POST A COMMENT

218 Comments

Back to Article

  • Paulman - Tuesday, October 11, 2011 - link

    The iOS5 improvement for the iPhone 3GS is ridiculous! The SunSpider bench completes in less than 50% of the original time. Wow. The iPhone 4 gains are impressive as well.

    - "I suspect Ice Cream Sandwich will bridge the Android smartphone gap."

    Hmmm... I wonder how big that jump will be. And I wonder if the Samsung Galaxy S II (and variants) will be getting the Ice Cream Sandwich update anytime soon (after Google releases it)...
    Reply
  • JasonInofuentes - Tuesday, October 11, 2011 - link

    It's up to the chipset manufacturers to manage the ports of Android variants to their respective chipset. This typically doesn't take a long time, though with Honeycomb we seemed to wait an awfully long time, and are only now starting to see non-Tegra 2 tablets roll out. With any luck ICS will get ported to all the SoCs on the market quickly, and then, unfortunately, it's up to the individual device manufacturer's to implement them and then the carriers to validate them. Sigh. It could be a while. Reply
  • B3an - Tuesday, October 11, 2011 - link

    I expect Ice Cream Sandwich to easily put the android phones ahead for javascript performance. As even a slower Tegra 2 with Android 3.1 can atleast match the 4S here. The Samsung GSII will take the lead once its gets ICS.

    No idea if ICS will help much with GPU performance though.
    Reply
  • steven75 - Tuesday, October 11, 2011 - link

    Has Samsung gone on record that they will provide ICS for the GSII? We all know how this story goes on Android... Reply
  • Bozzified - Tuesday, October 11, 2011 - link

    Samsung is fairly good at keeping it up to date, at least in my experience. They update SGS2 with the latest Android maybe a few weeks after an official SDK is released. Reply
  • michael2k - Tuesday, October 11, 2011 - link

    I guess it depends on how you define "good". They're still releasing Gingerbread updates to their Galaxy S (a 19 month old phone), which is good, but this is still 10 months after Gingerbread was released (which is bad). Reply
  • ph00ny - Tuesday, October 11, 2011 - link

    It's hard to comment on things when outside of carrier branded ones are updated to gingerbread much earlier Reply
  • AnandReader1999 - Wednesday, October 12, 2011 - link

    In Canada, we get our updates much faster than the USA. It's unfortunate that you guys are restricted so much by your carrier's, but it has nothing to do with Android or the phone manufacturer in most cases...just USA's carriers. Reply
  • Paulman - Sunday, October 16, 2011 - link

    Really, we do? Sweet! Hopefully that bodes well for the Galaxy S II LTE that will be released here by Rogers in Canada (soon). It's looking more and more like that will be my new phone (as opposed to the iPhone 4S) and it would be very much appreciated if/when ICS comes in for that model :P Reply
  • mwarner1 - Thursday, October 13, 2011 - link

    The following firmwares have been released in Europe for the Galaxy S. As has been pointed out, this is a US carrier issue and not a Samsung issue - Samsung are generally very good indeed at regular firmware updates:

    Firmware Android Date 
    I9000XXJE2  2.1  2010 May 
    I9000XXJE3  2.1  2010 May 
    I9000XXJE5  2.1  2010 May 
    I9000XXJE6 2.1  2010 May
    I9000XXJE7  2.1  2010 May 
    I9000XXJE9   2.1  2010 May  
    I9000XXJEC   2.1  2010 May  
    I9000XXJF1   2.1  2010 June 
    I9000XXJF2   2.1  2010 June 
    I9000XXJF3  2.1  2010 June 
    I9000XXJF7   2.1  2010 June 
    I9000XXJFB   2.1  2010 June  
    I9000XWJFD  2.1  2010 June  
    I9000XWJFF 2.1  2010 June 
    I9000XWJG1  2.1  2010 July 
    I9000XWJG3  2.1  2010 July  
    I9000XWJG5 2.1  2010 July  
    I9000XWJM1 2.1  2010 July  
    I9000XWJM1 # 2.1 2010 July
    I9000XWJM2 ## 2.1  2010 July 
    I9000XWJM5 # 2.1  2010 July  
    I9000XWJM6 ## 2.1  2010 August 
    I9000XWJM7 ## 2.1 2010 August
    I9000XWJM8 ## 2.1 2010 August
    I9000XXJP1 # 2.2  2010 August
    I9000XXJP2 # 2.2  2010 August
    I9000XXJP3 # 2.2   2010 August 
    I9000XXJPC ## 2.2  2010 August 
    I9000XXJPH ## 2.2 2010 September
    I9000XXJPK ##  2.2 2010 September
    I9000XWJM9 ## 2.1 2010 September 
    I9000XWJP6 ## 2.2 2010 October
    I9000XXJPM ## 2.2 2010 October
    I9000XXJPO ## 2.2 2010 October
    I9000XWJPA ## 2.2  2010 October
    I9000XWJPA ## 2.2 2010 October
    I9000XFJP7 ## 2.2 2010 October
    I9000XWJPB ## 2.2 2010 October
    I9000XFJP9 ## 2.2 2010 November
    I9000XXJPI ## 2.2 2010 December
    I9000XXJPU ## 2.2.1 2010 December
    I9000XXJPX ## 2.2.1 2010 December
    I9000XXJPY ## 2.2.1 2010 December
    I9000XWJS3 ## 2.2.1 2011 January
    I9000XWJS3 ## 2.2.1 2011 January
    I9000XFJS2 ## 2.2.1 2011 January
    I9000XWJS5 ## 2.2.1 2011 January
    I9000XWJS5 ## 2.2.1 2011 January
    I9000XXJQ3 ## 2.2.1 2011 January
    I9000RSJS2 ## 2.2.1 2011 January
    I9000XWJS7 ## 2.2.1 2011 February
    I9000XWJV1 ## 2.3.2 2011 February
    I9000XWJS8 ## 2.2.1 2011 March
    I9000XXJVK ## 2.3.3 2011 March
    I9000XWJVA ## 2.3.3 2011 April 4 
    I9000XWJVB ## 2.3.3 2011 April 8
    I9000XWJVB ## 2.3.3 2011 April 8
    I9000XWJVB ## 2.3.3 2011 April 8
    I9000XWJSD ## 2.2.1 2011 May 2
    I9000XWJVH ## 2.3.3 2011 May 4
    I9000XWJVH ##  2.3.3   2011 May 4 
    I9000XWJVH ## 2.3.3 2011 May 4
    I9000XWJVH ## 2.3.3 2011 May 4
    I9000XXJVO ## 2.3.3 2011 May 4
    I9000XWJVH ## 2.3.3 2011 May 4
    I9000XWJVH ## 2.3.3 2011 May 4
    I9000XWJVI ## 2.3.3 2011 May 14
    I9000XXJVP ## 2.3.4 2011 June 3
    I9000XXJVQ ## 2.3.4 2011 June 10
    I9000XXJVR ## 2.3.4 2011 July 27
    I9000XXJVR ## 2.3.4 2011 July 27
    I9000XXJVS ## 2.3.5 2011 September 8
    Reply
  • AnandReader1999 - Wednesday, October 12, 2011 - link

    The improvements are less impressive when you realize that Apple only gives you what if feels like it needs to. If you look at historical data, Apple improves their software at 'just enough' of a pace to compete and maximize their money.

    If you want to see how Android competes, get an SG2 and use a better than stock browser that loads flash and is tabbed with a ton of features built into it. Then run a comparison and you'll think...what's the big deal with Apples' 4S...it is competitive, but not so amazingly stunning, UNLESS you're a 3GS or 4 user...then its 'Amazing'...but only because you were using such an inferior product to begin with.

    Its the nature of Apple to make the most they can off of you while the user thinks they have the best product available...when really they don't.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Apple releases the phone with the fastest CPU/GPU combination you can get in any phone, and according to you they do 'just enough'.

    Yeah, OK.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    And by the way, it's much, much faster than the Samsung Galaxy S2, with better battery life and less user complaints. Reply
  • kebab77 - Sunday, February 05, 2012 - link

    Check out the massive benchmark improvements on a Galaxy S2 running ICS beta: http://www.bestsmartphone.com/2012/02/05/android-4... Reply
  • Formul - Tuesday, October 11, 2011 - link

    I wonder if combination of Ice Cream Sandwich with Kal El will be able to catch up to A5/iOS5 combo. Its twice as fast as anything on the market ... and how the hell is iPhone 4 with singe Cortex A8 having the same (or even beating) exact score as dual core Cortex A9 phones in many tests? some of them with doble the RAM? Reply
  • adriaaaaan - Tuesday, October 11, 2011 - link

    You're comparing apples to oranges.
    Gingerbread only uses one core in it's browser compared to honeycomb's hence why the iphone 4's newest browser beats gs2. With ICS It would easily win this benchmark as noone would deny its faster than tegra 2 and thats not including the obvious speed improvements ICS's browser would have anyway
    Reply
  • Chickenatr - Tuesday, October 11, 2011 - link

    But that still doesn't explain how an archaic processor (A8 vs A9) with half the ram beats the newer android superphone on that.

    Looks like Apple really know their stuff, or Android is just not well written. Heck, even older WP7 devices run faster than newer Android devices on supposedly better hardware.
    Reply
  • DrChemist - Tuesday, October 11, 2011 - link

    I highly agree that all these benchmarks really mean nothing other than that mobile OS dominates performance on mobile devices and nothing more than that. As far as graphics, that is highly dependent on the chip used which is dependent on the newest thing out. Take for instance my Samsung Focus (7720 - Mango) using the QSD8250 and Adreno 200 getting ~9500ms while the original WP7.0 gave ~44000ms. People need to focus on the OS to squeeze performance. I even feel the general performance of my phone is much quicker than iOS or Android 2.3. Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    I think you just explained “mobile OS dominates performance” as “integration of OS and hardware determines performance.”

    Which would support @Chickenatr's contention: must be a lot more love that went into those Apple devices than the stuff that you're comparing them to.
    Reply
  • Black1969ta - Tuesday, October 11, 2011 - link

    Apple has a company that "Hardens" their CPU design. While I would bet the homogeny of software and hardware in Apple closed environment does lend effciency to their design, but an A5 from HTC is not the equivalent of an A5 from Apple, many OEMs use a Hardened version of the ARM design so that it is more focused on their design specifications. Reply
  • kgunn - Wednesday, October 12, 2011 - link

    >>While I would bet the homogeny of software and hardware in Apple closed environment does lend effciency to their design

    precisely...closed system luxury.
    damn all the industry standard sw interfaces...just hardcode/backdoor the sw for maximum performance.
    Reply
  • KoolAidMan1 - Wednesday, October 12, 2011 - link

    It's the latter. WP7 and iOS devices on 2010 hardware are much smoother than even the latest Android handsets. The Android OS is a huge obstacle to performance until they fix hardware acceleration of the UI, etc etc. Reply
  • AnandReader1999 - Wednesday, October 12, 2011 - link

    Its a combination of things. Apple controls the Whole process, from beginning to end. They make the hardware, they make the software and they decide what you get for both and what performance you will see for the price they want to charge.

    The iPhone 4S is ONLY powerful due to its GPU. It is the most advanced on the market. The second is the Samsung Mali 400 (in its first version). If Apple didn't have massive market pressure on it from Samsung/Android, it would have run with only a slightly updated GPU. Want proof...look at the performance the GPU on the 3GS & 4 compared to the 4S.

    And to other's above...older designs are not bad...it just depends on what your technical goals are and the costs you want to pay.

    On the topic of 'needing' newer hardware to compete. Not really. Anands' preview stuff used only the phone's stock software. None of the actual advantages Android user's have was taken into account. Using a faster tabbed browser is a given. Taking into account Android can see native Flash, iPhone can not. How about the fact that in the Dolphin browser I can set it to whatever display method I want (i.e. Desktop, iPhone, Mobile, Native Android, etc.) by the flip of a switch AND because I can see flash, I can see the entire site on my whole 4.3" of screen......

