Comments Locked

110 Comments

Back to Article

  • mavere - Wednesday, September 19, 2012 - link

    With iOS6, the 4S should score in the ~1800 range.

    I was going to request adding iOS6 4S results, but I realize you might not have a 4S on hand or even a dev account.
  • agent2099 - Wednesday, September 19, 2012 - link

    I thought full version software updates to iPhones usually results in them performing worse, has this changed?
  • lowlymarine - Wednesday, September 19, 2012 - link

    Overall yes, but usually the update to the underlying JS engine will improve the Sunspider score. For example, on my 3G after iOS 4 landed, my Sunspider score nearly halved, while absolutely everything else about the phone become an intolerably slow pile of bugs and failure.

    Which really just serves to highlight how totally useless Sunspider is as a benchmark.
  • ltcommanderdata - Wednesday, September 19, 2012 - link

    Usually it's decreased general responsiveness that's the complaint. Safari is improved with every iOS version so the browser usually performs better regardless. And the major performance concern with iOS updates was really focused on the iPhone 3G and iOS 4.0. I believe Anandtech found the iPhone 3GS survived the transition from iOS 4 to iOS 5 without performance problems so hopefully the transition to iOS 6 goes just as smoothly.
  • AlexTheUkrainian - Wednesday, September 19, 2012 - link

    You were close! I am getting 1743 on 4S with iOS 6.
  • macs - Wednesday, September 19, 2012 - link

    And I get 1440 with the new iPad on iOS 6
  • anexanhume - Wednesday, September 19, 2012 - link

    The massive memory bandwidth on the iPad 3 helps.
  • danielfranklin - Wednesday, September 19, 2012 - link

    If I remember right, Anand's testing proved the CPUs in the A5x didn't have access to the bandwidth, mem scores were unchanged, all the bandwidth seems to go via the GPU.
  • Dissmeister - Tuesday, September 25, 2012 - link

    1444.6 on Droid RAZR XT910 running cm10 Jellybean. Definitely impressed, lol.
  • SantoBr - Tuesday, January 29, 2013 - link

    1286.9ms on chrome beta with webGL enable
  • Aikouka - Wednesday, September 19, 2012 - link

    iOS 6 releases today, so he won't need a dev account. :)
  • vdx660 - Wednesday, September 19, 2012 - link

    Apple's A6 is supposed to win and by a wide margin (not 28% faster) because the test is comparing an Apple A6 (Dual Core) vs an Intel Medfield (Single Core). For fair results this test should be run again when Intel Clover Trail (Dual Core) comes out.
  • Aenean144 - Wednesday, September 19, 2012 - link

    Sunspider is vastly single threaded.
  • Formul - Wednesday, September 19, 2012 - link

    yes because the sunspider is so well multithreaded and they are both on the same frequency ...
  • humancyborg - Wednesday, September 19, 2012 - link

    Wait, for fair results we need to wait for the competitors to release their newest chipset?

    How about we just compare devices that are available today and leave the speculation for less intelligent folk.
  • vdx660 - Sunday, September 23, 2012 - link

    I just run Sunspider and tests show that on modern browsers that I tested IE9,IE10, Firefox 15, Chrome 21, it make use of all available processor cores. Running Sunspider on a dual core A6 is supposed to be faster than running on a single core Medfield. You can also see from the Test results that a Samsung Galaxy S3 International (Quad Core) is faster than the Galaxy S3 counterparts that are dual core.
  • thebeastie - Wednesday, September 19, 2012 - link

    Nice!, I guess with performance like that Apple has some good standing room for its high mark up price.
  • KoolAidMan1 - Wednesday, September 19, 2012 - link

    What high price? The iPhone costs about as much as a Galaxy S3 AT&T version, the same one with double the Sunspider score as the iPhone 5
  • bill4 - Wednesday, September 19, 2012 - link

    1442 is double 914 now? I knew Obama was ruining the schools but this is crazy.

    Anyways I'm happy with the GS3 score there. It's 3rd place and not too much worse than latest and greatest iPhone 5. Not bad for an "old" phone. And yes, in the smartphone world a phone that came out (in USA, even earlier elsewhere) in late June is kind of old lol. Plus I understand these benches often depend on software optimization and not raw hardware strength anyway.

