Android 52% faster than iPhone in browsing speed

[Emil]

Update (10:45pm): As pointed out by our readers' comments, there seems to be an inherent flaw to the way iPhones were benchmarked. Apple claims the embedded browser environment that was used for this test doesn't have all of the Mobile Safari's performance optimizations that include JavaScript, asynchronous page-loading and HTML5 caching.

- Original story is below -
The largest-ever research study of smartphone browser performance, with over 45,000 measurements on the latest iPhone and Android devices, has found that Android was 52 percent faster than the iPhone, on average. The purpose was to determine which of the two leading smart phone vendors has the fastest browser, according to Blaze.

Android finished loading a webpage faster on 84 percent of the 1000 Websites tested. The study also found that the despite significant JavaScript performance gains in the latest Apple iOS 4.3 release and Google Android 2.3 releases, these improvement made no measurable improvement on the actual page load times of the sites tested.

The study used real phones on real-world websites to make the measurements. Past studies have often used fabricated benchmark sites or manual measurements on a small number of sites. The company developed custom apps for the mobile devices (iPhone 4 with iOS 4.2, iPhone 4 with iOS 4.2, Galaxy S with Android 2.2, and Nexus S with Android 2.3), which loaded a page on demand and measured how long it took.

"We were very surprised by the results", Guy Podjarny, Blaze CTO and co-founder, said in a statement. "We assumed that it would be closer race and that the latest JavaScript speed improvements would have a more material impact on performance. The fact that Android beat iPhone by such a large margin was not expected".

Permalink to story.

https://www.techspot.com/news/42877-android-52-faster-than-iphone-in-browsing-speed.html

 

[Rick]

The numbers from this 'study' appear to be completely unreliable. Appreciatively, Blaze points this out (I really believe they intended this to be as fair as possible). Don't take my word for it though:

http://www.blaze.io/business/embeded-browser-vs-native-browser/

“regards the tests as flawed because Blaze used its own proprietary application that doesn’t take advantage of Apple Safari browser’s Web-performance optimization”

“It’s not just JavaScript, though. Safari on iOS 4.3 also has multithreaded, asynchronous page-loading and some HTML5 caching”

“Despite this fundamental testing flaw they still only found an average of a second difference in loading Web pages”.

I don't trust Apple's input, but for any developer who hypothesizes that their own embedded browser [even though it uses Safari's renderer] is a fair substitute for an empirical study... well, they do not understand the concept of minimizing variables.

I appreciate what they were trying to do here but the reality is they did it wrong and even then, the difference was minimal so this is hardly worthy of the sensational headlines I've been seeing everywhere (not aimed at TS, of course).

 

[mosu]

quote:"The fact that Android beat iPhone by such a large margin was not expected". Maybe by you! I used both and came to a really close conclusion.And by the way, hardware counts.

 

[Leeky]

I have to say my experiences of my iPhone 3GS 8GB vs. my HTC Desire (both on the same network) are the HTC is considerably faster at anything using a network connection.

I can't speak for the new iPhone4 though, but mine did run iOS4.2 I believe before I last packed it up and put it away.

 

[negroplasty]

My Nexus One on 2.3.3 is lightning fast, I don't need a study to tell me that, nor an Apply fanboy to tell me otherwise.. It is what it is.

 

[NeoFryBoy]

I like how they didn't give actual time measurements. Clearly there are flaws here.

 

[Will_m]

My HTC desire beat my friends iphone 4 over wi-fi 4/5 times and the 1 was only lost by a fraction of a second, so I can't see this being wrong really.

 

[Zecias]

for those of you saying your android phones are much faster than the iphone
the speed difference may be due to your phones having superior hardware and very little to do with the browser; It really isn't a valid way of testing the speed of the browser. This may have also been the case with the study. screen resolution might have also played a role in the speed.
just something to think about.
in any case, take the study with a grain of salt.

 

[bonniesmith]

Android is faster in general, I have both device and that's fact.

 

[Leeky]

for those of you saying your android phones are much faster than the iphone
the speed difference may be due to your phones having superior hardware and very little to do with the browser; It really isn't a valid way of testing the speed of the browser. This may have also been the case with the study. screen resolution might have also played a role in the speed.
just something to think about.
in any case, take the study with a grain of salt.

I don't know about others, but I was reflecting on my actual experiences of using both devices.

Whether Android features far superior drivers or not, it is faster. Faster is faster, period.

Though I have to say its somewhat surprising when you consider the closed loop of driver requirements for iPhone hardware - its not like they have a 100 different setups (and counting) to deal with. They only need to consider ability to read bigger memory in the iOS, everything (to my knowledge) remains the same on each different iPhone type.

 

[Rick]

Leeky said:
Whether Android features far superior drivers or not, it is faster. Faster is faster, period.

Though I have to say its somewhat surprising when you consider the closed loop of driver requirements for iPhone hardware - its not like they have a 100 different setups (and counting) to deal with.

Drivers?

 

[Leeky]

I would imagine that they use pretty similar network hardware, my point being that maybe the difference is down to the drivers built to allow its use in the OS of each device.

I also made note of the fact you would usually consider it to be the other way around. With Apple developing software to suit certain hardware and the subsequent control they exhibit on it, you would expect Apple to be able to provide a considerably better OS given the set hardware.

Android on the other hand has to contend with tens of different designs, hardware and controllers - and work perfectly for each of them.

It should be easy to perfect things when you have only one unit to design, build and make a success.

 

[MrAnderson]

Test will always be imperfect. It might be more valid to do a study on perceived speed.

That is what seems to matter more since you are running 2 different OS on different hardware.

If Google took an iOS device and ported Android and browser to function on it and said this is the best we can do test away? and of course provided a tool to log and measure page loads? then apple provide a tool also log and measure page loads in safari? both with and without the optimization features on and off could we really get close to some answers.

But perceived speed is probably really more important because when people read these articles, we are thinking about our experience with the browser and our satisfaction with or perception of being able to consume the content loading in the browser?

This is way more difficult to pin down when running benchmarks for frames per second and JavaScript speed tests.