    I think if we actually compared strengths between the phones, they would be very much the same (iPhone to SG2 for example). The only difference would be that in 'some' cases, the 4S GPU wins out, but since no games take advantage of that, its a moot point. All screens are locked to 60fps, so extra horsepower gets wasted or (in the future) allocated to more background processing, which the current games aren't using.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    The mali 400 in the SG2 is not just '2nd best' to the Power 543 in the iPhone 4S. It's less than half as fast. That's a major, major difference.

    You can use apps to allow flash if you want. iPhone users can also 'see the entire site' on their screen.

    The bottom line is the iPhone 4s is faster, more responsive in everything (even when taking pictures, for example), has a larger app library, better battery life, smaller physically (volume), and has far far fewer user complaints than the Samsung.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Yeah a lot of people mistake clock speed for performance.

    The 800mhz iPhone 4S beats any Android CPU/GPU performance on the market today
    Reply
  • Omid.M - Tuesday, October 11, 2011 - link

    I would put it at 6-8 months. That is, the AT&T SGS2 could take about 6-8 months AFTER ICS debuts to receive that version OS via OTA. At least, I think that's par for the course for most carriers/manufacturers.

    Brian? Anand? Thoughts?

    This is what will always hurt Android: time to OS updates due to fragmentation (skinning, diff carrier bloatware).

    I'm personally waiting to see Nexus "Prime" vs HTC Vigor...and would prefer Prime only for the speedy updates and longevity of the device in terms of support. Otherwise, I think the best and most impressive devices will be using Krait, which is likely Q3 2012 at the earliest (sadly).

    At that point, I'd be comparing the best Krait Android device vs (hopefully) an iPhone "5"...

    @moids
    Reply
  • JasonInofuentes - Tuesday, October 11, 2011 - link

    Agree @moids. There's always hope in the custom ROM world to get updates, often more reliable than the updates pushed by carriers, but not everyone is comfortable with that sort of thing. And another +1 to you for your Krait supposition. That is going to be a potent chipset and will offer a power bargain integrating so many radios and processing power into a light package. But that won't stop me from upgrading this Fall. OG Droid has seen its end.

    Jason
    Reply
  • Omid.M - Tuesday, October 11, 2011 - link

    I saw you go Office Space on the OGD. Have Brian record it with you, stomping on the chassis with your Vibrams.

    I get 15% cut if this goes viral =)
    Reply
  • Omid.M - Tuesday, October 11, 2011 - link

    *say

    @moids
    Reply
  • 3DoubleD - Tuesday, October 11, 2011 - link

    My Droid (Milestone actually) has is also nearing it's last days in my pocket. The Bionic review really has me worried for the Prime though. Battery life is just pathetic. Hopefully I can just disable LTE for data altogether. 3G was fast enough on my Droid, I don't think I'll be missing out much. That will be the stopgap solution until Krait...

    I too hope for the Nexus Prime to be excellent as I would love to get speedy updates from Google. I currently enjoy the custom ROM scene on my droid, running stock 2.3.6 right now, but stability has always been an issue (I entirely blame Motorola for being )
    Reply
  • cditty - Tuesday, October 11, 2011 - link

    I definitely agree. If you are going to do Android, it should always be a 'Google Experience' device. It gets updated like a real phone should. Reply
  • steven75 - Tuesday, October 11, 2011 - link

    Yep, and sadly there's no modern Nexus phone for those of us that are strongly against the giant display wars.

    I won't consider an Android phone that I have to wait 8 months to update after being on iOS for years now where we get updates literally the day they came out.
    Reply
  • Piano Man - Tuesday, October 11, 2011 - link

    Why or why can't this phone have LTE. Then there would be no competition, and I could buy this phone in peace :) Reply
  • relentlessfocus - Tuesday, October 11, 2011 - link

    Battery life vs number of places that actually have LTE Reply
  • inplainview - Tuesday, October 11, 2011 - link

    Didn't you read the reason's why there is no LTE in the 4S? Dear God, it can't be that hard...

    Please do every one a favor and don't buy a 4S. This way you can buy something else and keep the whining to yourself.
    Reply
  • JasonInofuentes - Tuesday, October 11, 2011 - link

    Relevant. http://www.anandtech.com/show/4925/why-no-lte-ipho...

    TL;DR: Add LTE and you'd have a power hungry thicker device. Leave it out and next year you'll have an even thinner, less power hungry device with LTE.
    Reply
  • MonkeyPaw - Tuesday, October 11, 2011 - link

    AND you can sell yet another new phone. ;) Reply
  • name99 - Tuesday, October 11, 2011 - link

    Dear god this is a stupid comment.

    What exactly is your argument here? That Apple is deliberately updating their phones slowly so as to get people to buy a new phone every year?

    So what's your view of what Android phone vendors are doing? Their updating their phones every three months somehow doesn't force people to buy a new phone every three months, but Apple's once a year update does?

    So according to you BOTH of these hold
    - Apple released a new phone (which, in your opinion sux) AND
    - this new phone is of not much appeal to people already on contract with an iPhone 4 AND
    - presumably Apple's new phone in 2012 WILL be appealing to iPhone4 customers? AND
    - this is bad?
    So Apple releasing phone updates in a way that matches well the two year phone updating schedule of people on contract is "an evil plan to sell phones
    to people who don't want them"? I'm sorry but the logic here totally eludes me.

    (Compare with the following statements
    - iPhone 4S sux because the appearance didn't change
    - Android phones change their appearance every three months
    THEREFORE
    - Apple sheeple all buy phones based on appearance and fashion

    Huh?)
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    People expected Apple to change the appearance as in: "make the screen bigger".

    This is shorthand for:
    - a better web browsing experience
    - a better movie watching experience
    - a less crowded keyboard
    - more touchscreen real estate, making things less crowded
    and many other benefits to increasing the screen size from lowest-in-class 3.5 inches to something more reasonable like 4.0" or more.

    Apple has created just about the most powerful mobile gaming device. But they kept a small screen on it. Unfortunate for those who want to use it for that. Personally not my thing. So add this to the list of benefits from bigger screen size:
    - better gaming controls and usability

    The "appearance and fashion" you may be referring to is the sleek but unnecessary materials. For example, the back of the phone. Personally, first thing I do when I get an expensive phone is put it in a case. I like to watch the cheap plastic battery cover film that Samsung uses as it becomes completely enclosed by my snug rubberized white Case-Mate case and think of all the money saved that actually goes towards things that matter. As a result, the phone is lighter and gets better signal as a bonus.

    But I think you're mixing a lot of other criticisms about frivolous reasons to get a particular phone into that "appearance" category. There are many.
    Reply
  • vinzclortho - Wednesday, October 12, 2011 - link

    Agreed about the screen size. A bigger screen would be nice so long as it doesn't increase the dimensions of the iPhone to the pocket-bursting enormity of some of the recent androids.

    I suspect that Apple kept the current retina display for logistical reasons. They're a single company competing with the growth of an entire industry, so they need to crank out a _lot_ of devices to maintain or grow market share. A tiny high res lcd like theirs is damn hard to mass produce. Now that their existing factories are dialed in pretty well, retooling for a bigger screen would introduce risk of part shortages.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Very subjective opinions posing as facts there.

    A lot of people prefer smaller screens. You can wirelessly hook the phone up to HD televisions if you want larger screen gaming.

    Trying to argue that plastic on a phone is a good thing is certainly new.

    I prefer the fact that the iPhone 4 I own can actually fit in my pocket, where the larger volume of the Samsung Galaxy S2 can't. I also don't want my phone freezing all the time or the battery life problems so many are reporting.

    Also, it doesn't get better signal at all, why just make stuff up?

    As for 'better gaming controls and usability' - that fails to take into account that the SG2 couldn't even run some of the games the iPhone 4S can - how can you control it if you can't even play it? Not to mention responsiveness
    Reply
  • rangerdavid - Monday, October 17, 2011 - link

    Hear-hear, my fine fellow. I've posted several times that I DO NOT WANT A LARGER SCREEN. If anything, I'd like a Palm-Pre-size iPhone, or smaller. I've always perked up when I heard rumors of an "iPhone Nano."

    I do not plan to watch movies on this thing in the back seats of my 4th-period Social Studies class. I want it to fit in a pocket and last all day+ on its batteries.

    (Do they still call it Social Studies? ...been a while for me)

    So, enough with the "bigger is better" complaints about screen size. Sadly, I doubt Apple wants to veer from its "one size fits all" marketing simplicity, so neither of us will get our larger or smaller iPhones. We can both be sad and angry and pout.
    Reply
  • mcnabney - Tuesday, October 11, 2011 - link

    The existing 3G networks are slow and crowded. Verizon is now covering over half of the population with LTE with roll-out accelerating. AT&T is finally rolling theirs out. While an LTE radio makes it nearly impossible to get two days out of a charge, most of us charge overnight anyway.

    All Apple is doing selling non-LTE is having millions of customers sign two-year agreements to have inferior service compared to the competition. I would also point out that real-life performance is horribly crippled by connectivity. A fast browser score means NOTHING if it takes much much longer to just GET the data. All the synthetic tests done here have zero correlation to an actual user experience, especially when the current hardware leader is hampered by 3G connectivity.

    FYI - non-LTE Android devices are priced at or under $100 - far less than iPhones.
    Reply
  • steven75 - Tuesday, October 11, 2011 - link

    "While an LTE radio makes it nearly impossible to get one day out of a charge"

    T;FTFY
    Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    Hmmm: so we shouldn't care that LTE gobbles battery life and the service plans cost more thru at least one carrier, because you can get data faster.

    But we should pay all the attention to low-cost Android phones that DON'T get data as fast and DON'T process it quickly, and compare only their price to Apple's top-of-the-line product, even tho you can get a cheaper Apple.

    Frankly, I'm not sure WHAT you're actually pretending makes any sense, except, you want to be heard saying, “BUY ANDROID FER CHRISSAKES!!!”
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    And they are not at all comparable in any other way Reply
  • JustanAvgJoe - Wednesday, October 12, 2011 - link

    Or, you could make a thinner, lighter, faster device with LTE and if you don't want it to be power hungry just turn off LTE and go off 3G.

    *shrug*

    I prefer choice.
    Reply
  • tnrmem - Tuesday, October 11, 2011 - link

    I've got vastly different SunSpider and BrowserMark scores on my SGS2 to that of the listed charts. From the few tests that I've done, SunSpider scores around 1750ms while BrowserMark ranges in the mid-90k. Granted I'm running the latest version of CM7 on my device, but shouldn't the stock ROMs be a little bit faster, as the browser supports hardware acceleration? Reply
  • sleepeeg3 - Tuesday, October 11, 2011 - link

    I trust Anand implicitly, but the results just defy logic. Apple is using a Samsung CPU with 50% lower clock speeds, yet getting double the benchmark performance? Is Android that much of a bottleneck? What is going on here? Reply
  • sleepeeg3 - Tuesday, October 11, 2011 - link

    Edit: These are just results collected from the net? I will wait for the real review... Reply
  • Brian Klug - Tuesday, October 11, 2011 - link

    The results that are starred (*) are those that leaked today and don't have duplicates or confirmation, the other results are run by either myself or Anand (iPhone 4 / 3GS).

    The results from GLBenchmark 2.1 and Geekbench seem credible (multiple results).

    -Brian
    Reply
  • wicktron - Tuesday, October 11, 2011 - link

    There's a difference between designed by Samsung and manufactured by Samsung.

    The A5 is designed by Apple and manufactured in Samsung factories.