    And for that matter my GS3 still contains 2GB RAM vs the iPhone 5's 1GB, etc. Not saying the GS3 is stronger than the 5, just that it's no pushover.

    Anyways, loooooooooooove my GS3 lol. It usually takes Samsung a while, as a guy who for the most part hated my Galaxy S 1/Captivate, but they tend to get it right eventually. Believe me I experience zero iPhone 5 (well of course not with that tiny screen and boring oldass fisher price looking operating system, lol) or any other Android phone envy.

    I do always give Apple credit for one and only one thing though, they do pack the chipset power in their devices, even above and beyond the call of duty. And they dont have too, as Apple tards will obviously buy anything no matter how crappy it is as long as the brand is stamped on the side.
  • serversurfer - Wednesday, September 19, 2012 - link

    1825 is roughly double 914, and 1825 is what the AT&T version of the GS3 scored.
  • bill4 - Wednesday, September 19, 2012 - link

    It's actually less than double if you want to be exact. 2X 914.7=1829.4

    LOL.

    But yeah, I was looking at international version for some reason.

    Anyways yeah A6 is a good chipset. But this always happens, iPhone jumps ahead on release, Android phones trump it in a matter of months or less, repeat.
  • doobydoo - Wednesday, September 19, 2012 - link

    Do you mean like how no smartphone in America has matched the GPU of the 1 year old iPhone 4S?

    Or how the iPhone 5 has just doubled that performance?

    (According to Apple)
  • darkcrayon - Wednesday, September 19, 2012 - link

    I think the international Galaxy S III finally surpassed the GPU in the iPhone 4S, but it's not even going to be close to what's in the 5. Apple doesn't seem to mess around when it comes to GPU. What's different this time is that the CPU is meets or exceeds what any competitor is currently offering.
  • doobydoo - Wednesday, September 19, 2012 - link

    Yeah, that's why I said 'in America'.

    And I agree, the iPhone 5 will take the lead again.
  • yogi6807 - Friday, September 21, 2012 - link

    found this gl benchmarks put it in the wrong spot earlier

    "A little bit of casual benchmarking using the GLBenchmark Egypt High test yielded a score of 6766, while the iPhone 4S got 1158. The Offscreen test was closer: 16681 vs 8346. This looks like a lot more than day to day usage bears out, but it suggests that there's headroom for the iPhone 5 to do some pretty impressive stuff."

    http://www.stuff.tv/review/apple-iphone-5
  • EnzoFX - Wednesday, September 19, 2012 - link

    Pretty biased. Some of the so called cons of the iPhone for you, is what makes it a best seller for everyone else. It's not for you, fine, get over it. No need to measure your GS3 decision by that of an iPhone lol.
  • doobydoo - Wednesday, September 19, 2012 - link

    'Not bad for an "old" phone'

    The SG3 is just over 3 months old.
  • lowlymarine - Wednesday, September 19, 2012 - link

    That Nexus S score is about twice what it should be, likely stemming from the fact that it was measured under Gingerbread stock browser and never updated. Running ICS/JB and using Chrome, the Nexus S gets a score nearly twice as fast - I get ~3200ms on Jelly Bean with Chrome my original Galaxy S, running the same 1GHz S5PC110/Hummingbird/Exynos 3110/whatever it's officially called this week.

    If you aren't going to update it - which is understandable, perhaps you don't still have any first-gen Galaxy S hardware available - then you should probably just remove it.
  • serversurfer - Wednesday, September 19, 2012 - link

    Devices are tested and scored as shipped, for multiple reasons. First, the stock configuration provides a solid performance baseline for the device. People who are already familiar with the device will likely be familiar with the performance of the stock configuration, allowing them to assign meaning to the device's score. People who are unfamiliar with the device can look at its score and compare it to devices they are familiar with and get an idea of what kind of performance they can expect OOTB.

    If you do allow tweaking, where do you draw the line? If you're allowed to install Jelly Bean on your phone, can I install an OS that only runs SunSpider on mine? What about overclocking? If my phone completes the test before its circuits fuse, my score still counts, right?
  • lowlymarine - Wednesday, September 19, 2012 - link

    The iPhone 4's score has clearly been updated for new versions of iOS, as at launch http://www.anandtech.com/show/3794/the-iphone-4-re...">it scored over 10,000. Why shouldn't Android devices receive the same treatment? Jelly Bean for the Nexus S isn't a "tweak" or "hack," it's an official stable release by Google.
  • lowlymarine - Wednesday, September 19, 2012 - link

    So that got mangled somehow. Here's the link again: http://www.anandtech.com/show/3794/the-iphone-4-re...

