Compute and AI Benchmarks
Now some people don’t need a video card for gaming, they need the processing power for rendering or 2D/3D production, or in some cases, people who game also do work on the side. AI performance importance has increased quickly recently as well. So it is also important to check out the compute and AI performance on all of the video cards that come in. That includes doing a few different tests. In my first test, I ran Geekbench AI, a cross-platform AI benchmark that uses real-world machine learning tasks giving three results, a full precision score, half-precision score, and quantized score. The TUF Gaming RTX 5070 Ti OC improved on what we saw with the Prime by a noticeable margin here. Both cards were already up over the RTX 4080 and RTX 4080 SUPER so it didn’t change anything there.
Blender is always my favorite compute benchmark because the open-source 3D rendering software is very popular and it isn’t a synthetic benchmark. With the latest version of Blender, they redid the benchmark so we now have a new test that runs three different renderings and gives each a score. I have all three stacked together so we can see the overall performance. The TUF Gaming RTX 5070 Ti OC is slightly ahead of the Prime but even with a little more performance it wasn’t enough to catch up to the RTX 4080 or the RTX 4080 SUPER.
For CUDA-based cards, I also check out V-Ray Benchmark 5 to check out CUDA and RTX performance in the 3D rendering and simulation software. The TUF Gaming RTX 5070 Ti OC improved on the Primes CUDA result in v-Ray 5.02 by 24 points but interestingly it came in a hair below it in the RTX test. Both cards are sitting behind the RTX 4080 and out in front of last generation’s xx70 Ti with the RTX 4070 Ti.