    Exynos is designed and manufactured by Samsung.
    Reply
  • vision33r - Tuesday, October 11, 2011 - link

    And that's why the Exynos is inferior to the A5. If it was better, Apple would've used it. Reply
  • doubledeej - Tuesday, October 11, 2011 - link

    Uhhh... JavaScript performance is as much tied to software implementation as it is CPU. For the sake of argument, if Safari's JavaScript interpreter was twice as fast as Android's, you could run a CPU half as fast and get the same performance. iOS5 improves JavaScript performance quite a bit. Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Thank god we're not just comparing javascript performance, then. Reply
  • vision33r - Tuesday, October 11, 2011 - link

    It's an Apple designed CPU manufactured by Samsung. Of course the A6 will be designed by Apple and manufactured by TSMC.

    A4/A5 borrows some Samsung technology from contractual agreement. The A6 will have to design around Samsung's IP in order to get out avoiding lawsuits.
    Reply
  • KoolAidMan1 - Wednesday, October 12, 2011 - link

    "Is Android that much of a bottleneck?"

    Given that iOS on A4 or WP7 on Snapdragon was faster than Android on the technically faster and much newer Humminbird, yes, I'd say that Android is a huge bottleneck on performance.

    Having all the clockspeed in the world doesn't matter when the OS has fundamental issues holding it back.
    Reply
  • humancyborg - Monday, October 17, 2011 - link

    The A5 is *NOT* a "Samsung CPU". Samsung is simply the manufacturer. Reply
  • Brian Klug - Tuesday, October 11, 2011 - link

    Are you running the stock browser or something else? I wager something else. The results in that table are reflective of an international SGS2 running the latest stock ROM from Kies (XXKI1, which is 2.3.4). I'm not running CM7.1 on this SGS2 presently. I just ran again and got 4647.0ms, so I consider our score above to be representative, if an optimistic outlier, even.

    This is also the stock/default browser. The Sunspider 0.9 numbers on Android have always been that way for the sake of comparing between SoCs.

    -Brian
    Reply
  • JasonInofuentes - Tuesday, October 11, 2011 - link

    The browser GPU acceleration that Brian mentions in his review is designed to smooth scrolling and zooming, but it doesn't actually accelerate the compute process. That remains a good measure of CPU performance. CM7 is a speed optimized ROM and likely running a much newer version of Gingerbread than what shipped stock on the device, as such it's no surprise your scores are faster. Reply
  • DeciusStrabo - Tuesday, October 11, 2011 - link

    My SGS II results are better than the ones in the table, but not that much - 3500 ms in Sunspider and 60,000 in Browsermark. I'm using RomRevolution 2.7 as Rom, maybe CM7 uses both CPU-cores? That would explain your result. Reply
  • adrien - Tuesday, October 11, 2011 - link

    We can still see the performance gains after the iPhone 3GS in sunspider but this one is quite surprising. WebKit is the same shared codebase (after a delay sometimes, but it _has_ _to_ be out now) and it had reached a plateau:

    http://arewefastyet.com/old-awfy.php

    I always find such improvements dubious and I really can't wait to see the full benchmarks and analysis.
    Reply
  • Brian Klug - Tuesday, October 11, 2011 - link

    Sure, JS performance has plateaued on desktop architectures (that page seems to only apply to x86 and x64), but clearly mobile (ARMv7 w/NEON) is enjoying the benefits of newfound attention. Keep in mind that the JS engine isn't shared between iOS and Android at all: Android uses V8, iOS is using a mobile version of Nitro. I'm told at present that there are fewer than 5 people dedicated full time to ARM V8, and who knows how many for Nitro.

    The huge improvements in iOS 5 are thanks in part to moving to an updated Safari 5.1 codebase:

    "The WebKit framework has been updated to a version which closely matches the engine used by Safari 5.1 on the Desktop. There are some areas to be aware of with the new WebKit framework on iOS 5."

    We'll be talking about this more in our iOS 5 review.

    -Brian
    Reply
  • odedia - Tuesday, October 11, 2011 - link

    You go through a battery in 4-5 hours. I think it is either related to iCloud or iTunes WIFI syncing, turning these two off solves the issue. Reply
  • tipoo - Tuesday, October 11, 2011 - link

    Probably only a one time thing for battery that bad then. Like a new laptop indexing all the files. Reply
  • jklubi - Tuesday, October 11, 2011 - link

    Can you at least include the Nokia N9 and N900

    to give an overall look,
    Reply
  • skydrome1 - Tuesday, October 11, 2011 - link

    The GPU's power level...

    It's over 9000!

    What?! IT'S OVER 9000?!

    I'm really really really excited about PowerVR's GPUs!!! Even the PS Vita has one of em'. Or maybe 4.
    Reply
  • make_dots - Tuesday, October 11, 2011 - link

    Why that sunspider and browser chart does have Galaxy Tab but doesn't have iPad 2 nor iPad 1?

    You guys must put them on the chart for comparisons.
    Reply
  • Mike1111 - Tuesday, October 11, 2011 - link

    I second that. IF you put tablet results in smartphone benchmarks you should at least have one of each in there, especially if it's the fastest one (iPad 2). Reply
  • BoyBawang - Tuesday, October 11, 2011 - link

    I remember that the Die size of Exynos is about the same size as A5 at 45mn process But GPU architecture made a huge gain for A5! Samsung should give up Mali and follow the PowerVR path. Reply
  • Lucian Armasu - Tuesday, October 11, 2011 - link

    I thought the A5 GPU is that fast because it's a much larger SoC (and GPU) - twice as big as Tegra 2. Can you confirm that, Anand? Reply
  • tipoo - Tuesday, October 11, 2011 - link

    True. Its 122mm2 compared to just 49mm2 of the Tegra 2. Even taking the transistor size difference into account, the A5 clearly has more stuff, and most is due to that MP2 dual core graphics chip. Reply
  • BoyBawang - Tuesday, October 11, 2011 - link

    I was comparing A5 with Samsungs EXYNOS not Tegra2. If you google it, A5 and Exynos are of the same Size at about 120mm but A5 GPU performance is far ahead that's why I was praising its GPU architecture over MALI Reply
  • skydrome1 - Tuesday, October 11, 2011 - link

    I did remember reading somewhere that the A5 is huge, and that NVIDIA commented that that allowed them to market their 80mm^2 Kal El better. I believe the Exynos is much smaller than that? Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    <i>“the A5 is huge [122mm^2], and that NVIDIA commented that that allowed them to market their 80mm^2 Kal El better.”</i>

    Boy, selling that your competitor's CPU is too “huge” because it's half again as large would tax the best marketing department *I* can think of.

    Assuming that Apple knows a thing or two about power management (and they do), the size doesn't mean diddly for power consumption. It therefore doesn't mean anything about heat. It can't possibly have a perceptible impact on the size of the overall device.

    Instead, it'll merely tell prospective customers that your competitor has put in circuitry that they thought would be useful, worth a teensy bit of extra expense (that again won't be visible to the consumer). If Apple were to market on this level (and it doesn't), they'd ask to compare GPU-heavy benchmarks such as game speeds. If the iWhatever does at least as well as the TegraX, who cares what the size is?

    There are many things about nVidia that I don't understand, but I'll move this to the top of my list.
    Reply
  • BoyBawang - Wednesday, October 12, 2011 - link

    II was comparing A5 with Samsungs EXYNOS not Tegra2. If you google it, A5 and Exynos are of the same Size at about 120mm but A5 GPU performance is far ahead that's why I was praising its GPU architecture over MALI Reply
  • inplainview - Tuesday, October 11, 2011 - link

    Outside for the few hardcore people here that are never satisfied with anything, how will any of this matter to the average consumer to whom the iPhone is marketed at. It is all well and good to have these spec debates but really, who cares? Reply
  • bpcookson - Tuesday, October 11, 2011 - link

    Performance is a feature. Everyone cares, just not everyone wants to know numbers.

    Here is an excellent post about it:
    http://www.codinghorror.com/blog/2011/06/performan...

    Androids tout numbers left and right, so being able to forward benchmarks of this nature to friends and coworkers is fantastic. :)
    Reply
  • inplainview - Tuesday, October 11, 2011 - link

    Good points.... Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    <i>“being able to forward benchmarks of this nature to friends and coworkers is fantastic. :)”</i>

    Presuming that you want to forward this to coworkers who have chosen Android because they think in these terms, I'm not clear why/how it'll be fantastic to show that Apple software upgrades, free and easily available for compatible devices, enhances older devices' results by 50%.

    …or that Apple's new product is at the top of the heap of measured performance, despite others having supposedly faster CPUs and all the emphasis that Apples are just toys for the clueless.

    …or that the iPad2 is off the top of the chart against EVERY Android.

    Again, Apple doesn't play this game because they focus on the user experience, so I presume you are thinking these numbers will help promote Android. But they don't. Care to help me understand?
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    I think you thought the GP was saying something he wasn't....

    Nevertheless, I'll address your points. I think it could be argued that Apple has focused on the wrong areas. I mean, they improved the performance of the web browser beyond that of the Galaxy S II (which is already very smooth zooming in and out while display Flash animations on a full webpage), but the iPhone still does not display Flash (therefore does not display whole websites), and obviously the screen size is much smaller which also diminishes the web browsing experience.

    Similarly, the iPhone now has all this power while you're looking at the home screen, but the home screen doesn't DO anything. No widgets, no live tiles, not even any sort of eye candy. Rows of icons. No form OR functionality to be found there.

    So the processor may be helpful for Siri. For games absolutely. But does it improve the overall experience of the phone in the same way that adding any of the above features or increasing the screen size would? Probably not.
    Reply
  • Hoggleboggle - Tuesday, October 11, 2011 - link

    You might want to re-run the score on the Galaxy S2. I just ran Sunspider 0.9.1 on my stock (international version supplied by THREE) Rom with stock browser and got a score of 3372ms, well below the figure you have listed. Reply
  • Fysi - Tuesday, October 11, 2011 - link

    I ran it in Opera Mobile and got 1619.2ms Reply
  • Lucian Armasu - Tuesday, October 11, 2011 - link

    Anand, if you want to show "CPU performance" by using the JS benchmark, it would probably be best if you used a more current 3rd party browser like Opera Mobile or Firefox or Dolphin HD. But if you just want to compare the browsers, then using the stock browser is fair. Reply
  • Brian Klug - Tuesday, October 11, 2011 - link

    You're comparing SunSpider 0.9.1 to our 0.9 (for legacy purposes) results. We will be switching to 0.9.1 as soon as we have some more data (else the graph will be very small).

    -Brian
    Reply
  • Fysi - Tuesday, October 11, 2011 - link

    I got 1639.6ms +/- 3.8% in Opera Mobile on my SGS2 using 0.9 Reply
  • palehorse - Tuesday, October 11, 2011 - link

    I wouldn't mind seeing a chart built with all available browsers on both platforms; however, it should probably wait until after ICS gets released.

    ALL available iOS5 and ICS browsers, as well as the Prime vs. iPhone4S, are the Q4 2011 benchmarks I really want to see...
    Reply
  • Commodus - Tuesday, October 11, 2011 - link

    As has been pointed out, Android 2.3 won't use a second core in the browser... so many phones have been working with an arm tied behind their back thanks to Google.

    Android 4 (ICS) hopefully fixes that, but here's where fragmentation takes Android down: you now get to play the guessing game as to when Samsung, or HTC, or Motorola bothers to upgrade your phone, if at all, along with any separate carrier checks. If ICS does use extra cores, the Nexus Prime and their kind will show it, but you still have to buy a new phone.

    In the meantime, the iPhone 4S user will still have the practically faster device, and if there's any extra speed to get out of the code, he'll get it without having to wait for an intermediary. Something to be said for having speed in practice versus speed in theory.
    Reply
  • Fysi - Tuesday, October 11, 2011 - link

    'If ICS does use extra cores, the Nexus Prime and their kind will show it, but you still have to buy a new phone.'

    But you would have to buy a new phone to get the iPhone 4S....

