAKITA Posts: 382member
    Comparison with more recent results running the same version of Geekbench and as close as possible for iOS version.

    iPhone 12 Pro Max - iOS 14.71 - Geekbench 5.4.1 - Sept. 15th 2021 (https://browser.geekbench.com/v5/cpu/9853975)

    A14 @ 2.99 GHz
    Singe Core Score: 1605
    Multi Core Score: 4294

    iPhone 14,2 - iOS 15 - Geekbench 5.4.1 - Sept. 15th 2021 (https://browser.geekbench.com/v5/cpu/9851461)

    A15 @ 3.22 GHz
    Singe Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)

    muthuk_vanalingamnadriel
  • Reply 3 of 33
    KITA said:
    "Single Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)"

    A14 @ 2.99 GHz
    A15 @ 3.22 GHz
    = +7.33%

    M1 @ 3.2 GHz Single Core: 1721 (iPad Pro https://browser.geekbench.com/v5/cpu/9837998)
    +0.4%

    M1 @ 3.2 GHz
    A15 @ 3.22 GHz
    = 0.6%

    Conclusion, the difference mainly boils down to an increase in frequency and presumably the bigger cache in multi core score.


    edited September 16 canukstormelijahgrinosaurwilliamlondonwonkothesane
  • Reply 4 of 33
    Apple releasing a 10-25% speed increase every year will allow them to milk the A series for a long time. Smart business.
    jas99
  • Reply 5 of 33
    KITA said:
    Comparison with more recent results running the same version of Geekbench and as close as possible for iOS version.

    iPhone 12 Pro Max - iOS 14.71 - Geekbench 5.4.1 - Sept. 15th 2021 (https://browser.geekbench.com/v5/cpu/9853975)

    A14 @ 2.99 GHz
    Singe Core Score: 1605
    Multi Core Score: 4294

    iPhone 14,2 - iOS 15 - Geekbench 5.4.1 - Sept. 15th 2021 (https://browser.geekbench.com/v5/cpu/9851461)

    A15 @ 3.22 GHz
    Singe Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)

    not going to argue about that iPhone 12 score (it should be more correct than averages), but if you are choosing a particular iPhone 12 maximum performance, you should also use the iPhone 13 maximum available score. That would mean comparing with:
    Singe Core Score: 1734 (+ 8% over A14)
    Multi Core Score: 4818 (+ 12.2% over A14)
    tmaypatchythepiratemagman1979
  • Reply 6 of 33
    appleinsider said: 
    Apple failed to detail A15's CPU performance in its "California Streaming" event on Tuesday, saying only that the chip is 50% faster than the competition. The ambiguity led some to believe that the decision not to include direct comparisons 
    Translation: Because we simply don't want to admit that we have spread the nonsense of a notorious impostor for the sake of clicks, we continue to claim against the facts that Apple presented the performance of its latest chip differently at this year's keynote than it did the year before. Even though a quick look at the recording of last year's keynote proves the opposite of our claim, we couldn't care less. Because in no case do we admit mistakes. Period.
    Oh Appleinsider, what happened to you?  :'(
    tmaythtmagman1979williamlondonspock1234watto_cobra
  • Reply 7 of 33
    It’s funny that people complain that apple is stooping to compare themselves to the lowly competition ;-)

    I understand the complaint, of course — it’s legit to point out that the A15 is an anemic upgrade over the A14. But it’s still funny that the competition is so far behind that it’s considered a bad sign that apple is reduced to comparing themselves to it. 
    jas99patchythepirategenovellemagman1979watto_cobra
  • Reply 8 of 33
    michelb76 said:
    Apple releasing a 10-25% speed increase every year will allow them to milk the A series for a long time. Smart business.
    As long as they pair it with new abilities. We don’t need faster SoC’s if it doesn’t enable us to do new things, or do existing things considerably better.

    radarthekat
  • Reply 9 of 33
    michelb76 said:
    Apple releasing a 10-25% speed increase every year will allow them to milk the A series for a long time. Smart business.
    As long as they pair it with new abilities. We don’t need faster SoC’s if it doesn’t enable us to do new things, or do existing things considerably better.

