RSSGoogle Chrome in a runaway lead for browser performance supremacy
By Scott M. Fulton, III | Published October 31, 2009, 1:51 PM
If Apple's Safari is going to make any kind of a challenge for best performing Windows-based Web browser moving into next year, it needs to be now. In Betanews' most extensive testing to date, involving tests that by anyone's guess should not have given it any special advantages, the latest stable edition of Google Chrome runs away with a three point lead over the latest stable Safari -- a lead that now grows by one-half point with each point release.
Chrome now posts test scores in certain heats of our revised CRPI 2.2 test battery that are virtually obscene -- so far ahead of competition that we have to validate our results on various machines to make sure we're not generating false results. For example: On the control flow element of the SunSpider test, both Chrome 3 and the dev build of Chrome 4 post record low time scores of 2.6 ms. This is an element that tests the JavaScript interpreter's capability to keep track of nested loops and its location in a twisted program. By comparison, the latest public Firefox 3.6 Beta 1 -- released late yesterday afternoon after a flurry of delays totaling over one month -- posts a score of 38.2 ms in that category.
Mozilla's team has been making efforts to better Firefox' control flow scores, evidently knowing how much they influence test results like ours. The evidence comes from the latest daily builds of Firefox 3.7 Alpha 1, on the "Minefield" track, whose control flow scores recently quantum-leaped down to 8 ms. That's almost a 5x improvement, but it will need another 3x blast to catch up with Chrome. The latest stable Apple Safari scores 3.4 ms on this element.
Another example: A factorial is the result of multiplying together all positive integers that are less than or equal to a number, and a new element of our testing battery includes a classic algorithm for obtaining the set of all factorials. On this heat, the higher number is better since the objective is to obtain as many factorials as possible over a set period of time, so the score is a relative index. While Firefox 3.6 Beta 1 scores a 17 on this heat, Chrome 3 scores a 150.4, and the latest dev build of Chrome 4 scores 164.5.
There are certain things that Chrome does where the score differences are factors of 10, where one might get the impression that Google is improving Chrome just to score better with Betanews (the company has been expressing its interest to us directly in recent days) or more likely, with its own internal test suite. Indeed, the company's V8 benchmark suite would have users thinking the browser is hundreds of times more capable than its competition -- a claim for which we just don't see the practical evidence just yet, which is why V8 isn't part of our tests.
That's why we've made an effort to pack our CRPI test suite with examinations of a multitude of real-world characteristics in various categories, now with 69 different "heats" in ten separate batteries, plus a multitude of derivative scores (e.g., average of 50 iterations, consistency between the fastest and slowest run, etc.) for each browser.
Once we include all these different elements, we get a much more practical and believable result. There are many reasons why a person chooses a favorite Web browser, with JavaScript performance being just one of them. But that factor is becoming more important now with the onset of applications delivered to you from the Web rather than your hard drive. So with regard to that factor alone, Betanews can say that Google Chrome delivers almost twice the performance (not quite 2x) of the latest stable Mozilla Firefox builds, with Apple Safari probably pulling close, and Opera being left in the dust until it comes time to be thinking about Opera 11...if not Opera 12.
"Probably" pulling close? What, Betanews can't do better than that with respect to Safari? Yea, unfortunately there's still trouble with that: Apple's test builds of Safari come by way of grafts of its daily WebKit engine onto the existing 531.9.1 browser. Usually, after applying one of these grafts, the updated Safari displays better if not superior rendering performance than even Chrome. But its ability to serve as a full-scale browser for other tests vanishes. However, over the last week while Betanews has been trying to resolve this problem, it actually only got worse: Windows testers reported through Apple's forums that not even the grafting mechanism was working.
We validated those claims, discovering that the manifest which the replacement executables were being shipped with (the embedded XML files that point to proper COM components in the System Registry) were pointing instead to incompatible versions of Windows Common Controls, versions that may have worked back in the 1990s. Apple is apparently already aware of this, but as is the company's policy with regard to any kind of problem with its software or hardware, will not publicly comment.
Next: The latest test scores broken down...