    So I don't exactly see your point there.
    Reply
  • Commodus - Tuesday, October 11, 2011 - link

    Apologies. The issue is that a lot of Android fans have presumed that the dual-core phones they bought earlier, such as an Atrix 4G or a Galaxy S II, were automatically better -- both because they see higher clock speeds (didn't we settle this debate a decade ago?) and because, quite frankly, they assume that anything using Android has to be better than what Apple makes.

    Moreover, because of the lack of software optimization on Android, the iPhone 4 from 2010 is in many cases as fast in its browser as a dual-core gigantic Android superphone released just a couple of weeks ago.
    Reply
  • Bozzified - Tuesday, October 11, 2011 - link

    LOL at blinders. No... every single Android phone that was released in the last couple of months have destroyed iPhone 4.

    iPhone 4S is not an amazing piece of hardware. Most of the improvements we see here are purely based on iOS improvements which all phones from a few months ago on Android will get with Ice Cream Sandwich. Surely not all of them are "superphones" so they won't be the fastest but it's without a doubt that with Ice Cream Sandwich we will see huge performance gains on Android, just like iOS 5 is doing to iPhone 4S.
    Reply
  • KoolAidMan1 - Wednesday, October 12, 2011 - link

    Android BADLY needs performance optimization as it is still choppier than both iOS and Windows Phone 7 on slower hardware. That aside, the PowerVR GPU in the A5 is still better on paper than anything in the current Android SoCs. I'd call that superior hardware, wouldn't you?

    Tegra 3 is already looking like too little too late. By the time it drops will be around the time when the A6 is out. If it isn't a serious leapfrog then this current pattern will continue.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    The Galaxy S II is not choppier than competing devices, at least with the Exynos versions. It zooms webpages in and out while loading Flash, pretty much the most difficult thing to do in web browsing (watch some videos from PhoneDog or some sort). iOS doesn't even attempt to load Flash. I do not know of any Windows Phone device that accomplishes that feat.

    That said, Android optimization would be lovely.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Cling to flash support as the 1 negative which gives iphone users their superior battery life Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Lets just guess, shall we? Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    “…so many phones have been working with an arm tied behind their back thanks to Google.”

    No, let's be clear: Google gives the OHA software that they can modify, and then the OHA member sells a particular package to a carrier, which sells it to you. You don't like what you got from Verizon? Go bitch to them. They could've demanded that Samsung produce a high-capacity product, and, in turn, Sammy could've said something like not selling any phone before it was ready, and turned the screws on Google for a competitive product.

    Trouble is, all along the line, everybody was more interested in a sale (or a pair of eyeballs hitting Google ads) than performance. This oughtn't be just HUGELY surprising, or did somebody think that Verizon, Samsung and Google are all charities?
    Reply
  • Swapzzz - Tuesday, October 11, 2011 - link

    Very good way to market Iphone.... Totally Bias .... I can make a graph my self put some other phone on top .... And as far as I see No wonder Oracle ( JAVA) Has a law suit against the Apple guys .... (Love the innovator Steve jobs ) But hate these cheap marketing strategies......
    There are far better processors and phone in the market Iphone is definitely one of them but by far not the best !!
    Reply
  • steven75 - Tuesday, October 11, 2011 - link

    You sound like a guy that would show up at a drag strip and declare your V12 engine "better" than the guy with the V8 that just posted a faster time than you.

    The end results are all that matter.
    Reply
  • Swapzzz - Wednesday, October 12, 2011 - link

    Well I thought V12 engine are better that V8 Hmmm lets see ... I believe its the driver that matters ... and fanboy you definetly suck at Cars.... As far as Andriod goes Fanboys can fight it out as much as they want I would say APPLE is already being eaten.... You like it or not thats the fact Market stats is the fact.

    http://www.engadget.com/2011/10/06/comscore-androi...

    Remember, You fanboys are stuck with 1 similar looking piece globally. Where as Andriod is a open source platform much more customizable than any Iphone and andriod can make use of the resources provided to it.
    Reply
  • KoolAidMan1 - Thursday, October 13, 2011 - link

    Enjoy slower performance, weak developer support, and no enterprise support on your "open" platform.

    You throw the "fanboy" word around quite a bit for someone who ignores raw performance data and where the real developer support is.
    Reply
  • Swapzzz - Thursday, October 13, 2011 - link

    lol .... You have no clue what your are talking about you NOOB ! My phone can kick any "IPHONE" in the market Oh guess what ... My phone can be overclocked .... can your be ? ummmm,..... NO!

    So think before you speak of what you donot know .
    Reply
  • lurker22 - Sunday, October 16, 2011 - link

    Wow, you sounds like a 8 year old. Did you really write, "my phone can kick your iphone" ?

    Get a life. It's just a smart phone.
    Reply
  • jwcalla - Tuesday, October 11, 2011 - link

    Is it wrong of me to be skeptical of these benchmarks that show the 4S being a zillion times faster than any other phone on the market? Reply
  • uhuznaa - Tuesday, October 11, 2011 - link

    We should wait a few days for the thing being delivered and reviewed before fighting about that.

    Still, the iPad 2 also is faster than any other tablet on the market. I wouldn't be much surprised to see the 4S being quite fast also. And of course Android 2.x only utilizing one core anyway explains a lot of this. Ice Cream Sandwich should change this sooner or later.
    Reply
  • Lucian Armasu - Tuesday, October 11, 2011 - link

    Faster at what? graphics performance? You don't use that for most things. You use CPU performance, and that's about equal. If there's a difference in browser performance, then that's all software.

    I really hope Anand and Brian clear this up when they do the iPhone 4S review. They've started a wave of misinformation on the Internet because now everyone thinks that because of that JS test, the dual core 800 Mhz A5 CPU is twice as fast as the dual core 1.2 Ghz Exynos, when it couldn't be further from the truth. They are both Cortex A9, plain and simple, and the Exynos is clocked 50% higher so it should be 50% faster. If that doesn't translate into benchmarks, then the difference is coming only from the browsers being used.

    So if they really wanted to check CPU performance, they should've used other browsers, and not compare a brand new iOS browser with what is basically a 18 months old stock Android browser, that doesn't even use both cores. I can't believe the amount of misinformation this has created online. It's huge, and it's a shame, because it's not the real truth.
    Reply
  • uhuznaa - Tuesday, October 11, 2011 - link

    Come on, the dualcore PowerVR GPU in the A5 just wipes the floor with everything you get in other smartphones currently. And in iOS all (or most) of the UI runs on it. It's fairly obvious that this iPhone will be fast, very much as the iPad 2 with the A5 is fast.

    And yes, the CPU won't be faster than others, even slower due to running only with 800 MHz. It's just that currently with Android 2.x on Android phones these are not as fast as they could in the browser since the OS basically has the browser only run on one core.

    God, can we have a reasonable discussion here, please? The 4S won't be twice as fast as the SGS2 (at least not as soon as it gets ICS), but it also won't be slower with all that GPU power.
    Reply
  • 00DC2TW - Tuesday, October 11, 2011 - link

    yeah all software, which clearly proves the point that specs don't matter, and the consumers don't care about specs, if you optimize your software, your hardware specs can be lower, which in turn saves money and reduces power consumption Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    “Faster at what? graphics performance? You don't use that for most things.”

    Yes, absolutely true: graphics performance only matters on the *ONLY* thing that's actually very performance-sensitive on modern smartphones, hi-res games.

    Of course, AnandTech readers occasionally like to play games on their various devices, no?

    I'd say Apple has a triple advantage on that: (1) the A5's GPU hardware looks pretty fine against what else we see today; (2) Apple has a couple years' advantage in optimizing their core graphics libraries for particular GPU designs; and (3) Apple game developers don't have the performance penalty of dealing with java, even JITted java and its garbage collection.

    You could look at other real-world issues such as Android fragmentation — developing hi-res games is especially sensitive to screen dimensions — and monetization issues, too, but while that's a big deal about the actual user experience with getting and enjoying good games, it's not actually Anand's focus. It DOES, however, reinforce your point that today, Apple has a very sweet *combination* of hardware and software, and just the next release of Android is not likely to address the issue.
    Reply
  • Swapzzz - Wednesday, October 12, 2011 - link

    "I'd say Apple has a triple advantage on that: (1) the A5's GPU hardware looks pretty fine against what else we see today; (2) Apple has a couple years' advantage in optimizing their core graphics libraries for particular GPU designs; and (3) Apple game developers don't have the performance penalty of dealing with java, even JITted java and its garbage collection."

    HAHAHAHAHAHA !!! OMG i cant stop Laughing.

    Wake Up !!!
    Reply
  • tipoo - Tuesday, October 11, 2011 - link

    Not really. Android is built for a wide variety of hardware, so unlike Apple they can't make a full out push for dual core optimization exactly when the hardware is available, so the software lags a bit. Plenty of dual core Android phones, but the browser probably isn't using the second core since most Android devices are still single core. And improvements like this in browser scores through software updates are hardly unheard of, the iphone 4 used to get above 10,000MS in Sunspider, as did phones like the Nexus S but that changed with optimization. We'll see if ICS makes better use of multicore. Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    “Android is built for a wide variety of hardware, so unlike Apple they can't make a full out push for dual core optimization exactly when the hardware is available, so the software lags a bit.”

    May I fix that for you?

    “When you buy a particular Android device, you pretty much know it'll be a cobbled-together combination of some generic OS design, hardware that wasn't known to the OS designer *OR* the app developer, and was then sold thru a carrier that doesn't give a rat about anything other than signing you up for two years' worth of $79/month plus fees.”

    Besides seeing whether ICS makes better use of multicore, it'll also be interesting to see whether Google's promised tighter control over the OHA means that upgrades get to users faster than they did in the past.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    Eh. Just speaking of the flagship Galaxy S II, Samsung does just fine at integration. They also happen to be the world's largest mobile phone manufacturer. Anyway, they use Google's OS and value-added services, their in-house top-notch TouchWiz interface, their in-house top-notch processor, their in-house top-notch screens, their in-house memory.

    Samsung actually makes more of the phone themselves than Apple does. Actually, as far as manufacturing goes, Samsung may make more of the iPhone than Apple does. Just saying...
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Yet they still can't create a phone as good as the iPhone 4S, without infringing copyrights.

    /Fail
    Reply
  • tnrmem - Tuesday, October 11, 2011 - link

    Thanks for the reply. Yes, my quoted value of around 1750ms is based on a third-party browser (Dolphin HD) on the latest version of CM7 (currently on Android 2.3.7). I'm also sporting an international SGS2 (i9100) version. Using the stock Android browser to run SunSpider yields a slighter higher time of around 1800ms.

    But now that you mentioned it, I am getting these values using SunSpider 0.91 instead of your 0.9. I did the tests again and got a higher value of 2466ms, which may explain the rather large disparity of the original results.

    I also managed to secure an unmodded SGS2 from a friend to run the same tests. The same i9100 version runs on stock 2.3.4 UHKG7 with all the original bloat and more. Running SunSpider 0.91 on stock browser produces a value of around 3200ms so I guess your 4000ms+ result might be plausible on the previous 0.9 version. I am rather surprised with these values as I didn't notice much difference in browsing performance (and speed in general) between CM7 and stock ROMs. Sadly, I didn't get to test the BrowserMark scores as the website seemed to be overloaded then.

    I don't really know what to make of these values or what they are dependent on, but I am curious about the large disparities especially when compared to the new iPhone (given the hardware on both are pretty similar except GPU). I love all your articles by the way. Keep up the good work!
    Reply
  • steven75 - Tuesday, October 11, 2011 - link

    Why would a review site compare a stock iPhone vs a rooted and rom'ed Android phone?

    That would make no sense.
    Reply
  • Aikouka - Tuesday, October 11, 2011 - link

    I think it would be interesting to see stock Android vs. homebrew Android. Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    What do you think it would show? That Samsung is incompetent? That 3rd parties can optimize JavaScript if they don't have to worry about playing nice with RAM or other tradeoffs that the most-frequently-used app has to do?