    My kingdom for an edit button.
  • bill4 - Wednesday, September 19, 2012 - link

    "The iPhone 4's score has clearly been updated for new versions of iOS, as at launch http://www.anandtech.com/show/3794/the-iphone-4-re... scored over 10,000. Why shouldn't Android devices receive the same treatment? "

    The media/Anandtech's incredible pro Apple bias shows through LOL.

    Kind of reminds me of all those sites that bench AMD cards with old driver but use newest for Nvidia.
  • EnzoFX - Wednesday, September 19, 2012 - link

    No, you're just out of touch. Grow up.
  • Zink - Wednesday, September 19, 2012 - link

    The iPhone 4 is still widely sold and ships with iOS 6 installed. Most people with the phone will update to iOS 6 as well. The real number most people will see on their phone is is actually faster than shown here, about 2950.
  • serversurfer - Wednesday, September 19, 2012 - link

    That's actually a pretty good point. Not only are Apple good about pushing out updates to existing users, they're also good about putting the current OS on the device whenever they box one up.

    Do Android manufacturers do the same? If v3.4 is current when the device is ready for market, in six months will they ship them instead with v4.0? Or even v3.6 or v3.5.2? Or do you need to update immediately upon opening the box?
  • ssj4Gogeta - Thursday, September 20, 2012 - link

    I know that at least Samsung do ship with the latest version for their phones. Galaxy S2 (international) received ICS updates and the S2's in the market now come preinstalled with ICS.
  • tipoo - Wednesday, September 19, 2012 - link

    The iPhone results are on the latest final OS they can run, and sometimes they go back and update Android scores for the bigger releases. It's not high priority since it's an old phone now, but I'd like them to update the NS to ICS too, since that's an official release for it.
  • serversurfer - Wednesday, September 19, 2012 - link

    Also, by leaving the stock score on the chart, it allows you to come back years later and say, "Nice, JB cut my score in half!!" ;)
  • ssj4Gogeta - Thursday, September 20, 2012 - link

    Maybe they should make the graph interactive where next to the phone you can select the software version.
  • Steelbom - Wednesday, September 19, 2012 - link

    Fantastic!

    But... run GLBenchmark too!
  • doobydoo - Wednesday, September 19, 2012 - link

    GL Benchmark is not going to be a pretty story for Android fans :P
  • tipoo - Wednesday, September 19, 2012 - link

    You know, saying _____ fans will be ______ is almost as annoying as the fans themselves saying it. This is a benchmark and numbers site, benchmarks bring us all together, lets just appreciate the SoC for what it is. I guess you could say I'm an Android "fan" but I'm really excited that Apple just entered the ARM CPU race in a big way.
  • doobydoo - Wednesday, September 19, 2012 - link

    Alright, calm down there fella...

    Let me rephrase:

    'I believe the GL Benchmarks will be dominated by the new iPhone 5 which will significantly surpass the performance of any Android handset to date'
  • tipoo - Wednesday, September 19, 2012 - link

    I wasn't un-calm, just saying. The best way to reduce fanboyism in comments is just not to talk about it.
  • doobydoo - Wednesday, September 19, 2012 - link

    He says - continuing the discussion about fanboyism.
  • yogi6807 - Friday, September 21, 2012 - link

    i put it in the right spot this time

    "A little bit of casual benchmarking using the GLBenchmark Egypt High test yielded a score of 6766, while the iPhone 4S got 1158. The Offscreen test was closer: 16681 vs 8346. This looks like a lot more than day to day usage bears out, but it suggests that there's headroom for the iPhone 5 to do some pretty impressive stuff."

    http://www.stuff.tv/review/apple-iphone-5
  • bill4 - Wednesday, September 19, 2012 - link

    When I first read it I thought, "Oh, Anand must be showing how amazing it is that A6 outscores a low end X86 Atom like you find in notebooks!"