    Hence the significantly expanded Neural - seems like Apple will continue to offer additional AI-driven experiences.

    However worth noting is that there has been significant press stating that the A15 would only be a mild bump, and that Apple has "hit a performance wall" - This is interesting because it's not just wrong, but appears to be a wide effort at astroturfing. It's an especially bold attempt because it infers that apple M-series would be similarly hobbled. (I dare say Apple wouldn't switch to their own silicone without a realistic performance roadmap.)
    tmaybageljoeymagman1979williamlondonfastasleepradarthekatwatto_cobra
  • Reply 10 of 33
    KITA said:
    "Single Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)"

    A14 @ 2.99 GHz
    A15 @ 3.22 GHz
    = +7.33%

    M1 @ 3.2 GHz Single Core: 1721 (iPad Pro https://browser.geekbench.com/v5/cpu/9837998)
    +0.4%

    M1 @ 3.2 GHz
    A15 @ 3.22 GHz
    = 0.6%

    Conclusion, the difference mainly boils down to an increase in frequency and presumably the bigger cache in multi core score.


    Insider info leaked long time ago said that A15 design will be focused on power efficiency. It looks like that . They made it less hungry, probably cooler, better manufacturing process then allowed them to hick frequency and so the performance.  When we see proclaimed battery life improvements we can say that A15 give more juice for the same power. We will see what Anand tech will find up.
    d_2williamlondonwatto_cobra
  • Reply 11 of 33
    JWSCJWSC Posts: 1,049member
    Smells of classic market manipulation, a dump then pump of the stock price all within 24 hours.  Would love to see reporters follow the money on this.
    genovellewilliamlondonmattinozwatto_cobra
  • Reply 12 of 33
    dewmedewme Posts: 3,946member
    michelb76 said:
    Apple releasing a 10-25% speed increase every year will allow them to milk the A series for a long time. Smart business.

    Would you complain if you "only" received a 10% salary increase every year?
    MisterKitStrangeDaysradarthekatwatto_cobra
  • Reply 13 of 33
    How much performance do people want out of a handheld computer? How much performance is actually needed? Unless Apple significantly increases the number of megapixels in their camera I’d argue you don’t need any more performance than what the 13 Pro offers. The challenge Apple has is they need to continuously offer “compelling” reasons to justify the premium price of the iPhone. Android has a superior market share. But Apple has an incredible share of the market measured in dollars and average price per device sold. The performance numbers are more important with the M series of laptop and desktop CPUs.
    watto_cobra
  • Reply 14 of 33
    lkrupplkrupp Posts: 9,630member
    So just yesterday we were presented with a ‘report’ that the A15 was not any better than the A14 because of the ‘brain drain’ of Apple engineers leaving the company. Someone please tell me which ‘report’ we should believe. 
    tmaymknelsonMisterKitradarthekatwatto_cobra
  • Reply 15 of 33
    frantisek said:
    KITA said:
    "Single Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)"

    A14 @ 2.99 GHz
    A15 @ 3.22 GHz
    = +7.33%

    M1 @ 3.2 GHz Single Core: 1721 (iPad Pro https://browser.geekbench.com/v5/cpu/9837998)
    +0.4%

    M1 @ 3.2 GHz
    A15 @ 3.22 GHz
    = 0.6%

    Conclusion, the difference mainly boils down to an increase in frequency and presumably the bigger cache in multi core score.


    Insider info leaked long time ago said that A15 design will be focused on power efficiency. It looks like that . They made it less hungry, probably cooler, better manufacturing process then allowed them to hick frequency and so the performance.  When we see proclaimed battery life improvements we can say that A15 give more juice for the same power. We will see what Anand tech will find up.
    It is very likely made on TSMC's newer and improved N5P node, if so the better thermal efficiency is likely free lunch. Meaning Apple didn't put much/any work into it, but is profitting from TSMC's node progress.
    williamlondon
  • Reply 16 of 33
    JWSCJWSC Posts: 1,049member
    entropys said:
    The pro has a fifth GPU core though.
    I am going to assume that this is the same piece of silicon used in the regular iPhone 13 and that the fifth GPU core in the Pro is activated through a firmware modification.