    I hear tell of various “security” features built into stock OS distros, but I wouldn't think javascript performance would be the first place you'd expect to see a performance hit.
    Reply
  • mongo lloyd - Tuesday, October 11, 2011 - link

    Latest stock in Kies for the international version is KI8 (2.3.5) from last week. Reply
  • germz1986 - Tuesday, October 11, 2011 - link

    My sensation gets 2500 @ stock clocks and 1915 @ 1.5ghz, which is the stock clocks for the Sensation XE. Lets have a little less apple fanbio'ism Reply
  • Swapzzz - Tuesday, October 11, 2011 - link

    totally agree! Reply
  • steven75 - Tuesday, October 11, 2011 - link

    Using stock browser and ROM? This is supposed to be a comparison test after all. Reply
  • Tomne - Tuesday, October 11, 2011 - link

    Iphone 4 here : 4505 (0.9)
    Samsung Galaxy S : 3182 (0.9)

    Beating the SGSII seems a little too much. How about some real numbers Anandtech ?
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Why would it seem too much?

    The iPhone 4S is faster.
    Reply
  • enterco - Tuesday, October 11, 2011 - link

    Anand, I see you associate the SunSpider Javascript Benchmark with the device. I'm not so sure that the browser used should be omitted.
    I've made a test on my device, and I found that a third-party web browser (Opera Mobile) is the fastest browser according to this benchmark, two times faster than the browser included in my Android device. I didn't made any tests with Firefox (mobile version), it's too slow for me.
    Reply
  • hlovatt - Tuesday, October 11, 2011 - link

    It seems like you are really trying very hard to make Android look good! You said you expect the next version of Android "to narrow the gap" and in a couple of charts show a Galaxy tablet in comparison to phones and don't show an iPad for comparison in these.

    Why not just say: "It is the fastest phone money can buy - bar none."

    Personally I prefer your reviews when you states the facts and let the numbers do the talking rather than attempt to provide "false" balance where the journalist feels it necessary to say something nice about everything.
    Reply
  • FATCamaro - Tuesday, October 11, 2011 - link

    This. There is no reason to bring tablets into this. When you show the Galaxy 8.9 you don't show the ipad 2. Trying to protect Android are we? Reply
  • Anand Lal Shimpi - Tuesday, October 11, 2011 - link

    The GTab 8.9 was only included to show the performance from the latest Android browser code. The iPhone 4S already has that benefit, Android on the smartphone side does not. For the browser performance results this is as much an SoC comparison as it is a software comparison, which is why I wanted to put that reference out there.

    We weren't trying to protect Android, we were simply trying to provide the data necessary to support our discussion (if we were trying to protect Android we probably wouldn't have included the GLBench numbers :-P).

    Take care,
    Anand
    Reply
  • Invid - Tuesday, October 11, 2011 - link

    I understand the logic behind adding the GTab 8.9 to the chart. What I can't understand is the logic behind omitting the iPad 2 from the chart if you add the GTab.

    How can any meaningful comparison be made between the browser codebases when you ignore the 20% clockspeed deficit of the iPhone 4S? If you include the GTab, you should also include the iPad 2 running the same code as the 4S, but most importantly, at the same clockspeed as the GTab.

    That's why it looks like you're favouring Android...you're not comparing like vs. like. You even touched on it in the body of the article when you mentioned that the iPhone has tighter battery constraints than the iPad 2 which explains the lower clock, but when it comes time to benchmark, those constraints are no longer important?

    I was disappointed to see the lack of objectivity indicated by your choice of benchmarks. Oh well, at least it finally got me to register to complain about it.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    It's the same exact thing they did in earlier reviews, where the A5 in the iPad 2 was thrown in to a huge list of smartphones. The result was that people were taking the A5 in the iPad to mean that the A5 in the iPhone 4S would be that fast. Which isn't accurate.

    I don't think an unrelated product from a different market should be thrown in to the charts for smartphones. It is deceptive because many people won't bother to think before they interpret the data. If you want to include it, don't put it in the chart, which gets linked everywhere on the web. Just mention it in the text somewhere. And most importantly, explain it.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    So, you agree with his point then, that the Galaxy tab shouldn't be there?

    People didn't think the A5 in the iPhone 4S would be as fast as in the iPad 2 - but they knew it would be proportional to clock speed and that the underclock wouldn't be significant enough to take it below the < 50% performance of the Galaxy S2
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    You should include iPad 2 Reply
  • Tomne - Tuesday, October 11, 2011 - link

    Well, read th other comments on this topic. You'll see that the numbers aren't what they really are. The benchmarks are not accurate at all. Reply
  • doobydoo - Sunday, October 16, 2011 - link

    They are accurate, it's just the fandroids don't like them. Reply
  • kebab77 - Tuesday, October 11, 2011 - link

    http://www.bestsmartphone.com/2011/09/26/javascrip...

    ... very different numbers, also nicely shows the difference between stock browsers and 3rd party browsers.
    Reply
  • Anand Lal Shimpi - Tuesday, October 11, 2011 - link

    We've corrected the numbers above :)

    Take care,
    Anand
    Reply
  • kebab77 - Tuesday, October 11, 2011 - link

    Check out these figures ... I get very similar ones on my S2:

    http://www.bestsmartphone.com/2011/09/26/javascrip...
    Reply
  • Chudilo - Tuesday, October 11, 2011 - link

    iOS has a GPU accelerated UI.
    Android's browser / JavaScript performance will not be anywhere near those scores until they move the Browser interface itself off to the GPU.

    As of right now Google is denying that it is something that is needed for the android OS.
    Reply
  • shompa - Tuesday, October 11, 2011 - link

    This is the difference between a "closed" and "open" platform.

    30% of A5 die area i NEON SIMD/Apples "visual engine". Apple can accelerate its OS with these instructions since they control the graphic layer on the phone. Android can't do this since Google does not control the graphic layer.

    This is one of the reasons why A4 class devices only have been 5-10% slower then dual core Android phones.

    Microsoft WinMobile takes the middle road between Apples "closed" system and Googles "open" system. MSFT have locked down what hardware telephone manufactures can use. Therefore they can accelerate the OS with GPU/SIMD.

    It is also fun reading this thread.
    Androids browser scores are so bad because 2.3 only use one core?
    Apples scores are to good to be true?
    "Samsung" CPU inside A5? (no. A5 is designed with ARM cores by Apple. A5 is 30% larger then Tegra2. Apple can use this area for better memory interface, NEON SIMD and other stuff.

    "I want LTE". Why have 50 megabit on your phone? Downloading blu rays to it?
    "The 3G spectrum is to crowded" No. This is not the problem. This is a USA specific problem since AT &T only have 1/3 of the Cell density they should have. (I worked at Ericsson radio system who supply base stations) This is the reason for poor reception, dropped calls. AT&T tells us that they don't get building clearance for more towers. Maybe true. But AT&T also saves billions by only deploying 1/3 of the recommended base stations. If any phone company does the same with LTE, you will have the same problem"
    LTE telephones today have 50% less battery time. With 28 nm manufacturing LTE will have same battery time as 3G. This is also the reason why iPhone 5 was not released. The iPhone 5 late prototypes are ready. (teardrop design). When TSMC gets its manufacturing on track, Apple finally can technically release the Iphone5.

    Tegra3 to the rescue? Yes. Tegra 3 had been interesting if it was released in August as planned. Now its late Q4. How fun is it with quod core on 45nm? Cortex9. 50% less battery time if clocked at the same speed. Early next year we are going to have good 28nm quod core with ARM15. About twice the performance of Cortex9.

    I also hope that this article open peoples eyes. 1.5ghz is not always faster then 800mhz. It is about CPU/GPU design + how the OS work. Same with cameras. More megapixels does not mean better pictures.

    Tech nerds seems to believe that. PC home builders and Android rom optimizers. Something that 95% of the marked does not care about.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    I hate to break it to you, but the A5 most certainly is made by Samsung. Maybe in the future it will be TSMC. But it will never be Apple. Reply
  • doobydoo - Sunday, October 16, 2011 - link

    No it isn't. It's an Apple designed chip. Reply
  • palehorse - Tuesday, October 11, 2011 - link

    Please wake me up when you have:

    1) ICS vs. iOS
    2) ALL available browsers for both platrforms
    3) Nexus Prime vs. iPhone4S

    Until then, the benchmarks are practically worthless, and they're absolutely biased!
    Reply
  • steven75 - Tuesday, October 11, 2011 - link

    How are they biased? You can get a 4S in 6 days and iOS 5 tomorrow. Prime hasn't even been announced yet and ICS won't be on Android phones other than Prime for another 6-8 months.

    Sometimes reality isn't what you'd like it to be, but there it is.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    ICS will be on several phones by the end of the year. Samsung and Google won't announce ICS this month without releasing a phone to go along with it. And the rest of the phone manufacturers won't sit around twiddling their thumbs while Samsung steals all the glory. It will likely be a matter of weeks between the first phone and the second. Not "6-8 months". Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Still doesn't exist yet. Which is the point. Reply
  • DuduMaroja - Tuesday, October 11, 2011 - link

    Sorry but my galaxy S2 is faster then this

    http://i.imgur.com/tMeDX.png

    ps: not overclocked!
    Reply
  • tomhoward - Tuesday, October 11, 2011 - link

    Glad it's not just me :-) Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Depends on the browser. It's probably identical if you used the stock browser.

    All phones would be quicker if they switched browser. So the results are still reflective.
    Reply
  • doubledeej - Tuesday, October 11, 2011 - link

    Why no WP7.5 Mango phones on this chart? It would be nice to see how its browser stacks up. Reply
  • vrundmc - Tuesday, October 11, 2011 - link

    Just ran SunSpider on my Epic Touch 4G - stock - and came up with 2332 using Dolphin. Meh. I would rather have a GS2 over an iPhone anyday...I have used them extensively and prefer the Google experience and integration. Reply
  • mscrivo - Tuesday, October 11, 2011 - link

    I just ran SunSpider 0.91 on my Bold 9900 and it scored a 2609ms overall score, puts it in second place right behind the iPhone 4S. Reply
  • adrien - Tuesday, October 11, 2011 - link

    You're right that they can use V8 which makes sharing code and improvements everything but obvious.

    But, independently of that, I'm sceptical because of the 2x boost. It's "too good to be true". I'll be waiting for the full reviews. ;-)
    Reply
  • mojojojom - Tuesday, October 11, 2011 - link

    Why have you left out the iPad 2 from the first benchmark? I find this very irritating.

    In any case, this particular screenshot is doing its round all around the web including Engadget and I think you should put the iPad 2 numbers there just as you did for Samsung Galaxy tab. The Android enthusiasts are pointing out how Android beat iOS.
    Reply
  • jwcalla - Tuesday, October 11, 2011 - link

    Yeah I've noticed teh interwebz are aflurry with the big news that the 4S destroys everything on the planet, linking back to this article. But I don't know that there is much we can really conclude from the benchmarks provided here. The first two are just browser benchmarks I guess?

    My Samsung Fascinate scored just under 7.5s on the SunSpider test, and the only difference between mine and the one in the chart is that I have the 2.2.2 OTA update. So how can any conclusions about the hardware be deduced from these charts when identical hardware can be off by a full magnitude?

    Aren't there better benchmarks out there that actually measure processor performance?
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    The CPU/GPU results are pretty conclusive. Reply
  • vision33r - Tuesday, October 11, 2011 - link

    Android is just a platform to attract the wannabee geeks with big hardware numbers like GHZ and GB but across the board OEM use hardware that does not dramatically improve performance.

    1.5GHZ phone that gets outperformed by a phone with almost 1/2 the mhz.

    Almost all Android phones out uses inferior GPU.

    Oh yea, Android need 1GB of memory because all your widgets are memory sucking.

    Google is just a bunch of advertising geeks not real software gurus. Android is still beta.
    Reply
  • Sind - Tuesday, October 11, 2011 - link

    What a totally clueless comment. If you had any iota what you were talking about you would understand the bias involved in these benchmarks, especially versus real world use. Responding to any further of your drivel is pointless. Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    It's been a while since I've been to a real-world website that got bogged down because the idiot designer filled it with robots chasing eggplants or whatever, so I *kinda* get your point.