    But no, googling reveals it's just Intel's smartphone chip. Big deal, lol.
  • André - Wednesday, September 19, 2012 - link

    I believe you are missing the point entirely.
  • tipoo - Wednesday, September 19, 2012 - link

    I might remember wrong, but isn't the Atom in smartphones shown above pretty close to netbook Atom in Sunspider performance?
  • madmilk - Thursday, September 20, 2012 - link

    Yes, performance is about the same as the old single core Atoms in netbooks from 2008.

    Intel missed the best time to ship Medfield by about 6 months, when it would have been a viable competitor against dual core A9 chipsets. The gap is getting shorter though...
  • Penti - Wednesday, September 19, 2012 - link

    This is on slightly older stuff, what about Z2460 on 2GHz and newer Webkit? Should be close, and this Atom is still the same architecture as in 2008. It's a lot faster then the A5 or even A5X. If the clock speed is correct it should be the fastest ARM-around, but software matters so much here. Even at twice the GPU power and very fast custom CPU it's not a chip that will be miles ahead of everything for long. Much of the performance have probably been from faster memory and it's not a next generation GPU, even if it should fit Apple very well it's not like they will smoke next generation chips in everything or always have the best software.

    Current comparisons against other fast devices with updated software will be interesting, but I will wait for the full review for that. Compared to a 1.6GHz single-core Atom on a not so new old build of 2.3 it should damn well be faster though. Though it's fun it's basically Sony PS Vita power in your phone. To bad iPod Touch with A5 has no chance in competing against portable game consoles though, due to price. Would be interesting to see more hard-core stuff in that department.
  • Wilco1 - Wednesday, September 19, 2012 - link

    The Sunspider score for Z2460 at 2GHz turbo is 1062 (http://www.engadget.com/2012/09/18/motorolas-razr-... So the A6 beats the only benchmark where Atom looked good by a big margin. And that for the very latest Atom... This is the final nail in the coffin for Atom - it'll be late 2013/early 2014 before the next generation will appear.

    The A6 will be king of single-threaded performance until Cortex-A15 comes out in the next few months - at 2GHz it should double single-threaded performance again!
  • j85 - Wednesday, September 19, 2012 - link

    Most of the improvements in SunSpider have come from having the latest browser updates. For example, my Galaxy Nexus scores 1413ms on SunSpider in Chrome, which is 400ms less than stock. iOS6 naturally has the latest version of WebKit. The Droid Razr with the Atom Processor is not running the latest version of Android nor was it running Chrome.
  • Penti - Wednesday, September 19, 2012 - link

    It still looks good in Sunspider compared to other Android phones, I've never read anything else into it than that. I wouldn't buy it over fast Quadcore ARM Android-powered units because of it's speed, the devices are in totally different categories. Nice to see what they can do with a single-core Atom though. Glad to see a benchmark though, might have glanced over others without taking notice too.

    It's not the latest Atom however, it's still the 2008-era Bonwell architecture. It is the latest product, not architecture. Nobody expects early SoC's/platforms of doing well and it seems to do fine with a ~5Wh battery. From how it looked back in 2008 it's pretty impressive. That's the same year Cortex-A8 SoC's came available. Next generation is in the pipeline and nobody expected the Z2460 to be in every high-end device up until then. But it's not like you can run Android on the A6 either. It competes against other low-end SoC's. You can always use a larger variant on say a tablet or other type of devices. Or you can stop caring about what architecture it is or you have to run and simply build good products. Atom/PowerVR might not be my favorite combination, but it has it's uses.
  • Wilco1 - Wednesday, September 19, 2012 - link

    Atom does well on Sunspider precisely because of software optimizations. It's the only benchmark it used to win. ARM based phones are catching up with similar optimizations - there is no doubt that iOS6 has had significant JS tuning done, and future versions of Android will add more as well (a score of 1400 with stock browser is now becoming typical).

    Yes the Z2460 is based on the original Atom architecture with only minor changes. But it is actually the very first Atom chip that is capable of being a smartphone CPU, as the original Atoms weren't SoCs and used way too much power. If Intel had released a Z2460 equivalent in 2008, they could have gained a lot of the smartphone market. Now they have to battle with much faster and powerful ARM cores...
  • Penti - Thursday, September 20, 2012 - link

    Of course it's a low end chip that only does well in this benchmark. Only having a PowerVR 540MP2-gpu is abysmal now and it doesn't have that much memory bandwidth. At least TI have released OMAP4470 to get better gpu-performance. Until they have A15's out. It's still impressive to see a chip pushed or that you can update/optimize even better then what they did on 2.3.7/older Webkit.

