Why you can trust Tom's Hardware Our expert reviewers spend hours testing and comparing products and services so you can choose the best for you. Find out more about how we test.
Nvidia RTX 5070 Founders Edition: Content Creation, Professional Apps, and AI
Modern GPUs like the RTX 5070 aren't just about gaming. They're used for video encoding and professional applications, and increasingly, they're being used for AI. We've revamped our professional and AI test suite to give a more detailed look at the various GPUs. We'll start with the AI benchmarks, as those tend to be more important for a wider range of users.
Procyon has multiple AI tests, and we've run the AI Vision benchmark along with two different Stable Diffusion image generation tests. The tests have several variants available that are all determined to be roughly equivalent (in output) by UL: OpenVINO (Intel), TensorRT (Nvidia), and DirectML (for everything, but mostly AMD). There are also options for FP32, FP16, and INT8 data types, which can give different results. We tested the available options and used the best result for each GPU.
Procyon has finally received the necessary update to run the TensorRT workloads on Blackwell 50-series GPUs. As we've seen in some of the other test results, the 5070 FE ranks about 20% ahead of the 4070 in Stable Diffusion, but still comes in clearly behind the 4070 Ti. It's also quite a bit faster than any AMD GPU at present, but we'll have to see if RDNA 4 can change that tomorrow.
The AI Vision test received some updates to the CUDA code that clearly boosted performance on the 50-series GPUs, but it seems we'll need to retest the 40-series cards as their results now appear outdated.
ML Commons' MLPerf Client 0.5 test suite does AI text generation in response to a variety of inputs. There are four different tests, all using the LLaMa 2 7B model, and the benchmark measures the time to first token (how fast a response starts appearing) and the tokens per second after the first token. These are combined using a geometric mean for the overall scores, which we report here.
While AMD, Intel, and Nvidia are all ML Commons partners and were involved with creating and validating the benchmark, it doesn't seem to be quite as vendor-agnostic as we would like. AMD and Nvidia GPUs only have a DirectML execution path, while Intel has both DirectML and OpenVINO as options. Intel's Arc GPUs score quite a bit higher with OpenVINO than with DirectML.
The RTX 5070 beats the 4070 Ti here, but comes in just behind the 7900 XT in tokens per second. The time to first token on the other hand strongly favors the Nvidia GPUs.
We'll have some additional SPECworkstation 4.0 results below, but there's an AI inference test composed of ResNet50 and SuperResolution workloads that runs on GPUs (and potentially NPUs, though we haven't tested that). We calculate the geometric mean of the four results given in inferences per second, which isn't an official SPEC score but it's more useful for our purposes.
The RTX 5070 again beats the RTX 4070 Ti, along with squeaking past the RX 7900 XTX. Even without using FP4, it looks like Blackwell does better in some of the AI workloads than Ada.
For our professional application tests, we'll start with Blender Benchmark 4.3.0, which has support for Nvidia Optix, Intel OneAPI, and AMD HIP libraries. Those aren't necessarily equivalent in terms of the level of optimizations, but each represents the fastest way to run Blender on a particular GPU at present.
The RTX 5070 delivers 22% better performance than the RTX 4070 in our Blender geomean score, edging past the 4070 Ti again. AMD's GPUs again fall quite a bit behind the pace set by Nvidia for this ray tracing workload.
SPECworkstation 4.0 has two other test suites that are of interest in terms of GPU performance. The first is the video transcoding test using HandBrake, a measure of the video engines on the different GPUs and something that can be useful for content creation work. We use the average of the 4K to 4K and 4K to 1080p scores. Note that this only evaluates speed of encoding, not image fidelity.
The RTX 5070 has the same video encoding block as the other Blackwell GPUs, though clock speeds can vary slightly. It looks like the 5070 clocks higher than the 5070 Ti in this particular test, and the Blackwell GPUs are slightly faster than the Ada cards. AMD's 7000-series GPUs all deliver nearly identical performance, though it's worth pointing out that this is purely the speed of encoding. Our GPU encoding tests indicated AMD had significantly lower image fidelity — something RDNA 4 is supposed to finally address.
Our final professional app tests consist of SPECworkstation 4.0's viewport graphics suite. This is basically the same tests as SPECviewperf 2020, only updated to the latest versions. (Also, Siemen's NX isn't part of the suite.) There are seven individual application tests, and we've combined the scores from each into an unofficial overall score using a geometric mean.
The RTX 5070 comes in second to last out of the tested GPUs in the viewport rankings, only beating the RTX 4070 — as it should. AMD's drivers for its consumer cards tend to be more friendly toward these professional applications, which is why the 7800 XT and above beat the Nvidia GPUs.
These AI and professional tests are ultimately just one aspect of GPU performance, and if you only care about gaming they shouldn't exert much influence on your choice of GPU. That's especially true of the professional tests. AI could become something useful even for gaming, maybe, but higher Blender performance will only matter if you're actually using Blender for 3D modeling.
- MORE: Best Graphics Cards
- MORE: GPU Benchmarks and Hierarchy
- MORE: All Graphics Content