Penalizing for failure to meet standards should just be removed... In the end, whether a browsers is standards compliant doesn't matter except to a few people. Chrome may be fully standard compliant, but I get plenty of messages that it isn't supported by lots of websites out there. Heck, netflix doesn't even work on Safari... One of the main reasons its hard to have safari or chrome as your primary browser.
IE8, the least standard compliant... yet to find a website that generated a message about lack of compatibility except for some website that ripped IE for not being standard compliant...
Score: 0
|LOL, I will keep my default browser Opera, follow by FF then IE and on the Mac, FF then Opera. No freaking Safari for me.
Score: 1
|To Betanews:
please, add Arora browser to the mix. It's not yet popular but it has very nice features and it's blazingly fast.
Score: 0
|WinXP beats Win7 most of the time and that's on a modern hardware.
Now will those people, who say that Win7 is faster on a new hardware, please, shut up.
Thanks, betanews for showing us these straightforward results.
Score: -2
|*laughing*
Source? The benchmarks above hardly translate to anything but the author's vivid imagination...
Score: -1
|More like thank them again for another lackluster article.
@PC_Tool - lol, very laughable. This site has gone downhill A LOT!
Score: -2
|Am I the only one thinking who gives an eff? This would really only be of interest to you if you lived in a thirld world country still on 56k modem. But I happen to know that many third world countries now have DSL believe it or not, so what the heck does this really matter?
Score: -1
|I don't care how fast that crapware becomes, I will never use it again. I tested it once, and it is just junk!
Score: 0
|I find Chrome to be very nice not for the rendering speed but for the fact if i leave it open and walk away for an hour it doesn't use 99% of my system memory like the last few firefox releases have
Score: 1
|BN Google is already on .16... where's the update? slackers.
Score: 0
|Having just re-installed system,and started Firefox and typed in betanews it opened the actual page,did same with Chrome it gave me a list.It can have all the browser speed in the world but without the add ons and the ability to do what's asked,it will always be Foxy for me!
Score: 0
|I always say it and i'll do it again. What good is speed without control? And Chrome seriously lack control. No extensions, no extra features, no nothing. Sure it's fast but completely useless to me.
I need fully configurable interface, mouse gestures, adblocking (i really can't stand flashing banners), GMail notification (it's their service and they don't care about it lol) and finally, bookmarks synchronization. When they add all this (or at least via extensions) i'll switch to Chrome. But until then, i'm sticking with Firefox just because it's so damn flexible.
Score: 3
|Zactly! Sure, a nitro dragster is fast, but you're not gonna drive it to work everyday, pickup the kids from school, or get groceries. Once you make it able to do everyday tasks, you end up with a mini-van. Not fast, but much more versatile.
Score: 4
|Wanna know the main reason why this speed crown doesnt matter? Microsoft doesnt seem to give two sh#@s. IE is number one by a mile. And they never ever come out with a new updated version as often as the other guys. They will patch security holes. But never do anything else. Apperently the speed race is lacking the main player. And for that reason this game is meaningless.
Score: -2
|"Google Chrome in a runaway lead for browser performance supremacy"
...with no customization add-ons worth discussion and from a company whose track record in software dev is at best questionable (Google desktop anyone?).
**YAWN**
Score: 0
|Speed is ok, but how about security... Which is the MOST secure?? Most of us don't care about 5 or 6ms.
Score: 3
|It can be argued, but it really depends. Are we asking overall security, local security or remote security? On the local side it runs a Google Updater agent, no idea how secure this thing is but any extra things running always leave more of an attack surface.
On the remote side, I'd say it's fairing pretty well. One example to cite from would be the somewhat controversial results from the Pwn2Own event (specifically cited is the sandboxing):
http://arstechnica.com/s...-in-pwn2own-contest.ars
There's also the matter of JS/Flash which of course you could minimize the security impact of with things such as ABP & NS on Firefox, reducing it's attack surface in alot of situations. Some of these could be mirrored with time to come on the Chrome side with the introduction of Chrome extensions.
