Core i7 7700k benchmark

[Coaxialgamer]

11 hours ago, TheKDub said:

Interesting, considerably higher score than the i7 6700k

Single Core:

i5 6600k: 5309
i7 6700k: 5822
i7 7700k: 6131

 

Multi-Core:

i5 6600k: 14568
i7 6700k: 19437

i7 7700k: 20243

 

i5 6600k: https://browser.primatelabs.com/v4/cpu/620296

i7 6700k: https://browser.primatelabs.com/v4/cpu/621525

i7 7700k: https://browser.primatelabs.com/v4/cpu/583064 (Same as in the main post)

 

Hopefully that'll mean some real world performance increases lol

Well it has a 5% higher clock speed and a ~5% higher ipc,  so it makes sense. 

[Enderman]

59 minutes ago, Morgan MLGman said:

Didn't you just calculate that it's actually 2/3rd the difference between the 4790K and 6700K? How is that "just as large" That's 33% lower.

 

One of the values was 66%, the other value was 200%, that is an average of over 100%.

Even if we take the minimum, 66%, that is still a very big improvement.

66% of the performance difference between the 4790k and 6700k is still very significant if you've ever seen 4790k vs 6700k benchmarks.

[PlayStation 2]

Dunno why people are surprised that Kaby Lake is barely faster than Skylake. This is basically supposed to be like what Broadwell was, improving efficiency and the iGPU.

[Jv2391]

I don't see anything here that will warrant anyone jumping on the purchase bus when this is released. Unless these are just the stock numbers where it can do incredible processing on overclock that blows everything else out of the water at an affordable price I will stick with my 6800k.

[Electronics Wizardy]

1 hour ago, Sauron said:

also die shrink

Same size, just optimized.

[Sauron]

14 minutes ago, Electronics Wizardy said:

Same size, just optimized.

ah right, tick tock is dead

[Sauron]

54 minutes ago, Jv2391 said:

I don't see anything here that will warrant anyone jumping on the purchase bus when this is released. Unless these are just the stock numbers where it can do incredible processing on overclock that blows everything else out of the water at an affordable price I will stick with my 6800k.

I don't think they expect people to upgrade from skylake. In fact, there's not much reason to upgrade from sandy bridge yet to be honest.

[Jv2391]

Just now, Sauron said:

I don't think they expect people to upgrade from skylake. In fact, there's not much reason to upgrade from sandy bridge yet to be honest.

Completely agree. I don't know what this line's targeted audience is? Is it supposed to do more? Because the numbers don't show it. Is it supposed to be a more affordable option? Because the i7 6000 series is relatively affordable at this point. So I don't know why they are putting these out. It's almost as if hardware in the CPU world is the new CoD or EA sports game. Same thing every year, minor improvements, it gets the job done, but it's the price of buying the new one last year.

[Space Reptile]

the fact that this chip is running on a Z170 makes it dodgy , i thought it needs a 200 series 

[MageTank]

11 hours ago, Lays said:

Ran it again a few times with more things closed, I think the multi-core score on their run is still goofy somehow, my single thread is much higher so the multi-core should be higher too, I'd think.

@MageTank what do you think?

 

I think the test is a joke. I tested my setup, which is a 6700k at completely stock clock speeds (nothing touched at all, other than my 3600 C14-14-14-28-2 memory overclock) and I am scoring within 5.5% of your multi-core score? Considering you have nearly a 20% higher clock speed than I do, that sounds like nonsense to me. 

 

Here are my results: https://browser.geekbench.com/v4/cpu/628225

 

http://valid.x86.fr/a1sbyc

 

Now, I did test my ram at its XMP speeds (3200 C14-14-14-35-2) and noticed that memory performance does play a big part in the final score. Here is the XMP results: https://browser.geekbench.com/v4/cpu/628167

 

Still, I would not take this benchmark seriously at all. 

[Master Disaster]

13 hours ago, NumLock21 said:

Not much info on it. Just a leaked benchmark on the upcoming Intel Core i7 7700K based on the Kaby Lake architecture

 

https://browser.primatelabs.com/v4/cpu/583064

To be fair, on the multi core performance that's a fair increase over the 6700K, my 6700K at stock gets around 17,500 points. 

