Sandy Bridge-E Benchmarks Leaked: Disappointing Gaming Performance?

[qubit]

Just a handful of days ahead of Sandy Bridge-E's launch, a Chinese tech website, www.inpai.com.cn (Google translation) has done what Chinese tech websites do best and that's leak benchmarks and slides, Intel's NDA be damned. They pit the current i7-2600K quad core CPU against the upcoming i7-3960X hexa core CPU and compare them in several ways. The take home message appears to be that gaming performance on BF3 & Crysis 2 is identical, while the i7-3960X uses considerably more power, as one might expect from an extra two cores. The only advantage appears to come from the x264 & Cinebench tests. If these benchmarks prove accurate, then gamers might as well stick with the current generation Sandy Bridge CPUs, especially as they will drop in price, before being end of life'd. While this is all rather disappointing, it's best to take leaked benchmarks like this with a (big) grain of salt and wait for the usual gang of reputable websites to publish their reviews on launch day, November 14th. Softpedia reckons that these results are the real deal, however. There's more benchmarks and pictures after the jump.







View at TechPowerUp Main Site

 

[qubit]

Thanks to Damn_Smooth for this awesome lead!

 

[lilhasselhoffer]

So, what do Chinese benchmarks matter?

Before anyone else points it out, we've heard the same from Tom's Hardware. Even taking it with a grain of salt, this seems sadly disappointing. Not disappointing enough to forego a ramdisk and awesome video processing, but definitely disappointing.

 

[n-ster]

I'll take this with a grain of salt... Besides, we know many games are GPU intensive

btw, Power consumption, more is better... yup very trustworthy lol

 

[bear jesus]

I thought the architecture was really similar to the normal sandy bridge but with more cores so most games (single to 4 core using ones) would perform exactly the same at the same clocks?

*edit*
I forgot about the dual threading, would that possibly mean ones that use up to 8 threads could perform the same on a 2600k and 3960X?

 

[Bundy]

I thought the architecture was really similar to the normal sandy bridge but with more cores so most games (single to 4 core using ones) would perform exactly the same at the same clocks?

*edit*
I forgot about the dual threading, would that possibly mean ones that use up to 8 threads could perform the same on a 2600k and 3960X?

I agree. If they clock similarly at stock, they will perform similarly. These chart prove what we already know.

 

[EastCoasthandle]

Power consumption chart reads: More is better
Wait, what?

 

[ShRoOmAlIsTiC]

same reason why the bulldozer was a so called fail. these new processors will be better when more games are made for 6+ cores. plus it looks like the benchies were gpu limited.

 

[Jstn7477]

If these are correct (which if you remember all the Bulldozer "benchmarks" that were BS, probably not) then it just goes to show how great Intel's current "Performance" platform (LGA 1155) is for current, realistic workloads. I'm sure some of us here have the $$$$ to throw at an "Extreme" LGA 2011 SB-E rig, 32GB of DDR3 and >9000 GTX 580 graphics cards to show off some fancy benchmark scores or whatever, but for those looking for great (but not maximum) performance in games and everyday tasks with sane pricing, I wouldn't be skeptical of what is supposed to be a mid-range platform that has already proven itself for nearly a year.

 

[arnold_al_qadr]

power consumption, more is better??

 

[John Doe]

I thought the architecture was really similar to the normal sandy bridge but with more cores so most games (single to 4 core using ones) would perform exactly the same at the same clocks?

Higher IPC so you may need higher clocks to make up for in theory

*edit*
I forgot about the dual threading, would that possibly mean ones that use up to 8 threads could perform the same on a 2600k and 3960X?

HT actually decreases gaming performance. Games don't concurrently scale over 4 multiple cores, as it's just a few threads getting thrown across, which is one of the reasons why BD is underperforming.

Some people still haven't realized 2500k is the way to go. 2500k and a solid GPU. Anything else isn't worth it unless you simply want the best, or can't afford it.

 

[1c3d0g]

Uhm, duh. If you're after gaming, you should go for Ivy Bridge, Haswell etc. If you're doing heavy lifting like HD video processing, BOINC/Folding@Home, in short anything that needs more processing power than a quad core can offer, then, and only then, is the Sandy Bridge-E for you.

 

[Jstn7477]

Power consumption chart reads: More is better
Wait, what?