Score: 0
|According to Secunia's database, Chrome 3.x is the most secure OOB. It has had the least exploits of all the major browsers since release, (and those found have been patched within days of discovery, faster than any other browser to date as well.)
2.x
http://secunia.com/advis.../25469/?task=advisories
3.x
http://secunia.com/advis.../25720/?task=advisories
Score: -1
|Chrome is not nearly as popular as even Opera so malware authors/security experts don't have an incentive to find holes in it. And probably its sandbox architecture is paying off - who knows?
Score: 0
|How about some benchmarks that include how well the browser manages memory? Performance will go to crap if it has to page, and that happens quite a lot with 1Gb of RAM.
Score: 1
|Every app pages. Every single one. They always will.
Systems with 1Gib of RAM were commonplace in 2004? RAM is like $10/Gib. Give me a break.
Chrome 4.x Dev uses about 100M for 4 tabs. Firefox uses about 60M This is in an application I almost never close, use primarily on my system.
Of all the things people complain about, why is memory use of 1-10% of the system such a huge deal? You paid for that memory, don't you WANT it used?
Score: 0
|My FF is opened at about 7am, and stays open until around 3am, EVERYDAY. I haven't seen it use much more that 256MB of RAM with 4-8 tabs open. I have a boat load of plug-ins loaded as well. I love FF. It does everything that I need and want. As for speed, I click and I am there. It opens with all of my plug-ins and with a minimal of four tabs open, without a delay. I am only running an AMD 6400 x2 and four Gigs of Ballistic Tracer RAM, with W7 Pro 64 bit. Not a great system, but no speed problems with FF, no memory leak issues either.
Score: 0
|"Of all the things people complain about, why is memory use of 1-10% of the system such a huge deal? You paid for that memory, don't you WANT it used?"
Yes... but I want it used efficiently... and by more than one application at the same time.
Faster (and multi-core) processors, larger amounts of RAM, greater HDD storage capacity... these have all-too-often been used as excuses for developers to release (and consumers to accept) sloppy code.
Sadly, gone are the days of clean, efficient programming when developers knew they only had so much room to work with. They were forced to make their code as streamlined as possible.
These days, "add more RAM" to make something work better... that's just ridiculous. More RAM shouldn't be necessary to make a single application work better. It should be desired to make that application work better with several other applications simultaneously.
http://en.wikipedia.org/wiki/MenuetOS
http://www.menuetos.net/
That's an entire operating system (with a GUI) that fits on a single 1.44 MB floppy disk!
Score: 1
|"Every app pages. Every single one. They always will."
No, not every app pages. I (and I'm sure others) would love to see the source of this claim.
Every app does use Virtual Memory, which != pagefile.sys.
Space is only allocated in pagefile.sys when a virtual memory page in physical RAM must be paged out.
Score: 0
|You're BS'ing us. 90% of PCs in my organization have exactly 1GB of RAM and I'm scared to imagine a browser which is not trying to preserve memory.
Score: 0
|I have 3 web browsers installed, Firefox, Opera, and Chrome. The best out of the 3? Firefox. Why? AdBlock Plus(Mainly) & NoScript Addons.
Score: 3
|What's been measured is not browser performance but browser speed on a number of dimensions. How a browser actually performs is a combination of its features and users' preferences, of which relative speed is only one and, to me, not all that important beyond a certain threshhold. Btw, I tried Chrome a couple of weeks ago, and I found it to be a generic browser wholly inadequate in feature for my not-very-complex browsing needs. I suspect it gains a lot of speed from being generic.
Score: 2
|Chrome is a new browser and does not need to carry foward all the compatibility stuff that other browswers have. That's why it's fast...
Score: 0
|Enough speed. Let's talk about printing. I heard Firefox gives best result in this regard, while IE at very close second.
Score: 3
|Whoopty-****ing-doo
Seriously - who gives a ****ing rats arse about how fast a ****ing browser renders a page...when the ****ing determinant of how fast you see something is the ****ing latency of your internet connection - which is orders of magnitude slower...
Only brain dead smelly virgin nerds give a s***e about this sort of bollocks...