 

Single core performance is about 400pts increase, oh dear, I can break that with the easiest overclock possible (4.4Ghz with no voltage increase at all). 

 

It's great if your building but as an upgrade, same shit different day Intel, just not worth the cost. 

[Sauron]

57 minutes ago, Jv2391 said:

Completely agree. I don't know what this line's targeted audience is? Is it supposed to do more? Because the numbers don't show it. Is it supposed to be a more affordable option? Because the i7 6000 series is relatively affordable at this point. So I don't know why they are putting these out. It's almost as if hardware in the CPU world is the new CoD or EA sports game. Same thing every year, minor improvements, it gets the job done, but it's the price of buying the new one last year.

There's also the "why not" component. If they couldn't bring out a major improvement they might as well refresh the lineup with more optimized versions of the same thing.

[Jv2391]

2 minutes ago, Sauron said:

There's also the "why not" component. If they couldn't bring out a major improvement they might as well refresh the lineup with more optimized versions of the same thing.

Just seems like a waste of materials. Would prefer to see them blow us away every few years, instead of mildly amuse us every 6 months.

[Sauron]

23 minutes ago, Jv2391 said:

Just seems like a waste of materials. Would prefer to see them blow us away every few years, instead of mildly amuse us every 6 months.

What waste of materials? It's not like they stop production inbetween releases, there's always demand for new cpus. It also doesn't cost them much to reprogram the machines for a new line if they aren't even changing the process node.

[Guest]

I am gonna sit here with my non oc 4460 i5

[Mira Yurizaki]

I saw a WFFCtech (I'm not going to bother getting their name right) report on this and they were claiming "40% better" benchmarks with the i7-6700K getting 4000ish and the i7-7700K getting 6000ish. Considering people here are not getting that score it means that site is a crock of poo. Or Geekbench is a crock. Or both.

[TheKDub]

15 hours ago, MageTank said:

This is exactly it. There isn't a "10-15% improvement". I don't get where people keep pulling that number from. 

 

From these scores, we see nearly a 5.5% increase in single core performance. The difference between the 6700k and 7700k's single core boost clock speed is 300mhz, a 7% difference. While perfect scaling seems impossible, it's safe to assume that the 7% increase in clock speed is completely responsible for this 5.5% increase in single core performance, not an IPC advantage.

 

Let's look at the multi-core to be certain. Difference in clock speed? 200mhz (4.0 6700k vs 4.2 7700k) which is a 5% difference in clock speed. The difference in the scores however, was a 4% difference in multi-core. Again, safe to assume this comes entirely from the 5% difference in clock speed. 

 

I am not quoting you to call you out @TheKDub, your post just has the relevant information for me to do this math. You may or may not agree with me, I was just quoting it so others could see where my math is coming from.

 

This is yet another confirmation that people should not worry about Kaby Lake if they already own a high end Skylake machine. Now, if you are upgrading from something older, obviously Kaby Lake is a better option depending on how it's priced vs Skylake, but it's just not a viable upgrade option if you already have Skylake. Until we see how this new fin design works, and the impact it has on overclocking, I wouldn't get my hopes up for the previously reported gains. 

 

It indeed is very possible that the increase is from the clock speed alone, if there's anyone with a 6700k that could run some benchmarks with the same clock speeds as the 7700k, then that'd answer that question.

 

I'd like it if we saw some large improvements over the current CPUs, though I'm not likely going to bother with anything past Skylake with all the garbage about making windows 7 and 8.1 harder to install on Skylake and future CPUs.

[Avcn42]

Is there a launch date? 

[AresKrieger]

Didn't intel themselves say they were going to focus on efficiency and that performance would likely "plateau", if so this shouldn't be a surprise to anyone, intel has no reason to improve performance right now, even if zen does well I doubt it will beating intel in performance stats so they still will go slow and steady.  The only thing I can think might happen is a 6 core mainstream if push came to shove.