    Atom still has the same architecture as in 2008, roughly the same clocks, ARM-cores doesn't it isn't just power reductions, multi-core, memory bandwidth, die-shrinks (65nm to 28/32nm) it's also new architecture. It's not like it looks worse and worse for them. Intel already have had success in this field with the XScale line that they sold off. It's not like they need to take the entire market, it's impressive to be there at all regarding how fast ARM-chips have developed just in the last few years. They are large superscalar branch prediciting out-of-order chips already. They have a much better place in the Android ecosystem then MIPS at least. You need to be pretty flexible and move pretty fast to stay there, at least if you don't have a robust architecture to compete with. In 2008 most stuff was still on ARM11.
  • vdx660 - Wednesday, September 19, 2012 - link

    The funny thing here is that the authors left out a glaring detail-- that Apple A6 has a Dual Core vs an Intel Medfield Single Core.
  • darkcrayon - Wednesday, September 19, 2012 - link

    They should've included it but I wouldn't call it "glaring". If the single core is what's available and has a similar power profile to the A6, then why shouldn't they be compared? It's a completely different architecture. It's not like the Medfield phone they tested was a dual core, but they intentionally disabled one of the cores to perform the test. Just like the A6 should be compared directly to the quad core Exynos in one of the Galaxy S III's.
  • tipoo - Wednesday, September 19, 2012 - link

    Exactly what darkcrayon said, core count and clock speed are irrelevant next to power draw and performance. The single core Atom there drew as much or more power, so it is comparable.
  • Wilco1 - Wednesday, September 19, 2012 - link

    Sunspider is a single threaded benchmark so the number of cores (and hyperthreading) does not matter here.
  • Lucian Armasu - Wednesday, September 19, 2012 - link

    That's irrelevant. Sunspider is single threaded.
  • Toss3 - Wednesday, September 19, 2012 - link

    International Galaxy S3 here and I'm scoring 1200ms without any tweaks. Comparing the phones with their current FW would be no more than fair.
  • mjaniec - Wednesday, September 19, 2012 - link

    A pretty old Google Samsung Galaxy Nexus gets 1848.8 ms with Jelly Bean and Chrome...

    Yes, iPhone 5 is faster in this benchmark.

    But the difference is significantly less than presented in this article.

    I wonder what the "real" benchmark result for G3 is...
  • Evollution - Wednesday, September 19, 2012 - link

    Maybe you next time post the OS that you tested this .. GS3 with 4.0 or 4.1 ?!

    + can you test the GS3 with Firefox or Chrome so maybe all the IOS fanboys shout up ?!
  • tipoo - Wednesday, September 19, 2012 - link

    1000ms in Sunspider makes it the fastest smartphone shipping today at that test, and 1400-1600 in Geekbench is very very respectable. I expect they'll hold the CPU performance crown for months (I forget when quad core Krait is coming out, plus true A15 designs), and the GPU performance crown possibly all the way to the next iPhone which will again claim it.
  • tipoo - Wednesday, September 19, 2012 - link

    I think 1000ms is even faster than a Pentium 4 3GHz running a full desktop browser.
  • lowlymarine - Wednesday, September 19, 2012 - link

    I happen to have a Pentium M 750 (Single-core Dothan @ 1.86 GHz) right here, and it still demolishes the A6+iOS6 Safari combo in Sunspider, turning in a score just under 500ms running Chrome 21 on Xubuntu 12.04. Performance of the Pentium M 750 should be roughly comparable to that of the Pentium 4 630, according to Anandtech's own benchmarks: http://www.anandtech.com/show/1399/8

    Boy, that was a long time ago.
  • tipoo - Thursday, September 20, 2012 - link

    You're right, I underestimated, my parents have a 2.9GHz P4 running XP and Chrome 21 got 700.
  • lowlymarine - Wednesday, September 19, 2012 - link

    >"I forget when quad core Krait is coming out"
    "This week," it would appear: http://www.anandtech.com/show/6300/lg-makes-optimu...