No wonder we are stuck with s***e O/S's and half arse applications...
The combined talent of Apple, Google and Microsoft still cant produce a quality O/S or applications that actually work the way people work...probably because they are focusing on trying to make their facking browsers 0.01 of a nano second faster than the previous version...
What a way to focus resources...
Morons! The lot of them!
Score: -6
|i am using broadband and i dont see any big speed differences btn chrome,firefox or opera.....
Score: 3
|One good example where you can see a difference, and it's fairly extreme:
http://benfirshman.com/projects/jsnes/
While this may be not of interest to you, it highlights the fact that another site may want to use functionality that just simply works better on the Chome side at this point.
Score: -1
|Chrome is fast....now if only it were at all usable...
Score: 3
|About the only reason I would halfway consider using Google Chrome is if the use of Adblock Plus was an option.
Alas, I see that happening as much as I can see oil companies pushing for quicker adoption of hydrogen fuel cells.
Score: 3
|Someone has developed an "Adblock+" for Chrome. It does not use content filtering (as this is not yet a feature of chrome), but it will handle the basics...and I believe they even support the ABP subscription lists now.
Still... Too young yet. Browser needs to mature a good deal (which will probably make it slower and remove all of the benefits of using it).
Score: 1
|AdSweep works great in Dev version
Score: 0
|Wow, you "believe." Works for me. Blocks all ads, and Pressing Alt+B blocks elements just fine.
http://www.chromeplugins...ugins/adblock-7523.html
"Too young yet"
It's over a year old, it has had far fewer security issues than Firefox. It is more compliant to browser standards than firefox since day one, and has never been less compliant than Firefox, a 4+ year old browser continually changing its features and interface.
"Browser needs to mature a good deal (which will probably make it slower and remove all of the benefits of using it)."
Ah, the same boy that was telling me to add "in my opinion," hypocritically ignores it himself. He has no facts to support his "probably make it slower" in fact as the browser has aged it's only increased in speed.
Score: 0
|"Wow, you "believe." Works for me."
Yes. I believe. Because I personally haven't tested it. Unlike others (regardless of your pitiful accusations), I don't go around spouting BS I haven't personally tested or making statements of opinion as fact. Works for you? Great! Glad to hear it. Next time I comment on it, I will be sure to include the fact that it anecdotally works ... for you. But by simply browsing their forums, I can see that it is not working for quite a few others.
"It's over a year old, it has had far fewer security issues than Firefox"
Age has nothing to do with it. Security has nothing to do with it. Community support, management capabilities and extension support has everything to do with my opinion of it's "maturity".
"Ah, the same boy that was telling me to add "in my opinion," hypocritically ignores it himself."
Did you totally miss the "probably"? Unlike some, I didn't say it "would". I gave my opinion...as an opinion. Nice stretch.
" He has no facts to support his "probably make it slower" in fact as the browser has aged it's only increased in speed.""
Want backup? Look at Firefox. The older it got, the worse (in my opinion) it became. As for your "increased in speed' comment....BS. Try reloading this site in Chrome. Then reload it in Firefox. Not the initial load, but a refresh. Fast? Yeah...and I am a friggin' jedi. FWIW: it rocks with Pandora. I refuse to access Pandora in anything but Chrome.
Even so, it (Firefox) was still light-years ahead of Chrome in terms of extendability (and usefulness to me), even way back then.
Score: 0
|"Want backup? Look at Firefox. The older it got, the worse (in my opinion) it became. As for your "increased in speed' comment....BS. Try reloading this site in Chrome. Then reload it in Firefox. Not the initial load, but a refresh. Fast? Yeah...and I am a friggin' jedi. FWIW: it rocks with Pandora. I refuse to access Pandora in anything but Chrome."
Firefox has only increased in speed --by any measure-- since its release.
And unlike the insane ramblings of a Tool, I don't sit around refreshing the same site all day and consider that benchmarking on any level.
Score: -2
|Wow. What are you, 3?
OK, before you keep making this BS up...
