Android 2.2 (Froyo) versus iOS 4: the browser showdown (video)
By Richard Lai 
posted July 7th 2010 1:56PM
posted July 7th 2010 1:56PM
Update: for those who were concerned about the battery affecting the Nexus One's performance, we did use Android System Info to verify that the CPU was still clocked at 1GHz. We were also able to reproduce the same results with a full battery. Either way, it's still a win for Android.
Our test candidates were a 16GB iPhone 4 (with a shameless color mod) and a Nexus One rocking the official OTA 2.2 update and Flash 10.1. Naturally, we cleared out the cache files on both devices prior to each trial. Out of the five desktop-version websites that we tested for load time, three of them -- BBC News, gdgt and The Onion -- repeatedly produced a tie between the two phones, whereas the iPhone 4 consistently loaded Engadget about two to three seconds faster, and the Nexus One about one to two seconds faster with New York Times. Here's our video of one of the trials:
At this point we thought: would things load quicker with Flash uninstalled? Turns out it's a small yes -- this time the Nexus One consistently loaded Engadget, New York Times, gdgt and The Onion a tad quicker than the iPhone 4, whereas BBC News produced a tie. Still, this is far from the massive performance jump that Ars Technica's benchmarks suggest (not that we're saying the site did it wrong; these every-day sites just don't rely heavily on JavaScript), but considering Froyo running Flash still matches iOS 4's Safari loading speed, Android's just about won this two-man race. Apple, your move next.
"Still, this is far from the massive performance jump that Ars Technica's benchmarks suggest"
Ars is comparing Javascript performance. You guys only do a web-page loading test. Not even the same thing, yet you're comparing this with Ars'? :rolleyes:
@pika2000
A win is a win no matter how you look at it.
PWNED!
@Seven2k That's my point. Froyo is significantly faster than iOS4 in Javascript performance done by Ars, yet Engadget came in with just page loading tests, and tone Ars' test down by saying "Still, this is far from the massive performance jump that Ars Technica's benchmarks suggest" while n fact it's not even the same tests.
@pika2000
Not to mention Nexus One has to load up flash content, yet it still keeps up/ wins. To me, the Nexus One browser looks a lot faster.
@pika2000
true.
http://arstechnica.com/gadgets/news/2010/07/android-22-demolishes-ios4-in-javascript-benchmarks.ars
in case you guys want to educate yourself or just wait until your daddy steve says what he thinks..like always.
@pika2000
Yeah, this seems like a VERY weak comparison. Not really worthy of the moniker "showdown". Sorry, Engadget.
@NHAnimator What?! This is a week show down? Yes, comparing actual real life browsing speeds is a bad test, but comparing a ton of javascript functions is a good test. Lets consider how much javascript is on your typical web page. It's not much, it's certainly not going to make as big a difference in normal browsing, as seen here, as it would in a specific benchmark.
So both tests served their purpose. Ars specifically looked at javascript speed, which has only a small portion to do with actual page load speed. Engadget did a page load test.
@pika2000
That's because engadget is extremely biased in favor of Apple. They are an AOL company for goodness sake.
@AJerman Sorry, weak, I can't spell. Anyway, the important part here is that Android won in both tests. Perhaps Apple can see that people want choice in their mobile browser. Safari was the first decent mobile browser, but it's falling behind. Give the users choice. Doesn't every other company get sued when they try to force their own product upon people without giving them choice?
Android>Apple
@NHAnimator maybe we could say, safari looks like ass, the goolge android browser looks better. as the headline?
@AJerman Well, I wanted to point out more about Engadget toning down Ars' test with the comment "Still, this is far from the massive performance jump that Ars Technica's benchmarks suggest," even though they are not even doing the same tests. Engadget could just do their test without saying that comment about Ars', and things would be fine.
@pika2000 We aren't toning Ars' test down; we're simply saying that the average users won't be seeing that much of a jump.
@pika2000 there are blogs (engadget/gizmodo) and there are tech sites (anandtech, ars, tomshardware, etc). Anything more than reading tech specs is usually too overwhelming for the blogs.
To Engadgets benefit though, js performance doesn't make or break the speed of loading a website. Sure Android processes it faster, but they're still both on the same pipe downloading files at the same speed which probably accounts for 95% or more of your web surfing experience.
BTW, I'm no fan of the iPhone so Go Android!! Kick it's Ass!!! (I'm not a big fan of Android either but an enemy of my enemy is my friend). Go webOS!!!!
