RTX 3070 results appear on Geekbench, suggest it will outperform the RTX 2080 Ti

[midian182]

What just happened? There’s a lot of excitement surrounding next week’s launch of the RTX 3070, a $500 card offering what’s alleged to be similar levels of performance as the RTX 2080 Ti. But will it really be on par with the Pascal flagship? Leaked benchmarks suggest that Nvidia's claims aren't exaggerations.

The two Geekbench 4.0 benchmarks come from regular leaker @TUM_APISAK (via Tom’s Hardware). They both use the same system: Intel Core i9-10900K, ROG MAXIMUS XII EXTREME motherboard, 16GB DDR4, and the 8GB RTX 3070.

One of the tests brought an OpenCL score of 359,349, while the other result is 350,093.

RTX 3070 - OpenCLhttps://t.co/SJycgQPhpphttps://t.co/PWQJ1R2z8N pic.twitter.com/GivkxWMS08

— APISAK (@TUM_APISAK) October 21, 2020

As noted by Twitter user @Sebasti66855537, most of the RTX 2080 Ti results on Geekbench 4.0 lie somewhere between the 345K and 355K mark. Tom’s confirmed this is the case, though it pointed out that there are outliers significantly higher and lower the RTX 3070 scores.

Based on Nvidia’s chart comparing the RTX 3070, RTX 2070, and RTX 2080 Ti, the upcoming card is, on average, around 8 percent faster than $1000+ last-gen product and 68 percent faster than the 2070.

Nvidia will have cherrypicked the games and apps that favor the RTX 3070, of course, and two Geekbench results don’t tell the whole picture.

Responding to a question on whether the RTX 3070 is “better” than the RTX 2080 Ti, APISAK said they believe the latter card is the better of the two, except when it comes to ray tracing.

The RTX 2080 Ti has 4,352 GPU cores, 272 texture units, and 88 ROPs, while the RTX 3070 has 5,888 cores, 184 TMUs, and 96 ROPs. Other early benchmarks have also suggested the new card will have the edge, though if the launch is anything like the previous RTX 3000-series, the worst element of the RTX 3070 will be getting hold of one—a scenario AMD is trying to avoid with its Radeon RX 6000 series.

We’ve also heard that Nvidia is working on a 16GB version of the RTX 3070, but new rumors claim the alleged December launch of both this card and the 20GB RTX 3080 have been canceled.

Permalink to story.

https://www.techspot.com/news/87236-rtx-3070-results-appears-geekbench-suggesting-rtx-2080.html

 

[Kazkas]

I would not call it "outperform" - it's only 2 tests and I'd say their average is on par with 2080ti average (including error and fluctuation). Also, keep in mind 2080ti has +3Gb (and in some situations it matters quite a lot).
However, I don't call it a bad result! I'd say it's amazing for 1 generation to lower the price twice (for almost same performance)!

 

[Vulcanproject]

I'm curious about Big Navi now. These Ampere cards on Samsung's 8nm process seem to use rather a lot of juice. Granted they are actually the best performance per watt GPUs available, they aren't inefficient.

But I get the sneaking feeling Samsung's 8nm process used is not entirely suited or optimised quite as well as TSMC's 7nm particularly for power consumption at high performance.

I was looking at the power draw figures for Xbox Series X and although the software available to test is limited, it only hit 211 watts. That's pretty impressive for an entire SoC with what is basically an 8 core Renoir Zen 2 and a GPU that is faster than a 5700XT on it. Even if the machine can actually hit 250 watts with new high end games it has excellent power efficiency.

It bodes very well for Big Navi. I think the 3070 is going to have extremely stiff competition.

 

[QuantumPhysics]

When you say “outperform” all I’m interested in is that you can simply turn all settings up to “ultra” and run at 4K resolutions.

I am absolutely not interested in the how well it runs those benchmarkers - even though I’m sure it can probably do well on them.

What I want to see is how well it runs Microsoft flight simulator 2020 compared to the 2080 TI in 4K.

How well does it run Crysis remastered?

How well does it run DCS world ?

How well does it run Cyberpunk 2077?

 

[BadThad]

The 3070 exemplifies why spending over $1000 on a video card is just plain dumb.

 

[Evernessince]

I'm guessing in actual games it performs between a 2080 and 2080 Ti. The whole Amepre lineup has high theoretical performance that doesn't translate nearly as well to real world games compared to previous Nvidia cards.

The 3070 Ti will likely be where the majority of people are going to want to buy at. Enough gains over the 1080 ti while not being overly power hungry.

 

[toooooot]

I am way more excited for RX 6800 XT. I want it to be a killer so bad! But then, if it is, it will be bought out by crypto miners like 5000 series today due to cursed coin rising.
There is a rumor that rx 6800 got better scores in a bench than 3070.
Cant wait to know more about that too.

 

[Karl Hungus]

I am way more excited for RX 6800 XT. I want it to be a killer so bad! But then, if it is, it will be bought out by crypto miners like 5000 series today due to cursed coin rising.
There is a rumor that rx 6800 got better scores in a bench than 3070.
Cant wait to know more about that too.

Yes, I'm waiting for everything to be out and fully benchmarked. The 'majority' of gamers (not the tiny slice of gamers that inhabit these forums) will be looking hard at cards like the 3060ti. If it comes out with 2080 Super performance for $399 USD, that's a pretty sweet spot to be in. Again, for the majority (like 97%) that don't care about playing at 4K and have other things in life to spend their money on. I'm hoping AMD doesn't release trash drivers again and can form some sort of competition. Price/performance they will be there as always.