Only during Winter (and maybe on Thursdays).

I'm enjoying my rig keeping my room warm while it does Folding@Home. Who needs heaters, anyway?

 

[qubit]

Power consumption chart reads: More is better
Wait, what?

Yeah, good innit?

 

[erocker]

btw, Power consumption, more is better... yup very trustworthy lol

Lol, that's the first thing I noticed too.


I have doubts about these "slides" or whatever they are. If they are real.. "Dissapointing gaming performance"? Really? Since the SB platform can handle a GPU and the most demanding of games just fine, I don't see how having a SB-E or a processor two times the performance of that is going to make any difference. How about "SB-E benchmarks leaked" for a title? I suppose one should understand that before making the statement that it dissapoints in games. X264 and Cinebench look to be promising. I see nothing disappointing about this chip with the information given.

 

[hat]

>power consumption
>more is better

 

[John Doe]

I have doubts about these "slides" or whatever they are. If they are real.. "Dissapointing gaming performance"? Really? Since the SB platform can handle a GPU and the most demanding of games just fine, I don't see how having a SB-E or a processor two times the performance of that is going to make any difference. How about "SB-E benchmarks leaked" for a title? I suppose one should understand that before making the statement that it dissapoints in games. X264 and Cinebench look to be promising. I see nothing disappointing about this chip with the information given.

Well the article isn't in English. If you read the THG article (who tested the platform), they say the chip isn't suited for gaming due to it's size. Higher TDP, slower per-clock and when it costs $1000, you have no reason to get it over a $250 chip. That is given your primary object is gaming.

 

[LAN_deRf_HA]

You guys make me want to bash my head against the wall sometimes. Leaked? Disappointing? Expectations are being met. Intel already showed us this. I am not linking to that damn preview again. Everyone should have seen it by now. X79 = people that need ass loads of ram. Nothing else.

 

[John Doe]

X79 = people that need ass loads of ram. Nothing else.

More like more cores (for renders and such) but...

X79 = people that need loads of ass.

can be said as well.

 

[Wile E]

These results do not look disappointing to me at all.

Since when is gaming the only relevant metric we measure cpus by?

 

[John Doe]

These results do not look disappointing to me at all.

Since when is gaming the only relevant metric we measure cpus by?

I do, as well many people. Any CPU can run Windows just fine. Gaming performance is what matters. Well unless you do editing work, which breaks the formula. People build their systems for games, not for much else.

 

[Wile E]

I do, as well many people. Any CPU can run Windows just fine. Gaming performance is what matters. Well unless you do editing work, which breaks the formula. People build their systems for games, not for much else.

Actually, gamers are in the minority for people that buy and build computers.

And x264 performance is way more important to me than gaming performance. Any modern cpu games just fine in most cases, but try re-encoding BD's on a 2500K compared to a hexacore with HT.

So, if you ask me, gaming is the least useful metric in determining a cpu's performance capability. The hardware is way ahead of the software in gaming right now.

 

[n-ster]

Power consumption chart reads: More is better
Wait, what?

power consumption, more is better??

>power consumption
>more is better

Yea I beat you all to it lol

More like more cores (for renders and such) but...

I'm doing for RAM as a main reason

These results do not look disappointing to me at all.

Since when is gaming the only relevant metric we measure cpus by?

Since CPUs are the most important thing because the difference between a Q9650 and a 2500K is the difference between a 3850 and a 6850.... oh wait

I meant since I beat Chuck Norris...

If you game only, most of the time 2500K is your best bet

 

[LiveOrDie]

looks fine to me no real bench marks of games that really use CPU power like RTS games.

 

[John Doe]

Actually, gamers are in the minority for people that buy and build computers.

And x264 performance is way more important to me than gaming performance. Any modern cpu games just fine in most cases, but try re-encoding BD's on a 2500K compared to a hexacore with HT.

So, if you ask me, gaming is the least useful metric in determining a cpu's performance capability. The hardware is way ahead of the software in gaming right now.

No, between the people here they aren't.

Also, you're wrong about the 2500k. Even in threaded situations, it's still capable of beating the Westmere architecture.

http://ixbtlabs.com/articles3/cpu/intel-ci7-limits-p2.html

If you ask me, I buy my CPU's mainly due to their gaming performance. That's what matters to people building PC's on these forums.