@NHAnimator I think this test is more relevant to a regular user then the Javacript tests. Real life performance is what I care about.
Fellas.. you do know that you don't have to uninstall the Flash Player if you don't want flash to load in the browser. In the browser, go to Settings -> Enable plug-ins -> and select the "On demand" option. This way, any flash objects will load up only after you press on the little green arrow in place of the flash object. It's magic I tell you!
@pika2000 Why? They made a very valid point. Javascript performance doesn't make that much difference in most real world tests. Unless you're on a page loaded with javascript, you'll see nearly no difference, as proven by Engadget.
This doesn't make the javascript benchmark any less valid, it's just showing that the massive win in a javascript benchmark by Android means very little in typical browsing.
@AJerman OMG!!! It's going to take iphone owners a whole second longer to load a page. Damn! All you people go back and return your iphones now.
@jdmsirek4
microsoft
@jdmsirek4 The funny thing is Android is always being compared to iphone. Always.
@pika2000 Actually this is a clear win for android. Comparing Nexus vs Iphone 4 is an unfair comparison for the nexus since the A4 chip is a lot faster than the Snapdragon. Do the same test with the Samsung galaxy S (which has the exact same CPU than the iphone 4, it just re-branded) and now the comparison will be fair! And even with unfair comparison the nexus one still gets the edge. Android is catching up very very fast on apple!
Oh and BTW, arstechnica vas talking about JS performance not HTML and this is clearly and HTML rendering performance test...
@pika2000 the thing is, that's how most human beings use the web.
@jonyah I understand that Engadget was trying to point out real-life browsing experience. However, Ars' test is clearly titled as Javascript benchmark. Engadget's title said "showdown," with only page loading tests, and made that comment about Ars'. If Engadget would just title this with something like web-page/real life loading performance, with linking to Ars' site but without that kind of comment, I wouldn't mind.
@Richard Lai why did the wifi on the N1 have a weaker connection speed then the iphone? It seemed to only have 2 bars while the iphone had a full connection. Lastly why didnt you scroll up and down. Traditional the iphone doesnt load the entire page it only loads what you are seeing as to Android loads the entire page so when you scroll you see everything now those bricks on the iphone when you scroll up and down on the page.
@dxdragon Regular users don't read Engadget.
@Seven2k
Both of these phones are winners compared to my aging Blackberry Curve.
I'd be happy with either of them!
anandtech already did a whole bunch of benchmarks and was much more comprehensive than ars last week...
Froyo even blows the ipad out of the water in javascript performance. Websites will vary depending on how complex they are. I suspect all the google sites will show much better performance than iphone/ipad because they are javascript heavy. And with all the emphasis Apple places on html5, when more sites move to it, froyo will likely show better performance too, so it's a win win for Google.
http://www.anandtech.com/show/3794/the-iphone-4-review/12
@pika2000 you guys sound like a bunch of nerds trying to make excuses why it won. i mean seriously something is proven and you still cant admit it, you find excuses and use twisted logic. seriously if you care that much about android beating iphone go work for them and make it better. cause the battery life is horrible on android. i had the droid from motorola and the incredible a few weeks after it. i sold my iphone in april and got both those. the battery is the worst i ever saw so i went back and got an iphone 4. android is not as fun to use, the apps arent as good or as many choices. i mean like what u want to like its your decision but dont make such a big deal if someone wants an iphone over an android. android will never catch up to apple. just like no one ever will catch to ipod. its game over and things will not be changing for the next 5-10 years so get over it
@jawman Exactly but people for some reason are blind to the connection....
@pika2000 Well Engadget is just testing real world use and this is how I would load a browser >.> And the iPhone seems to the overall winner.
@pika2000 Maybe because websites has javascript?
@Seven2k
Agreed. Gimme Froyo for Moto Droid!
@NHAnimator I agree. Title was way too overhyped.
@pika2000 I disagree. Many websites have heavy JavaScript usage nowadays, especially Google sites (the whole "AJAX" trend). Having a faster JavaScript engine will benefit any user.
@pika2000
I'm an Android user and I don't see Engadget trying to diminish ArsTechnica's tests.
The way I read that sentence is that someone might look at Ars Technica's results and think that during real-life browsing pages will load significantly faster in Froyo, but in reality the difference is not as pronounced. That's why they wrote "Ars Technica's benchmarks suggest." Engad even clarified they weren't trying to suggest Ars did their benchmarks incorrectly...
