New iMac Benchmarks Show 10-25% Improvement Over Previous Generation

[N10248]

Clock for clock the old and new 21.5 2.7ghz ones are the same (lines 6 & 7).

[aliensporebomb]

Well, my 2009 27" iMac benches over 10,000:

See:
http://madsound.dyndns.org/geekbench.jpg

I want thunderbolt but honestly I'm happy with an optical drive and the firewire800 setup I have now works but I wish I had faster i/o (thunderbolt obviously).

Then I could boot off an external drive and not have to wait eons or do multichannel audio or video editing off an external drive without wanting to gouge my eyes out waiting.

I'll wait to see what benchmarks come from the 27" i7 bto model.

[till213]

And now... ladies and gentlemen! Let's wait for next summer, enjoy high outside temperatures and let's then measure the heat emission of those nicely compressed iMacs! Unless you live at either North or South Pole, that is...

[namethisfile]

Originally Posted by cgdrennan

You post in ignorance my friend. They have already done tear downs of the new iMac and it is very user upgradable... Hard drive, ram, and even the fact that the CPU is not soldered. The screen is held on by magnets like the previous model but since the LCD is laminated to the glass it is easier to get in to.

wait, so the 2012 21" iMac has upgradeable ram and hdd? if one is willing to take it apart?

i thought the RAM was soldered like the MBA's?

i am asking because the top-end 21" iMac with BTO i7 cpu looks enticing. i am only hesitant because of a couple of components such as adding ram is $200 upgrade and 5400rpm HDD needs to be replaced. and oh, no more firewire. and skeptical of the 512 mb VRAM.... the dream iMac tho after the 21.5" iMac is hooked up will only just be a couple of hundred dollars more with the BTO i7 & 680mx.... plus it comes with a 7200rpm hdd....

seems like apple really wants to draw the line between power-user and cute-user, for the lack of a better word.

[NachoGrande]

right now my late 2010 is a complete dog, but that's not enough to upgrade.

[madrag]

Glad I got the top Mac Mini...

Also glad that they mention that it is a good buy compared to the iMac.

[BeamWalker]

One Generation further and the iMacs get 2010 Mac Pro 8 Core Speed. I really thought they would manage this this time around though.

With the big Retina Macbook Pro at more than 12.000 points, the question now is, is the iMac CPU too slow or the notebook cpu line too fast.

[WardC]

My 2011 Sandy Bridge 27" beats all of those:

[AcesHigh87]

I'll keep my 2011 model, thanks. Yeah, the 27" ones will likely be a lot better than this but that's less than a 15% increase in score over my current 21.5" iMac and way too much lost to account for.

[madrag]

Originally Posted by namethisfile

wait, so the 2012 21" iMac has upgradeable ram and hdd? if one is willing to take it apart?

i thought the RAM was soldered like the MBA's?

i am asking because the top-end 21" iMac with BTO i7 cpu looks enticing. i am only hesitant because of a couple of components such as adding ram is $200 upgrade and 5400rpm HDD needs to be replaced. and oh, no more firewire.

I doubt it, maybe the HDD. Even if the RAM and HDD are upgradeable, it must be very painfull to get there.

I agree with all you said, why no FW?
Oh and no audio input, is that true? (now the iMac is here someone can finally confirm that)

[CausticPuppy]

Were people really expecting more than 15% performance increase with the move from Sandy Bridge to Ivy Bridge?

The IB CPU benchmarks have been out for a long time.

[pedromartins]

Originally Posted by Naimfan

No, it isn't. Apple specifies that there are no user-serviceable parts inside (RAM on the 27" excepted). So if you want to void the warranty, have at it.

You post in ignorance, my friend . . .



Also - my Late 2011 base MBP is faster than all the iMacs listed save the top two. A desktop should smoke a laptop . . .

Blame intel for that. After all only CPU is being measured. What's your ******** problem?
This is by far the best AIO you can buy.

[dlewis23]

Originally Posted by robjulo

Only a 15% improvement while removing key components? No thanks.

What key components?

[WardC]

Their tests are bunk, because as I have shown, the top-end 3.4GHz 2011 model is actually faster than the top-end 21.5" -- their readings are not accurate, or they ran the 32-bit tests and not the 64-bit tests (this is what I am guessing).

[ronm99]

Originally Posted by wildspin

Just curious ... are these result with or without the contributions of fusion drives?

My understanding is that Geekbench tests are CPU bound and don't really take the disk into account at all. That is one of the reasons I don't like Geekbench. The other is that Geekbench over emphasizes multi core. The Geekbench numbers are very realistic for threadble CPU intensive tasks, but very unrealistic for typical use.

[xgman]

I am very interested to see what score a 27" 3.4ghz maxed out will bring.

[WardC]

Originally Posted by xgman

I am very interested to see what score a 27" 3.4ghz maxed out will bring.

The one I just posted IS a maxed-out 3.4GHz model, albeit a 2011 one.

The difference is Sandy Bridge vs. Ivy Bridge.

[xgman]

Originally Posted by ronm99

My understanding is that Geekbench tests are CPU bound and don't really take the disk into account at all. That is one of the reasons I don't like Geekbench. The other is that Geekbench over emphasizes multi core. The Geekbench numbers are very realistic for threadble CPU intensive tasks, but very unrealistic for typical use.

You are right. Way too much emphasis on multiple cores. Everyday stuff will noticeably faster via ghz speed faster rather than ghz slower and more cores, at least to a point.

[IGregory]

Originally Posted by xgman

I am very interested to see what score a 27" 3.4ghz maxed out will bring.

What difference does it make. Ninety percent of you don't need all that horsepower anyway.

[iamgalactic]

Originally Posted by WardC

My 2011 Sandy Bridge 27" beats all of those:

yes, and the 2012 i7 27" will beat that

[Lone Deranger]

Originally Posted by JaySoul

Lost too much weight. Not enough calories to run fast.

Nice analogy.

Meanwhile, my old, fat, 2010 Mac Pro still runs circles around these new anorexic iMacs, when and where it matters.

[namethisfile]

Originally Posted by AcesHigh87

I'll keep my 2011 model, thanks. Yeah, the 27" ones will likely be a lot better than this but that's less than a 15% increase in score over my current 21.5" iMac and way too much lost to account for.

i was close to getting that imac a year ago and went with the 2011 mac mini. the quad-core and hyper-threading and beefier gpu (compared to the middle 2011 mac mini) would have been more consoling that my computing needs are good for a while. as it is, my dual-core macs are envious of the newer quads. oh well....

[xgman]

Originally Posted by IGregory

What difference does it make. Ninety percent of you don't need all that horsepower anyway.

I'm firmly fixed in the 10%. No actually, I'm in the 5%.

----------

Originally Posted by WardC

The one I just posted IS a maxed-out 3.4GHz model, albeit a 2011 one.

The difference is Sandy Bridge vs. Ivy Bridge.

I'm guessing roughly 10-15% + then.

[WardC]

A good example of seeing how Geekbench scores are skewed like this is looking at a 12-core Mac Pro with a hard disk versus a MacBook Air with an SSD. The MacBook Air may boot and feel snappier for most all tasks, and navigating the OS, launching apps will be faster....but the Mac Pro will have the advantage for processor-intesive tasks like compressing video.

And the Mac Pro will score probably 3-4x higher on Geekbench!!! Just because it has 6x as many cores.

[flavr]

My 2009 27in quad i7 still has a score that compares to these overall (8500) give or take....guess im stickin with my current setup