"Firefox has only increased in speed --by any measure-- since its release."
"Worse" does not imply slow. Worse is a subject of impression, which can include usability, speed, extendability, support, updates, community, and any number of other things.
I never said firefox got slower. Not once. So now you're simply making crap up. Is this effort you seem to have undertaken to "prove me wrong" really worth it? I've been wrong many times. Would it help if I pointed you to a few of those posts?
"And unlike the insane ramblings of a Tool, I don't sit around refreshing the same site all day and consider that benchmarking on any level."
...and there you go again. Apparently, if MJM doesn't frigging do it, it is meaningless for *everyone*.
How cute. Almost as bad as the last post where you basically assumed I had fallen victim to your mistakes, celebrating the fact that you weren't the only one. The equivalent of saying, "Yay! You did it too! That means you're stupid! ...like me...."
Clever...for a 3 year-old.
Oh, and call me a "tool" again. It's so original...
Score: -1
|Enough with the e-peen. Although I find nerd wars to be entertaining at times, nobody cares. When it results to name calling, perhaps that's your cue to shut up. You're both acting like 3-year-olds.
Score: 1
|Meh...
It was all well and good for a bit. Someone wanted an adblocker for Chrome, I informed them of an existing extension. The rest is merely self-defense. I admit I've never checked, but I believe adults do that from time to time. :)
Score: -1
|Agree with PC_Tool completely this time. I try Chrome and Safari every couple of months, and I'm completely unimpressed. I saw no significant speed boost over IE, Firefox or Safari on my relatively slow connection. The designers don't even have enough confidence to fully enable extensions yet - that speaks volumes. Like most things Google, its an experiment meant to draw more people into its web of marketing and data mining. That doesn't really scare me all that much, and there's many ways to be anonymous on the web if you feel like it. That said, my preferred browser Firefox has some serious issues, like breaking lots of plugins with virtually every release..but that's a game you always play with stuff that's actively developed. It also won't render certain sites correctly, usually those that heavily employ ActiveX-derived controls. And the ubiquitous AdBlock Plus will render many sites virtually unusable thanks to spyware-like banners and Flash-based menus (I use a Flash blocker, too). FF is also clearly getting slower, but all of these issues can be fixed by Mozilla or plugin programmers - I'm not so sure about Chrome yet.
Score: 0
|"Chrome is fast....now if only it were at all usable..."
One behavior that drives me nuts is when your deleting the address bar contents. Try holding down the backspace key. It starts dinging like mad when the last characters have been deleted. I don't find this helpful, I find it an unnecessary addition. Firefox & IE do not seem to exhibit this behavior.
Just out of curiosity what drives you most nuts about the browser, and what would you do to improve those failing aspects?
Score: 0
|"Oh, and call me a "tool" again. It's so original..."
Just had a sudden flashback to Hanc*** ...
Call me "tool" -- one more time.
Score: 0
|How stable is stable...
Once went onto Facebook on a Chrome browser, the thing crashed 5 times in 10 minutes
Score: 1
|"so far ahead of competition that we have to validate our results on various machines to make sure we're not generating false results. "
better bolder lines
betanews is learning how to do proper benches! Thank you!
Score: -2
|I have next to no crashes since last update in dev. version 6-10 tabs open most of the time. Only time it crashes is when flash player screws up.....
Score: -2
|I love chrome because it is faster than Firefox
Score: -3
|LOL , i think now even Firefox 3.6 Final wont run Betanews tab previews :P
Score: 0
|BTW if we just see Sunspider benchmarks , then Firefox 3.6 Beta 1 is 18% faster than 3.5.4
Score: 0
|I thought you should now that in tests of speed to render Flash, Chrome on my system is about 20%-30% slower than Firefox or even IE. Snailsanimation flash benchmark is one, but the results are consistent with most flash benchmarks.
on medium: Firefox 30.5fps, IE 30.2fps, Chrome 25.6fps
Score: 0
|OMFG!! Now dial-up ppl will load pages in just under 32 seconds! WOW! Me, on the other hand, using broadband, will be able to load pages in almost nano seconds. Whew! I live for another day! You fking morons and this speed s*** really crack me up. Functionality a******s, functionality! Every fking browser takes me to the same place. Until one holds a tissue for me while I masturbate I'll stick to Firefox.