    Perhaps you'll respond to my non-drivel: what performance benchmarks indicate how smooth and even speedy a phone is?

    I dunno how you'd test smoothness of scrolling, pinching, etc., but I'm gonna guess that if that was OK on any phone since Froyo, it doesn't matter much today on the high-end phones.

    I think the graphics benchmarks are more relevant: gaming is moving to iOS big time; the iPodTouch may be the most common handheld gaming device today.

    Anyway, go ahead & suggest some benchmarks that AT ought to use, or that you prefer. I don't think you'd be 3 pages down in a discussion about benchmarking if you didn't have some thoughts.
    Reply
  • deV14nt - Wednesday, October 12, 2011 - link

    Personally I'd go to YouTube and watch side by side videos of browser performance while pinch-zooming. Galaxy S II with Exynos is much smoother than any other Android phone on the market. The old phones you're talking about definitely are not smooth when playing Flash. iOS doesn't play Flash at all so I don't really know how to compare it in the "real world." It's...disqualified. That's all I can say. Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Broken... Record... Flash.

    Cling to flash support which can be achieved through apps, we'll continue to enjoy our faster phone with better battery life.

    You can have flash support, we'll have flash support and a better phone.
    Reply
  • morphon - Tuesday, October 11, 2011 - link

    Interesting results, considering they are testing the entire hardware and software stack.

    Just for comparison, I ran the sunspider benchmark on my Gingerbread-equipped Optimus 2X (G2X on Tmobile). I use the Opera browser - and it delivered a clean 2200ms. The DolphinHD browser, which uses the standard web rendering system, only delivered 4010. Now, I realize that the Tegra2 has a 200mhz advantage against the 4S's A5, but in basically stock configuration, the Tegra2 will deliver similar browsing performance to the A5, provided you use a browser that can take advantage of both cores.

    The bigger difference will be in 3D performance. The GPU on the A5 looks pretty beefy.
    Reply
  • seanleeforever - Tuesday, October 11, 2011 - link

    hi Anand.
    you have to standardize the test. i am getting HUGE differences using different browsers. why not run all the test using the same browser (i.e. Opera Mini, since it is available for both andriod and ios).

    case in point, my n900 scored 21631 with default browser, but just over 9000 with opera. i suppose this doesn't mean my hardware suddenly went from 900 Mhz to 2 GHz.

    use some sort of standard, and re-run all the test to give us a more accurate performance.

    thanks
    Reply
  • mzinZ - Tuesday, October 11, 2011 - link

    He is using stock OS's and default browsers because that is what 99% of people use. Reply
  • seanleeforever - Tuesday, October 11, 2011 - link

    except most people use browser other than stock.

    and that's the questions. why not use a standard browser, like opera, to test stock OS , stock phone across the board?
    Reply
  • uhuznaa - Tuesday, October 11, 2011 - link

    Most people use other browsers than stock? Really? I doubt that very much.

    And there IS no common browser available on both platforms. Opera Mini is not a browser at all, it renders on Opera's servers and sends the results back.

    Comparing stock browsers on a stock OS as delivered in a phone you can buy is just the only sensible thing you can do.
    Reply
  • seanleeforever - Tuesday, October 11, 2011 - link

    wasn't long ago Opera was the number 1 download app across the globe in every single country for idevice. you should probably google that.

    you have a point for the opera mini, i suppose opera mobile is a better choice for the test.
    Reply
  • andynormancx - Tuesday, October 11, 2011 - link

    Opera Mobile would be a lousy choice for the test, because it isn't even available on iOS. Reply
  • kmmatney - Wednesday, October 12, 2011 - link

    Yeah - a lot of people like me downloaded Opera, tried it a few times, and then went back to Safari... Reply
  • doobydoo - Sunday, October 16, 2011 - link

    So what if Opera was the number 1 downloaded app?

    Most people still use the stock browser.
    Reply
  • frijo84 - Tuesday, October 11, 2011 - link

    I'm liking this community and comments posted, I don't know if its because you delete the endless fanboy babble (on both sides), but alot of this is a good civil discussion, without meme's or namecalling, good info all around!

    I'm a long time reader, I think since the AMD Athlon Thunderbird days if I remember right. Great article, and I look forward to the full teardown and review this upcoming week, I'm in a tough spot deciding on whether or not to upgade or hold on for a prime. I'm in a Sprint WiMax area (Overland Park actually, right by Sprint HQ!), but with the announcement of going to LTE (and 2 years till that), my Evo isn't cutting it anymore, need more RAM and actual hard drive space, without relying on SD cards. 32GB iPhone looks like a good choice for my mobile multimedia use so far, but the Evo has been pretty good to me, so I'll give the Prime a chance to shine too! Either way, with all these smart phone wars going on, the only ones that really win are the consumers, alot of good choices.
    Reply
  • DerekMorr - Tuesday, October 11, 2011 - link

    ARM has submitted several patched to V8 to improve performance - http://blogs.arm.com/software-enablement/456-googl...

    That blog post was from April 2011. It claims "It takes a few months of work for Google to integrate and test the latest V8 engine with new devices, so you will not be able to see these performance improvements appearing in products until the second half of 2011." So I suspect that these improvements are not part of Honeycomb, but will be in ICS. It will be interesting to see ICS's Javascript performance.
    Reply
  • kebab77 - Tuesday, October 11, 2011 - link

    Brian, this article has #fail all over it I'm afraid.

    The video you took the iPhone 4S sunspider scores from clearly show they used Sunspider 0.9.1 so you can't - by your own admission - compare them to the 0.9 results you already have.

    You should be comparing the iPhone 4S score from the video with others using 0.9.1 like here: http://www.bestsmartphone.com/2011/09/26/javascrip...
    Reply
  • Anand Lal Shimpi - Tuesday, October 11, 2011 - link

    Thank you for the heads up, a definite mistake on our part!

    We have updated the article to use our 0.9.1 results.

    Take care,
    Anand
    Reply
  • name99 - Tuesday, October 11, 2011 - link

    Anand, might I suggest some changes in how you benchmark future phones/tablets?

    Right now you are (IMHO) measuring a bunch of stuff that is not important to many people, and not measuring stuff that is important. Specifically, when I use my iPad (and to a lesser extent my iPhone) what I notice as slow is pretty much the same stuff that used to be what caused PCs to fell slow --- app launching and IO. But you have no benchmarks that measure these.
    The lack of IO benchmarks is especially strange coming from THE SSD web site!

    So let's think about this.
    Measuring IO is, ultimately, not hard --- you simply need an app that reads and writes a bunch of data. Of course someone has to write the app(s). I suspect this will not be too hard if you ask around --- a benchmark app would be a good "my first app" for anyone trying to learn iOS/Android/WP7 programming. Even in the absence of such an app, you can get a feel for the write speed of flash by observing sync behavior. My experience, for example, has been that Apple has slowly ramped up the write speed of their flash from around 4MB/s in my first gen iPod nano, to 6 in my 3rd gen nano, to around 12 in my iPhone1 to around 18 in my iPhone4 and iPad1. Eyeballing the speed of a sync (say in syncing a few large movies to a device) is not the greatest way to benchmark, and it's not going to reveal the difference between a flash write speed of 18MB/s and 19MB/s, but it does at least give one an initial feel for how much faster the device will be (for this type of write operation) than what one might have used before.

    Launch speed and suchlike are harder. One could be dumb and measure boot speed but, honestly, no-one gives a damn --- people reboot their phones what, once every six months or so. And you have the OS matching problem.
    My solution is not ideal but, again, maybe is a start.
    We argue that the browser is a common app across all platforms, and one people care about. So we
    - manually quit the browser (and every other app) on the device
    - power it off
    - power it on again and leave it a minute or so to do its startup things
    - START THE CLOCK
    - start the browser with a URL that points to a very simple web page --- say a simple paragraph of text (I think, one way or another, all the browsers have a way you can launch them with a URL).
    - wait for the text
    - STOP THE CLOCK

    The point of the URL and the text is to try to get around the problem of "when is the browser really launched" given that they all throw up splash screens and show UI before they're really alive.

    One could imagine similar tests with other common apps. For example, with a movie player, quit the movie player manually while it's part way through a movie, then restart it and time how long till the movie is playable again. Another common app where you could do this is music playing.

    I expect the first round of timing tests like this will reveal a bunch of complaints from partisans --- "you forgot that if you launch Safari in this way it is extra slow", "it's not fair to launch Android Video Player on that movie because most Android movies follow this spec which can use built-in HW, and that movie does not follow that spec", etc etc. But you (and all of us) will learn, and I think something useful will come out of it.

    Certainly, for example, I love my iPad1. But I'm not so deluded as to claim that it is perfect. App launches are slow enough to be irritating --- especially so in the case of Videos and iPod --- which are both especially bad because they seem to be large enough that they're never retained in memory when switching to another app. Is this fixed in iPad2? Are Android devices as bad? Will Win8 tablets likewise be slow in app launching? I've no idea, but, honestly, that's the sort of thing technical reviews like yours should be telling us.
    And do these numbers get worse with time as flash is filled up then items are deleted? How much worse? Do different OSs do a better or worse job in their flash GC? I don't know --- do you?

    Truth is, personally I've very little interest in how many fps my iOS devices can deliver when playing games --- they have enough fps for all my needs. But I DO care about the places where a device pauses and makes me wait --- and a decent set of benchmarks should INFORM ME about those delays.
    Reply
  • name99 - Tuesday, October 11, 2011 - link

    "Apple's ability to control the entire information chain, down to the point of limiting leaks, appears to be gradually slipping as it grows as a company. Case in point are the numerous hardware and performance leaks surrounding the newly launched iPhone 4S. "

    I love you guys, but, seriously, this is just silly.
    A whole bunch of unsubstantiated rumors, plenty of which were wrong, does not count as a "leak". What about all the iPhone 5 claims? The supposed larger screen? The tapered pearl design?
    If there had been any sort of serious leaking of the iPhone4S specs before the launch, we would not have seen the spectacle, on launch day, of a million commenters telling us all how "disappointed" they were with the device --- they would have vented their "disappointment" in the weeks before the launch, and on the day would have been sullenly telling us all how right they were.

    (But apart from that, great article --- thanks for the round up of the numbers, though, as I said in my previous comment --- we need IO numbers as well --- and heck, a test of the BT4 behavior would be nice if you can find some BT4 equipment to pair it with!)
    Reply
  • Sind - Tuesday, October 11, 2011 - link

    Not a huge fan of the article as I believe it is flawed. There is no doubt however that the 4S has some beef, but negating to even mention ICS or other options available now to Android users (different browsers, custom roms) doesn't do a consumer whom is looking for information any justice and seems more so like marketing. For instance my custom ROM at stock speeds with the stock browser on my Nexus S 2.3.7 gets 3964 in Sunspider. Failure to mention Googles goal to get a grip on fragmentation starting with ICS and the likely hood it will be showing up in the next month with a new phone on top of that does not help consumers and only Apple with this article. Got some page hits though right. Reply
  • Anand Lal Shimpi - Tuesday, October 11, 2011 - link

    I believe we clearly mentioned that ICS should narrow if not eliminate this gap entirely, which was the point of including the Honeycomb result in the chart as well - to give a bit of a preview.

    Take care,
    Anand
    Reply
  • Captainobvvious - Tuesday, October 11, 2011 - link

    Why stop there? Why not compare the iPhone 4S to next year's iPhone?

    ICS nor the Prime are released yet so why should they be compared? If you hack the hell out of your phone it MIGHT do slightly better, should they account for every configuration?

    Stock vs. Stock... Sorry but that's the way it is.