[patrickjp93]

1 hour ago, M.Yurizaki said:

I saw a WFFCtech (I'm not going to bother getting their name right) report on this and they were claiming "40% better" benchmarks with the i7-6700K getting 4000ish and the i7-7700K getting 6000ish. Considering people here are not getting that score it means that site is a crock of poo. Or Geekbench is a crock. Or both.

In the wccf article, they compared an old GB 3.0 score to a new GB 4.0 score.

[Mira Yurizaki]

1 minute ago, patrickjp93 said:

In the wccf article, they compared an old GB 3.0 score to a new GB 4.0 score.

So in other words, everyone needs to stop reading their articles.

[tonyeezy]

23 minutes ago, Andrevcn said:

Is there a launch date? 

 

This.

 

I do plan on upgrading actually. However I will be going from a Sandy Bridge i5-2500k to i7-7700k.

[MageTank]

1 hour ago, TheKDub said:

 

It indeed is very possible that the increase is from the clock speed alone, if there's anyone with a 6700k that could run some benchmarks with the same clock speeds as the 7700k, then that'd answer that question.

 

I'd like it if we saw some large improvements over the current CPUs, though I'm not likely going to bother with anything past Skylake with all the garbage about making windows 7 and 8.1 harder to install on Skylake and future CPUs.

That's the problem. We have people like @Lays running a 5ghz 6700k, scoring only 140 points higher on the multi-core test, and people like myself with a 20% lower clock speed, only scoring 5% lower on the multi core test. The test itself seems flawed. Not only that, we don't know the real clock speed that was tested. Geekbench does not report the actual clock speed. In Lays 5ghz result, it shows "6700k @ 4ghz" which means its only reading the DMI string, not current clock speeds.

 

For all we know, this could be an overclocked 7700k being tested by an AiB or Intel themselves. We also know that memory speed improves the score of this test, but we have no way of knowing who is running what speeds, because the test itself does not specify the memory configurations. I can tell you right now that the memory benchmark itself is inaccurate compared to every other memory benchmark I use, as my ram runs at 53GB/s on average, not 44GB/s. My memory copy speed is also 51GB/s, not 29GB/s. 

 

If it were not for the fact that my 6700k is in an ITX case with a tiny ITX cooler, I would gladly OC to 4.5ghz and test again, but It would be risky for me to do so. I'll see if I can improve thermals enough to give it a try later on tonight. I just don't expect it to do much, after seeing Lays results. His system is better than mine in every regard and only barely managed to beat the 7700k in multi-core. 

 

EDIT: Okay, I went ahead and went for it. This is my result at 4.5ghz.

 

https://browser.geekbench.com/v4/cpu/631193

 

 

Proof of my clock speeds: 

 

Ignore the vcore, this was a very quick and dirty run. No doubt this is unstable under real stress too, but it does show us something. On my very clean Windows 10 install, my score at 4.5ghz is extremely close to that 7700k at the exact same all-core boost clock speed of 4.5ghz. Within margin of error, as my multi-core is slightly faster, and single-core slightly slower. This should put that IPC rumor to rest.

 

@Lays you may want to do a clean install on a backup drive and test again if you want the best possible score. Seems background applications impact the score.

[patrickjp93]

1 hour ago, M.Yurizaki said:

So in other words, everyone needs to stop reading their articles.

No, because most of their articles are good. The author made a mistake, and the article has been taken down because of this error.

 

Hold their feet to the fire, but be willing to forgive. Should everyone stop reading my programming blogs if I make a mistake one time when all the remaining content is very helpful and informative? Should I stop reading Microsoft's optimization guides just because it has the worst compiler for optimization? No.

[Mira Yurizaki]

Just now, patrickjp93 said:

No, because most of their articles are good. The author made a mistake, and the article has been taken down because of this error.

 

Hold their feet to the fire, but be willing to forgive. Should everyone stop reading my programming blogs if I make a mistake one time when all the remaining content is very helpful and informative? Should I stop reading Microsoft's optimization guides just because it has the worst compiler for optimization? No.

When it comes to speculation however, they seem to reek of stirring up the rumor mill more so than most other sites for hits.