    Then again Sunspider is essentially single-threaded so don't look for quad-core Krait to improve performance any over dual-core in that particular benchmark.
  • krumme - Wednesday, September 19, 2012 - link

    "SunSpider JavaScript is only useful for those reviews were
    Atom based phones are to be promoted as "the fastest in the world".... and now
    Apple did spoil that as well"
    Hans de Vries
    http://semiaccurate.com/forums/showpost.php?p=1686...
  • BSMonitor - Wednesday, September 19, 2012 - link

    And the Atom SoC in these is how old?? I hold to Intel taking most of this market by 2014. 14/22nm Atoms on 450mm wafers... Can someone do the math? That's a LOT of smart phone CPU's.. They'll be able to cut the legs out of any ARM maker, price wise and now they have Google making phones WITH them.

    Intel does one other thing well... Make partners.
  • extide - Wednesday, September 19, 2012 - link

    I agree, if anything, the next few years are going to be HELLA fun to watch. Intel is going to put the full force of chipzilla behind getting into this market.... and I believe they will get into it. Atom2 will be quite a significantly different CPU, and it will have a manufacturing process advantage vs any ARM chips right out of the gate. This is a good thing though, competition gets us consumers faster phones for less money.
  • Z3ra7uL - Wednesday, September 19, 2012 - link

    Try running that benchmark on the Puffin browser on android - yep, that's right, you'll get incredible results. I on my dual core Krait(stock rom, no root) got 400 sth points, so if we consider it a valid speed test it would mean that it is twice as fast as the A6, which i think it is not. Soooo as far as I am concerned this comparison shows nothing.

    P.S.
    On the stock android browser I got 1100 sth :)
    P.S. 2
    I have nothing against the article or this website whatsoever, I am only pointing that those results are quite misleading.
  • doobydoo - Wednesday, September 19, 2012 - link

    All you're doing is showing why using stock browser is important.

    It doesn't make the benchmark any less relevant.
  • blueseeker - Wednesday, September 19, 2012 - link

    Nope. All you're doing is showing how limited actually is iOS having only one browser engine.
  • doobydoo - Wednesday, September 19, 2012 - link

    So limited because it dominates the stock benchmark?

    Or is that because you are unfamiliar with the fact that Chrome, Dolphin, Opera, Atomic, Mercury, Photon, Switch, Webout, Cloudbrowse, Knowtilus Pro, Puffin, Flash Browser and Sky Fire are all available on iOS?
  • dysonlu - Wednesday, September 19, 2012 - link

    Isn't Apple forcing all 3rd-party browsers to use the same slow engine: UIWebView?

    I think that's what blueseeker meant.
  • Z3ra7uL - Wednesday, September 19, 2012 - link

    So do you know that stock android is not the same as stock iOS, which makes it the same thing as comparing Chrome and Dolphin on iOS, and that is as you mentioned irrelevant.
    The score doesn't reflect the hardware, it just compares a single component of a specific browser to the same component on a different browser.

    P.S.
    I just ran it on my second gen 4,5GHz Intel i5 on Firefox and got 115ms, just for laughs and giggles.
  • doobydoo - Thursday, September 20, 2012 - link

    I don't think comparing stock for stock is irrelevant just because the browser can affect the score. It's a stock comparison with the stock browser.

    It does reflect the hardware - it just also reflects the software. It's a good real world benchmark.

    @dysonlu - I just ran the Sunspider test on Puffin on an iPhone 4 on iOS 6 and scored 523.5 ms - so it's not being forced to use the same 'slow engine'. Safari achieves 3,000 ms.

    Puffin must have some kind of short-circuit on all devices which makes the result look more impressive than real world performance is - so we shouldn't use it as a comparison.
  • thunng8 - Thursday, September 20, 2012 - link

    Puffin web browser runs Javascript on its own server, so is not a good comparison (not on client machine). Quite an interesting technology. Also allows viewing of flash on iOS.

    According to it website, the new ipad running puffin turns in a score of 325ms om sunspider

    http://www.puffinbrowser.com/
  • doobydoo - Thursday, September 20, 2012 - link

    Ah - this explains my above analysis - thanks.
  • keylimesoda - Wednesday, September 19, 2012 - link

    Any sense of how this will compete with IE10 on WP8 on SnapDragon?
  • Aenean144 - Wednesday, September 19, 2012 - link

    Depends on the JavaScript JIT compiler in WP8 IE. The CPU core is basically the same as the US versions of the SGSIII, HTC One X, HTC One S, Evo 4G LTE, and the Optimus G, which are all on the chart in the article.