    Anyone know differently?
    williamlondonwatto_cobra
  • Reply 17 of 33
    MacProMacPro Posts: 19,426member
    blastdoor said:
    It’s funny that people complain that apple is stooping to compare themselves to the lowly competition ;-)

    I understand the complaint, of course — it’s legit to point out that the A15 is an anemic upgrade over the A14. But it’s still funny that the competition is so far behind that it’s considered a bad sign that apple is reduced to comparing themselves to it. 
    I was struck by the same thing throughout the presentations.  As far as I can remember all comparisons of any kind were to existing Apple products. Quite amazing really.
    watto_cobra
  • Reply 18 of 33
    thttht Posts: 4,130member
    JWSC said:
    entropys said:
    The pro has a fifth GPU core though.
    I am going to assume that this is the same piece of silicon used in the regular iPhone 13 and that the fifth GPU core in the Pro is activated through a firmware modification.

    Anyone know differently?
    They are the same chips, but chip manufacturing is an imperfect process. The GPU is the largest component on the chip and is therefore subject to the most manufacturing defects. So, there will be chips with 3, 4, 5 working GPU cores. Instead of throwing away chips, they can sell them as chips with 5 GPU cores, 4 GPU cores, etc. This is what is meant by binning. Chips can also be binned for frequency, CPU cores, cache, voltage, etc. 

    Nobody will be able to activate any unused part of a chip. They are typically fused off. IOW, the circuits to those cores and components are cut at the chip level. If a user gets a perfect chip that had components fused off, at minimum, they would have take it out of the package and solder it in at the metal layers of the chip with micrometer sized tools. That's assuming it's a perfect chip. If it is not, and it is apt to be, the core is either not functional or operates outside qualification requirements, like does not run at the right clocks, uses too much power, delivers the wrong result too often, etc.
    muthuk_vanalingamfastasleepwatto_cobra
  • Reply 19 of 33
    And yet look at the speed tests done with Android phones side by side.  All that power is not being utilized in the least bit.  Apple I’m very disappointed in you.  I’m thinking about selling my iPhone 12 mini and going back to my first generation iPhone SE.  Software runs at about the same speed and that’s five generations older.  

    Apple, please optimize your software as my newest phone feels and acts just as slow as my older phone.  Shame on you 😂
  • Reply 20 of 33
    frantisek said:
    KITA said:
    "Single Core Score: 1728 (+7.6% over A14)
    Multi Core Score: 4695 (+9.3% over A14)"

    A14 @ 2.99 GHz
    A15 @ 3.22 GHz
    = +7.33%

    M1 @ 3.2 GHz Single Core: 1721 (iPad Pro https://browser.geekbench.com/v5/cpu/9837998)
    +0.4%

    M1 @ 3.2 GHz
    A15 @ 3.22 GHz
    = 0.6%

    Conclusion, the difference mainly boils down to an increase in frequency and presumably the bigger cache in multi core score.


    Insider info leaked long time ago said that A15 design will be focused on power efficiency. It looks like that . They made it less hungry, probably cooler, better manufacturing process then allowed them to hick frequency and so the performance.  When we see proclaimed battery life improvements we can say that A15 give more juice for the same power. We will see what Anand tech will find up.
    It is very likely made on TSMC's newer and improved N5P node, if so the better thermal efficiency is likely free lunch. Meaning Apple didn't put much/any work into it, but is profitting from TSMC's node progress.
    TSMC reported that N5P node would only make a 5% increase in performance at isopower, so clearly Apple found anoother place to get some extra performance.
    williamlondonwatto_cobra
Sign In or Register to comment.