Score: -6
|Obviously this struck a nerve but the language, although implied, could be left out.
Score: 1
|Yes, it did strike a nerve and I apologize for the language. I'm just so fed up with the speed thing already, that's all.
Score: -4
|I don't know about the rest of you folks out there, but somehow I've just become a little sadder for the human race.
-SF3
Score: 0
|The point is taken.
I use my browser to browse web pages, not run benchmarks. While JavaScript has become an easy way to speed up processing, it's still not the only element of a page but it's still a concern for the developers.
I'm quite happy with Firefox and the extensions which help me accomplish things more efficiently. Chrome is really good at getting there quickly, but it's hardly close to a finished browser and neither is Safari.
Score: 1
|Scott, we could deal with this issue if we were on a PvP server :D
Score: 0
|Scott:
Google "Left 4 Deads2 Racism".
If you are not overcome by an acute sense of embarrassment that you are part of the same species as these folks, well...I guess that would mean you were one of 'em.
Score: -1
|@ jc_lvngstn:
LOL
Score: 0
|This test and others are useless. Being like myself i just prefer a IE over anything else regardless. It may be slower but doesnt at all feel slower. Plus like so many other people, who just like a certain browsers cause they just do. I really hate chrome, and will never like it cause i hate the design. Opera and Firefox are not bad. I actually use them and they are pretty nice. But my favorite is IE. It doesnt crash and it seems to work very well, and always had.
The test is meaningless cause people like what they like.
Score: 1
|Never say never. If there is one thing that is true about software, it's that it's always changing.
Score: 0
|Curious, what about the Chrome design do you not like? It does everything in its power to be as nonintrusive and out of the way as possible, and simply display the pages you want. I can understand if you manage AD networks and not having fine-grained control over every aspect of the browser across a domain, but what else is there?
Score: 2
|Some people just think it's ugly. I know...go figure, right? Must be a matter of taste.
Score: -1
|If you use and like IE you need to close your browser and never come to betanews or any other tech sited again... You sir have no idea what you are talking about
Score: -3
|@ rstouder:
IE prints certain sites better than Chrome/FF for me. Tabbing through text-entry fields works better for me.
...but of course, I don't know what I am talking about, right?
Right now; I have BN open in Firefox, Pandora open in Chrome, and our intranet and vendor sites open in IE 8.
Why? Because I use what works best for me for whatever it is I am doing.
You sir, have no idea what you are talking about. Take your own advice?
Score: 1
|@ PC_Tool
I agree with you on that statement. You use what WORKS in your environment. I use Firefox for browsing and etc. IE8 for intranet and webmail. Not every browsers supports everything. You use what works for you, not because someone posts on BN... "This works the fastest". I prefer stability over speed any given day. If there was a browser that was fast, stability and supports everything. I'll be all over that.
Score: 1
|For help of others , i done some calculations to show the benchmarks in %s
Results show that
Chrome 3 is 13% faster than Safari 4
Safari 4 is 45% faster than Firefox 3.6 Beta 1
Firefox 3.6 Beta 1 is 9% faster than 3.5.4
Firefox 3.5.4 is 48% faster than Opera 10.10 Beta
on windows 7 RTM platform
Score: 0
|It would be easier to see if numbers weren't that inflated, being relative to IE7
Score: 0
|Last time , 3.6 Beta 1 Build 1 was 22.8% faster than 3.5.3 , but this time build 3 is just 9% faster than 3.5.4 ?? Is 3.5.4 that fast?? Or there is some flaw somewhere here?Im confused now...
Score: 0
|How fast is firefox 3.6 beta 1 than 3.5.4 ?? In % plz
Score: -3
|http://freeonlinecalculator.net/index.php
Score: -1
|sorry but i dont know how to calculate relative scores. is it [(11.73-10.58)/10.58]*100 ??
Score: -5
|