    I don't think MS will do a much better job than Apple or Google with the JIT compiler, so it's going to be in the 1500 to 1800 ms range, if not worse.

    You have to compare one-to-one with Sunspider. Same OS, same browser. So, you should be comparing results to the Lumia 900 or Titan or whatever. Even there, it's a problem as WP8 will only run on new phones.
  • john1506 - Sunday, November 11, 2012 - link

    I completely disagree, the 900 was released early this year and mango last year. You obviously don't understand how wp works. Wp8 was released alongside ios6 and the lumia 920/htc 8x/ Samsung ativ s are all current gen hardware released with it only 2 weeks after the iphone 5. I got a score well below the iphone 5, 910ms so yeah your guess was twice as long highly wrong
  • MUTINOUS - Wednesday, September 19, 2012 - link

    I had almost a year with a phone that still rocks and it was never built to be a "top of the line phone". You might be able to beat the specs but you can't beat the the GNex. LOL spec whores.

    https://docs.google.com/open?id=0B62PO1Far_OiUlBib...

    Samsung Galaxy Nexus
    android version : 4.1.1
    Base Version : FF02/FG02
    Kernel Version : 3.0.38-04149-gldc555-dirty Trinity Kernel
    AOKP version : AOKP_toro_jb-build-1
    build number : JRO03H eng.
    Carrier : USA, Verizon LTE
    Hardware updates: Extended Battery 2100mAh + Door
    Release Date : November 17, 2011
  • humancyborg - Wednesday, September 19, 2012 - link

    Sure you can. I sold mine and pre-ordered the i5 last week.
  • yahyoh - Wednesday, September 19, 2012 - link

    one years old s2 with Jelly bean get 1400 ms @ stock cpu speed

    https://dl.dropbox.com/u/59541221/Screenshots/Scre...

    and get 1080ms @ 1.6

    https://dl.dropbox.com/u/59541221/Screenshots/Scre...

    so who care about Icrap , just wait for s3 to get Jelly bean and u will see who will win :D
  • red_dog007 - Wednesday, September 19, 2012 - link

    This benchmark seems to be a load of junk.
    My HTC Rezound scored just 300points higher than my Samsung Galaxy S3.
    Both using Chrome, both on ICS.

    Is there some kind of performance setting on the S3? I turned power saving off.

    I like peacekeeper better for a browser/cpu benchmark.
  • tom.jones - Wednesday, September 19, 2012 - link

    of all the tech blogs, i expected a more nuanced view from you Anand.

    anyone who knows the first thing about JS performance knows how dependent it is on (software) optimizations. just in the last few years, we got up to 50x improvements on various benchmarks *on the same hardware*.

    and anyone who knows the first thing about JIT optimizations know that they must be carefuly written for each architecture, even specific versions of each (x86 vs x64 vs ARM6 vs ARM7 vs..)

    so, TL;DR version is: comparing phones by JS benchmarks, and especially _across architectures_, tells you nothing about CPU performance..
  • dysonlu - Wednesday, September 19, 2012 - link

    Agreed.

    Where did this stupid idea of using JS benchmarks as comparative of CPU performance come from???
  • madmilk - Thursday, September 20, 2012 - link

    There just aren't very many cross-platform benchmarks.

    Coremark is even worse: remember all of Nvidia's claims that Tegra 3 was faster than a Core 2 Duo? Maybe if your whole dataset is in L1 cache...
  • tipoo - Wednesday, September 19, 2012 - link

    Well, the 4S went down from 2300MS to 1700, but the 5s score of 900-1000 is still much lower, so comparing the same software on different hardware we can still say it's just short of 2x.
  • abishekmuw - Wednesday, September 19, 2012 - link

    My HOX running ICS 4.0.4 scores 1200ms in the stock browser. Jellybean is supposed to be faster..
  • Bpease - Wednesday, September 19, 2012 - link

    Well done to Apple on the new A6, it seems an intelligently designed piece of silicon. However Jelly Bean will significantly boost Sunspider / JS performance.

    The Galaxy Note 2 was previewed by gsmarena, and it scored 972 ms in its stock browser, the International S3 also improved its score by around 20% in another preview of the Jelly Bean update. It is worth noting that the tests were done with Beta software, so actual performance may improve or worsen!