@Eliasj
Engadget could have easily turned off the Flash and done a REAL comparison.
@geo1378
Well, I wanted to point out more about Engadget's comment about Ars' test: "Still, this is far from the massive performance jump that Ars Technica's benchmarks suggest." I'm not siding with Android nor iOS. Engadget could just do their test without saying that comment about Ars', and things would be fine.
Let's say Anandtech did a gaming benchmark of an nVidia vs ATI video card, and said nVidia is faster by x fps. And then a gadget blog came in and do a test of both video cards by measuring loading times of the games, and pointed out to Anandtech's test that the nVidia card is not that much faster. That's how I feel when I read that Engadget's comment.
@Tes Uh, we did turn off flash in the second round.
@Richard Lai
My bad, didn't peep the second vid.
@MichaelJJackson
Did you read the article?
@pika2000 yes, Engadget tested actual real world performance rather than pointless benchmarks focussing on one small aspect involved in the operations people actually do with web browsers. What a terrible test!
Engadget never claimed to be performing the same test. What they're pointing out is that a large percentage number in a very tightly focused benchmark can provide a misleading impression when compared to what you actually experience in typical use.
(I don't use Android or iOS. But I do hate the ridiculous over-reliance on Javascript benchmarks that's inexplicably crept into the browser industry, so thanks Engadget for resisting it.)
@jonyah
We share a relative anyway(Linux)
@AJerman " Lets consider how much javascript is on your typical web page. It's not much, it's certainly not going to make as big a difference in normal browsing, as seen here, as it would in a specific benchmark. "
Incorrect, how about those web apps that Google so kindly offers and has gotten their steamroll from in conjunction with their search domination?? Even made MS consider web apps, because FREE, mostly reliable, accessible from anywhere apps beat paid, half-working, integrated BS anyday. And when HTML5 gets its big pushes in the coming years, this will make a HUGE difference.
Remember, Google specializes in software engineering... and Apple. They are exceptional in hardware but software -- not so much (bar doctoring for 3 generations, N *just now* figuring that, huh Apple?)
@geo1378 Everything changes in five to ten years. Apple didn't have a foothold in telecommunications, music, television, movies, or software: there was no ipod, itouch, iphone, ipad,or itunes.
Just a load of shit software and shit computers.
Ten years ago apple was about to go belly up. However, Steve Jobs came back to company and the rest is history.
Respect, the decade of their ascension and the possibility for change in the future.
Disclosure: I do not really like apple products. I only own a 4th gen iPod flashed with rockbox because I do not like apple's restrictive software.
@Richard Lai PLEASE go take a journalism class!
@pika2000
Keeping in mind that the Nexus One is 6 months older, running on a weaker processor (consequently with a weaker GPU as well), using Wi-Fi G at 54Mbps (rather than WiFi N at 300Mbps or more on the iPhone), loading flash , and if you look closely, Richard Lai is pressing the iPhone barely earlier at times(forgiveable, seeing as Richard is only Human). Yet the Nexus one still ties or beats the new iPhone at all? If that isn't a testament to the rapetastic speed of Froyo then I don't know what is.
Android won this test by one of the largest margins I have ever seen in a browser/performance test.
@pika2000 I don't see why you guys (Engaged) post flame bait articles like this. I understand you are just trying to show that "real life usage" is not going to see a huge difference, but you come across as sticking up for the iphone. I have always stood up for you when some tool comments, "Engaged is in Apple's payroll" but its very hard to stick up for you when you come across like this. What happened to good ol' unbiased tech reporting. You all have more class than this. You could of at least left out the comment about ars' test.
@pika2000 I partially agree with you, but I think everyone needs to take into account that these tests are in the millisecond ranges. 4 times as fast doesn't look like a lot when in that range. They definitely still have that slight apple tint to things. Either way, performance and feature wise, my nexus one is one of the best mobile browsers... if not THE best. I'm happy with that.
@Otsegowupiwupi Correction... Android *2.2* won. Now if there were more than the measly 1.8% of Android phones actually running 2.2!
http://news.softpedia.com/news/Android-2-2-Froyo-Takes-Its-Share-of-the-Android-Pie-146128.shtml
@gargle
Based on some hands-on videos I've watched on this site, it seems many of the main Engadget editors don't know how to use an Android phone nearly as well as an iPhone.
I would have liked to apply for the SF job (so the staff has at least one full-blown Android user) but I know I'm not that great of a writer.