News RTX 5090 beats RTX 4090 by 36% in the Blender benchmark — RTX 5090D is 40% faster than RTX 4090D

[Admin]

Benchmarks for the RTX 5090 and the 5090D were leaked to the Blender benchmark database, showing the cards are modestly faster than the RTX 4090.

RTX 5090 beats RTX 4090 by 36% in the Blender benchmark — RTX 5090D is 40% faster than RTX 4090D : Read more

 

[jp7189]

Every article about the 5090 is the same.. we get it. Multiply everything about the 4090 by 1.33333 and you get a 5090.. cores, vram, power, price, performance.... and so on.

Oh.. and we get fp4 support.

 

[Pierce2623]

How can the 5090D be any faster at native without falling afoul of restrictions? Wasn’t the 4090D right on the limit? Or is the fp32 compute about the same and the 40% faster is using frame gen BS?

 

[OldAnalogWorld]

We've already discussed this - now normalize the performance of the 5090 relative to the 4090, taking into account the difference in consumption (575W vs 450W). And it turns out that the difference in performance is ridiculous - only +5-10%. And this is with a significantly higher price and huge heating of the room even with the 4090...

 

[dipique]

We've already discussed this - now normalize the performance of the 5090 relative to the 4090, taking into account the difference in consumption (575W vs 450W). And it turns out that the difference in performance is ridiculous - only +5-10%. And this is with a significantly higher price and huge heating of the room even with the 4090...

That's like normalizing horsepower on cars to fuel economy. No, a 400hp car @ 17mpg is not about the same as a 200hp car at 34mpg. Those cars are obviously for different people, and one of them obviously costs (and should cost) more.

 

[ihateregister]

Synthetic tests in blender have absolutely nothing to with texture heavy video games. Also, it's pointless to check specs on 5090. The rumor mill is that it's another paper launch. There will be no 5090s for sale at launch.

 

[Alvar "Miles" Udell]

But the 5090 can predict the future and generate multiple fake frames so it doesn't need to actually be faster!

 

[Joseph_138]

What the heck is a 4090D? Is it a disabled card for the Chinese market, like the RX 7900 GRE?

 

[AndreX86]

It's about 23% faster than my stable and overclocked OC 4090 AERO. That being said overclocking the 5090 might lead to some interesting results. Think i'll wait for the 6090 and AMD ****X3D @ 6GHZ before I upgrade again, barring the 6090 isn't $2.5k.

 

[Peksha]

That being said overclocking the 5090 might lead to some interesting results.

For example, to melting of the power connector😉

 

[Phaaze88]

What the heck is a 4090D? Is it a disabled card for the Chinese market, like the RX 7900 GRE?

Yep. 4090D(ragon).

 

[Prow99]

Very sad indeed. 33% more cores and the same in performance uplift. No architectural improvement here whatsoever. No better node at tsmc. No IPC gain. Potentially worse performance per watt. This 5000 series is a flop.

Worse yet is the 5080 that now is only half of a 5090. Remember when the 80 series was always a cut down of the top tier 90 die? Like the 3080 which had 80 to 85% performance of the 3090? That's where the best bang for the buck used to be. Now greedy Nvidia wants to screw all us gamers with this joke of a 5080. I say none of us buy it and we wait for the 5080ti/super which should be a cut down 5090 with a respectable amount of vram. Just doesn't make any sense to go from a 3080 to this laughable 5080 imo.

 

[DeNachtwacht]

@Admin

For version 4.3, today 4 other records have been added to Blender Benchmark, so that makes four 5090s tested (and one in 3.6). Each of these four scores around 14.800, and one as low as 13833. With the highest 4090s scoring up to 12.600 the difference is much smaller then 40%. There may be some room for tweaking the 5090, but bear in mind that in this hierarchy:
https://opendata.blender.org/benchmarks/query/?compute_type=OPTIX&blender_version=4.3.0

we'll find my 4090 benchmarked today on page 3, (place 51) with a score of 11565.45.

Yup, proud to be me

But did I tweak and watercool? Not at all. This is a 4090 set to 80% Power Limit, but with core clock set to +125 and memory clock to +1700. So basically a slight performance tweak, no serious overvolting and overpowering etc. And it's installed in a DDR4 system with 5950X cpu, so not quite the latest and fastest. The median score of 10.500 is misleading here...

So these four 5090s scores score about 28% faster than my quite normal 4090 in the same 4.3 benchmark.