    Hopefully the A6 will push Samsung to launch the Eyxnos A-15 based 5450, quad core @ 2.0 GHz and Mali T-658, pretty soon. A Nexus phone with that SoC might persuade me to ditch my WP7 and return to a pure Android stack, currently I run a Lumia 710, alongside a Nexus 7 ( + old iPod Touch for teh exercising)

    http://www.gsmarena.com/samsung_galaxy_note_ii-rev...
  • vision33r - Wednesday, September 19, 2012 - link

    1GHZ iPhone outperforming so many 1.2~1.5GHZ Android phones

    Efficiency > Raw processing power
  • superman3gsm - Thursday, September 20, 2012 - link

    The latest Sunspider scores on current Medfield SW builds beats the iPhone5 scores shown
  • thunng8 - Thursday, September 20, 2012 - link

    No it doesn't:

    http://www.engadget.com/2012/09/18/motorolas-razr-...
  • yogi6807 - Thursday, September 20, 2012 - link

    found this

    "A little bit of casual benchmarking using the GLBenchmark Egypt High test yielded a score of 6766, while the iPhone 4S got 1158. The Offscreen test was closer: 16681 vs 8346. This looks like a lot more than day to day usage bears out, but it suggests that there's headroom for the iPhone 5 to do some pretty impressive stuff."

    http://www.stuff.tv/review/apple-iphone-5
  • tipoo - Friday, September 21, 2012 - link

    Double the performance of the 4S should put it near the iPad 3, but those reported scores are WAY higher.

    http://www.glbenchmark.com/result.jsp
  • tipoo - Friday, September 21, 2012 - link

    Actually I was looking at the wrong thing, but in the Egypt High test the 4S gets 6000 too...
  • yogi6807 - Friday, September 21, 2012 - link

    i was on the gl bewnch web site nothing came close to 6000. the 4s scored 1158 it says. the highest score to it was 3445 the xiaomi mi 2. that looks pretty good to me. i just cant figure out what the second test is.
  • yogi6807 - Friday, September 21, 2012 - link

    i hope i looked at the right thing
  • Achtung_BG - Friday, September 21, 2012 - link

    iPhone 5 is already on the market, waiting for a detailed test of the A6 chip
  • TechDenzo - Thursday, September 27, 2012 - link

    And got a score of 1791.3ms. Looks pretty good to me. I have no idea what this really means, but thats what a 4S gets. I have everything on (Wifi, BT, 3G etc) 64GB model nearly full in memory as well if that makes a difference.
  • eliway - Thursday, September 27, 2012 - link

    Just got 1030 on my HTC one X at&t with a custom kernel. Also got 1800 on geekbench (compared to 1600 on the iPhone 5, higher scores are better).

    I think what it shows here is that both Qualcomm and Apple chose not to use A15s due to battery concerns, and their custom arquitectures are actually quite comparable.

    Also, I think Sunspider should not be used as a reliable test/benchmark, even for memory interface measurements... For example, using chrome I get 1900ms while on stock browser I get 1000. Stock is almost twice as fast!

    These differences in software could potentially get pretty misleading results, and I think any reputable and respected tech site that takes its reporting seriously should find an alternative that's not so reliant on software.
  • john1506 - Saturday, November 10, 2012 - link

    I got 912ms 😎 on the lumia 920
  • lolzxdrofl - Sunday, December 2, 2012 - link

    I've runed the sun spider test 5 times on my lg optimus G on the default browser and i get 1250 on my sun spider, idk how yours got 1600
  • Zekk98 - Friday, December 28, 2012 - link

    I am responding to this post because the LG Optimus G results are seriously off I have the LG Optimus G and I consistently get scores around 1000-1250ms and have yet to get any higher. I can easily provide screenshots or a video showing the phone as I do the benchmark, I just hate to see this phone be shown inaccurately for potential buyers.
  • SantoBr - Tuesday, January 29, 2013 - link

    Chrome Beta 25.0.1364.47 running Android 4.0.4 on Motorola XT910

    1286.9ms
    http://goo.gl/7PCl2

    1324.2ms
    http://goo.gl/E9C97
  • Gnius101 - Thursday, June 12, 2014 - link

    My iphone5 score is 748.5ms
    http://m.imgur.com/godDPwk
    What does it mean?

Log in

Don't have an account? Sign up now