    You want to manipulate the results to somehow benefit the device you plunked your money down for. When the Prime and ICS is released (or in the case of the Prime... Announced!!!) then maybe it will be faster, until then it isn't.
    Reply
  • jwcalla - Tuesday, October 11, 2011 - link

    Stock vs. stock browser is about the only thing you can compare with the first set of benchmarks. You can pretty much draw no conclusions about the performance of the hardware.

    The GL benchmarks are more interesting and also more believable considering what we know about the PowerVR... but who knows how equitable 720p offscreen benchmarks are, especially for GPUs used in phones designed for SD.
    Reply
  • morphon - Tuesday, October 11, 2011 - link

    I agree with the GL benchmarks being the more important part. I don't know of that many games that are available and properly optimized for both, but that might be an interesting thing to figure out/investigate.

    However, Stock vs Stock is a little... odd.

    Anyone who cares about browser performance on a dual-core Android device is probably running Opera Mobile anyway. It's solid, has excellent desktop sync, and very good Flash integration. It's not a mod, it's a recommended download from the Android Market and is free. You can just assign Opera to be the default web browser when it asks and bravo - done. Dual core performance. As I mentioned earlier, my non-overclocked, non-modded G2X (Tegra2, 2.3.5) running Opera gets the same Sunspider score as the iPhone 4S.

    Thing is - it's NORMAL to run a different browser on Android. Everyone I know is running DolphinHD, Opera, or XScope. It's like putting Chrome on your desktop. Not a mod. Normal behavior. Just testing against the stock browser gives a non-representative result. Doesn't reflect the real world.

    But I am totally on board with your second paragraph. Gaming performance is going to be the real test. If the A5 allows game developers to do more/better than what ships in the current Android superphones, then that's where the time and effort will be spent.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Well, hold on a bit there my Android - biased -friend. You can't then take a specific downloaded browser for Android and then compare it to the STOCK iphone browser, now can you?

    That would defeat all of your own logic.

    If you did do that, the iPhone would be faster again.
    Reply
  • WaltFrench - Tuesday, October 11, 2011 - link

    Obviously, a lot of the commenters here have already sent off their check for future devices that will have ICS Real Soon Now.

    Many of these same commenters also have a guarantee that AT&T or Verizon or whoever will NOT lock down these new devices, or otherwise make it difficult to install non-standard ROMs.

    Perhaps you missed the *guarantees* that the 3rd party browsers will exploit all the extra CPU and GPU power in their future releases, which will be ready on the day this new hardware/OS ships.

    And all these new models, upgrades and patches will be ready for YEARS before the Fruit Company releases its next models.

    Open always wins!
    Reply
  • KoolAidMan1 - Thursday, October 13, 2011 - link

    You win best post.

    It is hilarious how much spin and excuses are going on here, holy crap...
    Reply
  • Shadowmaster625 - Tuesday, October 11, 2011 - link

    So how long does the battery last playing Infinity Blade? Reply
  • tipoo - Tuesday, October 11, 2011 - link

    Good question. They said the battery was improved in almost every metric (standby time is down to 200h from 300 for some reason), but that might change when both cores and the GPU are maxed. Reply
  • webdev511 - Tuesday, October 11, 2011 - link

    It would be pretty embarasing if you did have one in the mix (like the HTC Titan) and it beat the snot out of everyone.

    Repost this story when you decided to include more than just the mono-culture and the fragemented platforms.
    Reply
  • cioxx - Tuesday, October 11, 2011 - link

    Apple controls the entire stack and can optimize like crazy on top of having faster hardware. Android ODMs don't have that option despite the fact they have access to the source. It's like shooting a fast moving target while juggling bunch of components.

    These results are insane. iPhone 4S smokes the Samsung flagship phone and holds its own against the tablet. I hope the developers don't treat this as baseline.
    Reply
  • morphon - Tuesday, October 11, 2011 - link

    Multi-core browser vs. single-core browser.

    Opera Mobile on any of the Android superphones (anything dual-core) will put up the same numbers as the iPhone 4S in browser benchmarks. My 8 month old G2X does, and it isn't as fast as the new Samsung.

    But it's what you'd expect. The ARM cores inside the A5 are not significantly faster than the cores in a Tegra2 or Exynos. The Android phones are running at a higher clock speed as well.

    Imagine two machines - one running OSX with the latest Safari, the other with Windows and IE. The Safari box will probably win. But does anyone who cares about performance run IE? No, they probably run Chrome or Opera. Use one of those and the Windows machine, seemingly by magic, will match or exceed the OSX box. Same hardware. Similarly optimized OS's. Highly optimized browsers.

    The important part of the A5 is the GPU. I think everyone would like to see more data on that.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Again, if you want to compare non-stock, you have to do it on both sides. Taking 1 stock vs 1 non stock is.. desperate, to say the least.

    The GPU performance speaks for itself. The iPhone 4S is by far the fastest phone on the market.
    Reply
  • tomhoward - Tuesday, October 11, 2011 - link

    On my SGS2 I'm getting 1561ms as the browser benchmark, what software version is the one tested here?
    Screenshot - http://postimage.org/image/21rbk83hg/
    Reply
  • xdoylex26 - Tuesday, October 11, 2011 - link

    I just honestly couldn't believe these benchmarks, so I went ahead and tested them out myself for verification on my GS2 w/ 2.3.4 on AT&T.

    SunSpider 9.1 w/ firefox beta = 1412.9 ms

    Given it's not the stock browser, but why does that matter when your comparing graphical benchmarks on a a screen resolution higher than your device?

    Move along people, nothing to see here.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    Did you run the OpenGL test too? And find out that your phone is less than half as fast as the iPhone 4S? Reply
  • xdoylex26 - Tuesday, October 11, 2011 - link

    my previous comment got deleted for an unknown reason.
    anyways, check out a firefox beta sunspider score on your GS2. It will be about 1400ms . I know this because I just did it. Nothing to see here folks.
    Reply
  • awokado - Tuesday, October 11, 2011 - link

    I just run SunSpider JavaScript Benchmark on mytouch 4g with cm7.1, score is 3147
    mytouch 4g is 1 GHz Qualcomm Snapdragon S2 MSM8255 processor with Adreno 205 GPU
    Reply
  • ab303 - Wednesday, October 12, 2011 - link

    ipad-2/iphone4s results are inflated for glbenchmark.

    i suspect a bug in ios port of glbenchmark.

    in an intermediate version of glb2.1 with vsync on, Egypt was ~ 38FPS for 720p offscreen with vsync on, on the IPAD-2. The new version of glbenchmark removes the vsync, and the result now shoots up to 85.7! this is too good to be true.

    kishonti needs to double check the sanity of the new version of glbenchmark, before people get misleaded thinking the IPAD-2 GPU is much superior compared to mali400/adreno220.
    Reply
  • JaM1977 - Wednesday, October 12, 2011 - link

    Why only 2 of 8 GLbenchmark 2.1 tests are posted, especially those least accurate (offscreen rendering)? in other tests it wasnt so dominant, especially against SGS2

    Mali-400 is more powerfull graphic chip than SGX543MP2

    iphone4s/SGX543MP2 7760kVertex/s 14773kShader/s

    sgs2/Mali-400 7880kVertex/s 23090kShader/s
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    The SGX543MP2 has more than DOUBLE the performance of the Mali-400, which now looks very slow and dated in comparison.

    The benchmarks included were the only OpenGL benchmarks which weren't limited by VSYNC - in other words the best representation of reality.

    Sorry but the Mali-400 just doesn't cut it.
    Reply
  • valnar - Wednesday, October 12, 2011 - link

    Android is slow. I used to have an Android phone and the equivalent iPhone has always been snappier, even with a slower processor. All the Android phones that have fast processors *need* them to compensate for the crappy written OS. I'm not an Apple fanboi, and I don't own any other Apple products, but I love my iPhone 4. It's fast and does everything I want. (Still hate iTunes though). Reply
  • AnandReader1999 - Wednesday, October 12, 2011 - link

    @Valnar
    You mistake a closed environment that is 5 years old as being superior.

    You correct that Android has been slow in the past, but that has been inefficient hardware, manufacturer bloat and an immature Android OS that is only 2 years old.

    Reality is that Apple is in danger of being crushed by an OS in its infancy because it has several manufacturer's pumping out state of the art products at a rate Apple can't hope to compete with. The only downside....the infancy of the OS and it is growing in leaps and bounds.

    As for new phones...you need to use a Galaxy SG2 stock. Its lightning fast, $25 bucks (or less) when its on sale. You can stream youtube videos to it (21mps vs 14.4 on 4S) and watch flash inside web browers.....you can even tell the Dolphin HD (downloadable browser) browser to display sites as a full desktop computer...again, complete with flash. My phone has become a laptop. Something the iPhone can never be at this point, since it only supports 'some' web standards, as seen fit by Apple.
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    'Lightning fast' - if lightning means travelling half as fast.

    It's cheaper because it's worse, not to mention the freezing issues and battery life issues.

    Apple supports all web standards apart from Flash, a decision which has any many benefits as drawbacks. Flash can be used with an app if necessary.

    All iPhones can zoom websites out to full screen too.. jeez.
    Reply
  • Paulman - Tuesday, October 18, 2011 - link

    AnandReader1999 meant that you can view the full desktop version of the websites (instead of the mobile versions) automatically with that browser. I think you can do that by setting the UAstring in your Android phone settings, too.

    But his bottom line with that point is that you don't have to trade anything off vs. a laptop when you're browsing on your Galaxy S II because Flash works. That's something the iPhone can't give you.

    Now, I wonder if the "Call phone" feature will work on the Galaxy S II's "desktop version" of the Gmail website... (I was Googling that a few days ago. Managed to find one mention of it working on a Xoom tablet...)
    Reply
  • KoolAidMan1 - Thursday, October 13, 2011 - link

    Yes. The same goes for Windows Mobile 7 as well. Both WP7 and iOS on 2010 hardware are snappier and smoother than Android on the latest handsets.

    Android is a trash OS. No real focus has been made on performance, it's mostly been about serving ads to as many people as possible while zealots brag about being on an "open" platform.

    I'll enjoy the closed platform that has the best developer support and best performance, thanks.
    Reply
  • ab303 - Wednesday, October 12, 2011 - link

    can anandtech check with Kishonti, the validity of glbenchmarks for iOS (IPAD-2/IPhone4S)?

    for e.g.
    - are we sure that the iOS offscreen test is indeed rendering 720p, similar to android?
    - this is an offscreen test, the underlying drivers and GPU in iOS could be smart enough to detect that the same FBO is being used for rendering over and over again without any reads. The drivers/GPU could very well be ignoring all the commands coming from the application layer. In this case, the test would be CPU bound and not GPU bound
    - if the same test is repeated for different resolutions on iOS, is the FPS really changing? If the FPS doesnt change, then we can know for sure the offscreen testing result is not trust worthy

    i kindly request anandtech to sanity check these points. Otherwise the results give a wrong picture of the GPUs.
    Reply
  • AnandReader1999 - Wednesday, October 12, 2011 - link

    I'm a long time Anand fan and have appreciated the depth which articles were done, from both a technical and fairness standpoint. Having reviewed the above 'preview' of the new iPhone 4S, I'm wondering if the actual forthcoming review will be as in depth as it needs to be give a fair shack to both sides (Android & iPhone).

    Some points I'm expecting.
    - Both reviews will use the latest synthetic benchmarks. Any shortcomings of said benchmarks will be noted, including any software that may be taking advantage of hardware or not taking advantage of it.
    - That the actual strengths of BOTH platforms be highlighted and displayed during the review. The iPhone is a LOCKED platform and circumventing it is very difficult. Stock browser's and stock apps are the norm. The Android platform is an OPEN platform with many choices for browsers and even rooting/ROM's is acceptable and supported by some manufacturer's. When comparing, the iPhone for should be Stock apps (as the norm) to Android Stock AND the Best Available, because that's what Android is. Free choice to chose the best of the best. If Cyanogen (or whatever stable ROM) is available for for Android phones, do the same tests using it. There should be a REAL comparison of platforms, not just a phone to a phone, locked down to stock browsers and constricted to Apples view of the world.

