Apple iPhone 5s is the fastest smartphone according to benchmark tests

Just which smartphone is the fastest? According to Which magazines independent speed test, the Apple iPhone 5s beat out rivals like the Samsung Galaxy S4 to earn the title as the world's fastest smartphone using the Geekbench benchmark tests; in single-core testing, the full-featured iPhone had a huge margin over the LG G2, the second place finisher. The Samsung Galaxy S4 was third...
This is a discussion for a news article. To read the whole news, click here


43. bigstrudel

Posts: 574; Member since: Aug 20, 2012

Samsung cheats. Boosted benchmark results. Your phone actually scores in the 2500-2700 range. Which is still very good.

50. jacko1977

Posts: 428; Member since: Feb 11, 2012

i bet apple cheats too just no one can access the files in the phone lie cheat steal isn't that the apple saying

56. GeekyGene

Posts: 88; Member since: Aug 25, 2013

@jacko1977 Wow really? That's your argument... K.

123. saffant

Posts: 274; Member since: Jul 04, 2011

Yup they cheated on their pseudo-720p slowmo recording. That's 480p.

134. wildfiregt

Posts: 179; Member since: Jun 10, 2013

Well ,they did concerning the slowmo recording It's funny they said the 5s is twice faster than the 5 and it scores the double in Geekbench 3 Funnier that ,it is still behind android phones on Geekbench 2

69. darkkjedii

Posts: 30833; Member since: Feb 05, 2011

See post #56

79. blingblingthing

Posts: 890; Member since: Oct 23, 2012

I disagree. From what I read, the cores just operate at max clock speed without idling. If they temporarily were over clocked I would consider that cheating.

81. Ninetysix

Posts: 2933; Member since: Oct 08, 2012

It's cheating because it's using a whitelist to boost apps. You can "normalize" the score by just changing the name of the benchmark app.

84. willard12 unregistered

But the cores are indeed producing the score, correct? Or is it figuring out how to produce a false number?

85. Ninetysix

Posts: 2933; Member since: Oct 08, 2012

It sure is. Just like how the S800 on the L2 G2 is producing the score. The nexus 5 will also not have this boosting code and will score much lower. Whose score is correct?

98. apurb.lal

Posts: 13; Member since: Oct 17, 2013

have you even seen the leaked bench marks of nexus 5.... They are really good.. So, please dont speak without knowing...

114. blingblingthing

Posts: 890; Member since: Oct 23, 2012

Also, remember these phones are more than likely NOT running 4.3 android.

10. bugsbunny00

Posts: 2260; Member since: Jun 07, 2013

not even race not over yet, we still have NEXUS 5 Vs IPHONE 5s..

63. squallz506

Posts: 1075; Member since: Oct 19, 2011

Nexus 5 will take the crown, until the gs5 comes out.

83. tyger11

Posts: 285; Member since: Oct 29, 2012

Nexus 5 uses the same SoC as LG G2, so don't expect it to be any faster.

129. werthedroids

Posts: 60; Member since: Sep 15, 2013

something called software optimization out there

11. cj100570

Posts: 204; Member since: May 12, 2009

Lets stop the BS shall we? We all know that none of the benchmark apps to totally cross platform and synthetic benchmarks tell us absolutely nothing about how a device actually responds in real world conditions. In my possession I have the HTC One, iPhone 4s, iPhone 5s, Galaxy Note II, Galaxy S4, Galaxy Note 3, Nexus 4 and an LG G2. And know what? In day to day use each phone is fast at opening applications, moving between screens, booting up, etc. and rarely if ever have any kinds of slowdowns to sully the experience.

20. tedkord

Posts: 17131; Member since: Jun 17, 2009


61. Allfonefan

Posts: 4; Member since: Sep 06, 2013


68. datphoneguy

Posts: 155; Member since: Sep 15, 2013

If you really own all those phones....can you adopt me? :P

13. abhi12345

Posts: 14; Member since: Sep 16, 2013

Note 3 also did not beat iphone 5s. The exynos model of note 3 is slower in geekbench 3. Note 3 s800(587 ms) also lost to iphone 5s(403 ms) in sunspider tests. The only benchmarks note3(s800) has beaten iphone 5s is glbenchmarks. Overall iphone 5s is best and fastest phone than both note 3 models.

28. tedkord

Posts: 17131; Member since: Jun 17, 2009

Note 3 beats the 5s in multi core.

77. Ninetysix

Posts: 2933; Member since: Oct 08, 2012

Lets rename geekbench to lowerscorebench and watch the Note 3's score drop by 20-50%. Awesome right?

91. tedkord

Posts: 17131; Member since: Jun 17, 2009

Why do you insist on throwing out false numbers? Anand found that the benchmark priming Samsung did boosted numbers less than 5% in nearly all instances. They specifically stated that the process wasn't worth doing because they boost was almost nonexistent.

95. Ninetysix

Posts: 2933; Member since: Oct 08, 2012

What kind of magic did samsung put in the S800? False numbers? Lol... To see how some other benchmarks are affected, we made "stealth" versions of those, too—the exact same app, just with a different package name. These results back up the Geekbench findings: we're seeing artificial benchmark increases across the board of about 20 percent; Linpack showed a boosted variance of about 50 percent

130. tedkord

Posts: 17131; Member since: Jun 17, 2009

Try Anandtech. 0 to 4% gain on average. A rare few got as high as 10%. Are is a good site, head and shoulders and torso and toes above BGR, but for in depth writing on this stuff, Anandtech is the way to go.

38. Shatter

Posts: 2036; Member since: May 29, 2013

Sunspider is a browser benchmark and it is not reliable go run puffin on your android phone it will score a 150-250 in sunspider no matter what the hardware is as long as its decent.

14. alaw.14

Posts: 414; Member since: Sep 10, 2013

twens you are right there is a video on youtube showing the note 3 scores 3000 and the z1 scores 2700 on geekbench 3 beating the iphone 5s 2500.

25. twens

Posts: 1163; Member since: Feb 25, 2012

I know am right cos I own a note 3 exynos version. I can even post my benchmarks if anyone doubts the note 3 scores.

19. jove39

Posts: 2140; Member since: Oct 18, 2011

Apple's cyclone core in A7 is certainly best (and perhaps only commercially available) implementation of ARM's v8 instruction-set. I am very much impressed with single core result of geekbench - MSM8974-krait 400@2.26GHz: 882 A7-cyclone@1.3GHz: 1410 cyclone core is outperforming krait400 while running at 1.7x less frequency...that's amazing work done by Apple's engineering team.
This copy is for your personal, non-commercial use only. You can order presentation-ready copies for distribution to your colleagues, clients or customers at or use the Reprints & Permissions tool that appears at the bottom of each web page. Visit for samples and additional information.