    - The iPhone 4S is a HUGE leap in performance from the 4 and 3GS. How about some logical statements. Like why on earth would someone take a 3GS or 4 for ANY amount of money, when you can buy an Android Samsung Galaxy for $25 bucks on sale? I don't care if the iPhone 4S is faster (now), I'm still only paying $180 on contract at the worst and its routinely no sale for $75 or $25 here in Canada. (The USA will have them on sale more in the next month or so). The iPhone is NEVER on sale. They just drop the price to dump them before the next release.

    I'm hoping to see the REAL advantages of the iPhone 4S vs Android (Samsung Galaxy S2 & S2X). The Prime can always be added at a later date for comparison to showcase newer hardware and OS update improvements...as this is also a strength of the Android phones.

    Comments Anand?
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    allow me to translate this whole post:

    'Waa waa, please Anand, make sure you don't compare the iPhone 4S to the Android. Please try to unbalance the test in Androids favour with non-stock browsers (but ignore the non-stock browsers on iPhone) because we want our geek-droids to look less owned. Please Please.'
    Reply
  • Swapzzz - Thursday, October 13, 2011 - link

    http://www.webkit.org/perf/sunspider-0.9.1/sunspid...

    Mentioned URL proved that the Scores over there are Fudged I benchmarked my phone HTC Sensation 2.3.3 and guess what you guys suck because you try to beat competition with fake results.

    Also, even though the HTC Sensation is running a stock browser that uses single core it still beats most of it Can wait till i get the Icescream Sandwich to see some real dual core processing.

    ON YOUR FACE ! FANBOYS!
    Reply
  • lang999 - Thursday, October 13, 2011 - link

    Its pretty clear that even with android 3.x it gets the same resluts as ios5.
    And soon android 4 is out.

    So this test is pretty much USELESS:

    Not compententertive. No nothing.

    !
    Reply
  • BrandoHD - Thursday, October 13, 2011 - link

    I think a lot of people would be surprised by how fast Samsung would update the SGS2, it has been rumoured that a device is already running 4.0 with Touchwiz, I have a SGS2 and I am running 2.3.5, while I cant speak for the carrier versions, the international versions of the SGS 2 should hopefully see the first 4.0 Roms coming out by the ending of 2011. Reply
  • TunaSandwich - Sunday, October 16, 2011 - link

    The iPhone 4S is great without a doubt but this article is not well written. The article almost misrepresents reality by only reporting select information. I expect more from AnandTech. Regardless, I've learned more about benchmarks and the potential for biased reporting by taking a closer look.

    The SunSpider Benchmark is biased depending on the browser. Some benchmarks on the Samsung with alternate browsers do much better.

    Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 & Firefox Beta – 1370
    Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 & Opera Browser – 1600
    Apple iPhone 4S with iOS5 – 2222
    Samsung Galaxy SII @ 1.2Ghz with Android 2.3.3 – 3371

    http://www.bestsmartphone.com/2011/09/26/javascrip...

    The Rightware BrowserMark also has issues and is browser specific. A Firefox browser on the Samsung does great (but maybe too good to be true).

    Samsung Galaxy SII with Firefox Beta: 94834 http://www.youtube.com/watch?v=ld0KMsxax2I
    Apple iPhone 4S: 89567

    There is a reported problem with Firefox and Safari on this test so maybe neither value is of any good.
    http://www.bestsmartphone.com/2011/10/11/browserma...

    Anandtech has only reported on the GLBenchmark 2.1 "offscreen benchmark 720p" without looking at other tests that show a lot of similarity between the iPhone and Samsung. There are also some funny things happening in this benchmark. If you take a look at the individual tests at GLBenchmark for the iPad2 50% are around 80 fps while 50% are around 50 fps. So does this mean that the iPhone 4s is faster than the iPad2? This offscreen benchmark is at 720p to which many devices may not be optimized simply because they were never intended to run at 720p. I've decided to misrepresent things a little in using only the top benchmark values for the Samsun in this test (see below).

    iPhone 4s Samsung Galaxy SII
    GLBenchmark 2.1 Egypt Fixed Time : 47930 ms 47595 ms
    GLBenchmark 2.1 Egypt High : 57.5 Fps 59.2 Fps
    GLBenchmark 2.1 Egypt Offscreen 720p : 73.1 Fps 49.9 Fps
    GLBenchmark 2.1 Egypt Standard : 58.2 Fps 59.7 Fps
    GLBenchmark 2.1 Pro Fixed Time : 21049 ms 20870 ms
    GLBenchmark 2.1 Pro High : 58.5 Fps 59.9 Fps
    GLBenchmark 2.1 Pro Offscreen 720p : 122.7 Fps 97.2 Fps
    GLBenchmark 2.1 Pro Standard : 59.1 Fps 59.9 Fps

    http://www.glbenchmark.com/phonedetails.jsp?benchm...
    http://www.glbenchmark.com/phonedetails.jsp?benchm...
    Reply
  • doobydoo - Sunday, October 16, 2011 - link

    The benchmarks which SG2 wins are due to VSync on the iPhone.

    The iPhone beats the SG2 in ALL benchmarks if you ignore VSync.

    The offscreen benchmarks are the only ones that do this.
    Reply
  • krumme - Monday, October 17, 2011 - link

    One day more for ip4s superiority - in an area that doesnt matter anymore.

    Then all is left is siri, and the subjective interpretation of build quality, that last until this unnessesary heavy brick hits the floor.

    I hate this iphone 4 reminds me of the old B&O remote controls, that was made heavy to signal quality. Worlds oldest marketing trick. Its like colouring the washing powder blue, to signal its good at taking the hard dirt. Lol. People walking around with iron in their pockets. How stupid is that?
    Reply
  • edsib1 - Friday, October 21, 2011 - link

    Using Firefox and Android 2.3.3 in Sunspider 0.9.1

    Samsung GS2 scores 1467
    HTC Desire scores 3197

    The SG2 blows away the Iphone 4S, and the Desire beats the IPhone 4.

    All you can say is that the stock browsers on the various androids seem slow.
    Reply
  • Silkwood - Saturday, October 22, 2011 - link

    Apologies if this has been asked/answered before, but when are we gonna see the full review of the 4S? (can't check the rest of the comments because this computer is slooow... OK, I'm really just lazy) Reply
  • kylewat - Friday, October 28, 2011 - link

    I read a post from Brian, I believe, last week saying we would get the iPhone review last weekend. I'm dying to know what's taking so long. I suspect it is battery life tests. It is absurd how bad the battery life is! 200 hours standby!? No way! Reply
  • JesusR - Tuesday, November 01, 2011 - link

    Regarding the stock/custom browser/ROM stuff to compare, we all just want to know what the best device is. But Apple fans here seem more interested in finding merit, culprits and heroes. Android phones may be better than 4S with different browser or ROM. Buaaaa, that's not fair, that's not Android! So what? Call it whatever you want, people just want to know what the best option is, and for that purpose, comparing non-stock is not just fair but necessary. Some people here speak as if using a different web browser was some kind of high-level hacking... Come on, guys... Reply
  • gel nail polish - Thursday, December 01, 2011 - link

    I love gadget. Although I'm not a tech savvy but I think this mobile is great!

    <a href="http://couturegelnailpolish.com">gel nail polish</a>
    Reply
  • arafat_mw - Tuesday, February 14, 2012 - link

    just visited the Rightware BrowserMark website reading this post..

    My cell is : Google Nexus One
    Custom Rom: Medroid 6.1 CM 7.2
    SetCPU : ONDEMAND @ 1.13GHz

    if my cell gives a score like 64694... I have no comments to make on the benchmark they have released.. I mean are they kidding me ? what ever clock speed is set on my Nexus One.. is it really better than - Optimus 2x, Motorola Atrix or Even iPhone 4(iOS5) ? I can't rely on their benchmarks ..I'm sorry.. on Quadrant my Nexus one leads the stock 2.2+ only by a few percentage like 5%... ..Haven't tried the other benchmarks.. but I'll try soon :)

    Screenshot : http://tinypic.com/r/dno65h/5
    Reply
  • Rizi - Tuesday, July 17, 2012 - link

    Messaging on this <a href="http://cellocean.com/iphone-4s-specifications-2210... phone</a> has been given something of a boost by the inclusion of the iMessage, which is a BBM-a-like service for iOS devices. It can be used on any device running iOS 5, which means conversations can be easily carried across on loads of Apple products without an issue. While many will expect iMessage to be a separate app in the same manner as BBM, it simply jumps in when a relevant phone is on the other end of the conversation, meaning essentially free text messaging and cool features like read receipts and being able to see when the other person is typing. However, this will be more useful for iPhone 3GS and 4 models, as it's surely only good to replace text messaging for those that need to save money and haven't got a price plan that offers thousands of messages for free each month. iPhones have always been looked at as decent messaging devices, and that's certainly true when it comes to email. There's a unified inbox for all your accounts, with multiple email addresses supported on the phone. Setting these up is as simple as you'd imagine, with only an address and password needed in most situations. As we mentioned earlier, it's so easy to keep track of your emails thanks to the new notifications system, but it's hardly anything new, so not really a unique selling point. The keyboard is another great selling point from Apple for its iPhone - some people have complained that it's a bit hit and miss in the past, but most people should have become trained in the art of tapping out a message on a touchscreen, so most will quickly be up to speed with the well-known keyboard. There's a new addition to the keyboard, and that's an option to speak out the message reply using Siri. It's almost unerring in its accuracy compared to other voice recognition systems, although you do need to say things like 'comma' or 'exclamation mark' to add in the punctuation. We sent 100 messages using Siri to see the accuracy, and found that the accuracy was around 45%, although shorter messages were obviously better. However, we were relieved to be able to head back to tapping out our messages on the keyboard, as you could make sure what you wrote was correct first go. If you're going to speak your messages, why not just call the person? Reply
  • Halo9x - Thursday, October 25, 2012 - link

    Benchmarks are fine, but let's get real. All this talk about speed is beginning to sound like the speed wars of the Desktop days. I purposely decided to save $100 and get a 64GB 4s while I could. Is the iPhone 5 faster, maybe. It really depends on what you are doing. I compared my 4s to the 5 and found the differences to be negligible.
    Everyone needs to take a deep breath and remember what they have. Whether it's an iPhone or Android, it doesn't matter. They mainly have to make phone calls, they do that. A secondary use is taking pictures, they all do it with the iPhones taking the lead. None of them are going to completely replace a dedicated camera. They all record video with the 4s/5 doing 1080p. As for the rest of the functions they are all about equal and yes, I know there are some minor improvements. Okay, the 5 did some things a full second faster. What will one do with all that time saved???
    Everybody acts like it's a matter of bragging rights but in reality, it's just plain dumb! It's like a bunch of school kids arguing about whose device is faster! Who cares? The more important question is whether or not one's chosen device does the job in a manner that works. The 4s is no slug and neither are the other phones.
    So, what did I like about the 4s? Stainless steel! Much more durable than Aluminum. The weak point is having not just one glass element, it has two. Advantage...5! However, I shopped around for replacement backs for the the 4s. Result, I found a stainless steel back and so now, the glass back is no longer an issue. Furthermore, the back is identical to the glass back I swapped out. There are a whole range of backs for the 4/4s. Can't do that with the 5, advantage...4/4s.
    The bottom line is the 4s is fast enough and I like the styling and size. It therefore remains a winner in my book. I do understand the desire to have the latest and greatest but it is a race most pocketbooks will not win. I do think Jobs was right, the 4/4s do fit the hand just right.
    Same goes for the NEW New iPad. Is it really THAT much better than the 9 month old new iPad???
    I doubt it. Certainly not in day to day functions.
    Reply

Log in

Don't have an account? Sign up now