AMD Radeon RX 9070 XT And 9070 Review: Competition Heats-Up For Gamers
Our Test System Configuration:
| Hardware Used: AMD Ryzen 7 9800X3D (4.7GHz - 5.2GHz, 8-Core) MSI X870E Carbon WiFi 32GB G.SKILL DDR5-6000 Samsung SSD 990 Integrated Audio / Network Radeon RX 7900 XTX XFX Radeon RX 9070 XFX Radeon RX 9070 XT Powercolor Radeon RX 9070 XT GeForce RTX 3070 Ti GeForce RTX 4070 GeForce RTX 4070 Ti GeForce RTX 5070 GeForce RTX 4080 GeForce RTX 5080 Relevant Software: Windows 11 Pro 24H2 AMD Radeon v24.30.31.03 NVIDIA Drivers v571.86 / v572.30 |
Benchmarks Used: MLPerf Client Geekbench AI Procyon AI Text Generation Procyon AI Stable Diffusion XL Blender v4.3 Blackmagic RAW Speed Test v4.3.1 V-Ray UL 3DMark UL VRMark Unigine Superposition Games Tested: Assassin's Creed Mirage Black Myth Wukon Homeworld 3 Horizon Zero Dawn Remastered Cyberpunk 2077 (press beta) The Talos Principle II F1 24 |
MLPerf Client Benchmarks
The MLPerf Client benchmark was designed by MLCommons to evaluate machine learning inference tasks on PCs. It focuses on client form factors and aims to measure how well different hardware and software configurations handle four different AI workloads using a single model. It supports DirectML via ONNX Runtime for a wide range of hardware, but Intel also gets a specialized OpenVINO path for now. Participants in MLCommons are also able to optimize the models for their hardware, but must meet strict guidelines for accuracy.
The Radeon RX 9070 and 9070 XT offer mixed performance in the MLPerf Client benchmark. Throughput is good, with an average 2nd token rate higher than the GeForce RTX 4070 Ti and RTX 5070, but all of the Radeons rank near the bottom in terms of latency and time to first token. This is probably an area AMD could improve with future software updates.
Geekbench AI Testing
Geekbench AI is a cross-platform benchmark tool designed to evaluate the performance of AI workloads on a wide range devices, including smartphones, tablets, laptops, and desktops. It measures the performance of CPUs, GPUs, and NPUs (Neural Processing Units) across different operating systems like Android, iOS, Windows, macOS, and Linux with an array of machine learning tasks.
Performance in GeekBench AI's smaller, more bursty workloads looks better for the Radeon RX 9070 and 9070 XT. When ranked by the Quantized score, the Radeon RX 9070 and 9070 XT cards rank near the top behind only the GeForce RTX 5080. In individual Single and Half Precision scores are also competitive.
Performance in GeekBench AI's smaller, more bursty workloads looks better for the Radeon RX 9070 and 9070 XT. When ranked by the Quantized score, the Radeon RX 9070 and 9070 XT cards rank near the top behind only the GeForce RTX 5080. In individual Single and Half Precision scores are also competitive.
UL Procyon AI Text Generation Benchmarks
The Procyon AI Text Generation Benchmark is a tool developed by UL Solutions to evaluate the performance of large language models (LLMs) on Windows PCs. It features real-world use cases and uses seven prompts with both Retrieval-Augmented Generation (RAG) and non-RAG queries. It tests various AI models like Phi-3.5-mini, Mistral-7B, Llama-3.1-8B, and Llama-2-13B. These tests were run using ONNX with DirectML, not TensorRT, which is optimal for NVIDIA's RTX series discrete GPUs, but unavailable in this test at this time with this particular test.
UL Procyon AI Text Generation ASUS PRIME GeForce RTX 5070 Ti Details
With all four LLMs, the new Radeon RX 9070 and 9070 XT trail the rest of the pack in Procyon's text generation benchmark. This is a somewhat unexpected result, and again, suggests some software optimization is needed. Then again, the Radeon RX 7900 XTX has been out for a couple of years and it doesn't fare much better.
UL Procyon AI Text Generation ASUS PRIME GeForce RTX 5070 Ti Details
With all four LLMs, the new Radeon RX 9070 and 9070 XT trail the rest of the pack in Procyon's text generation benchmark. This is a somewhat unexpected result, and again, suggests some software optimization is needed. Then again, the Radeon RX 7900 XTX has been out for a couple of years and it doesn't fare much better.
UL Procying Stable Diffusion XL AI Image Generation
The Procyon AI Image Generation Benchmark measures inference performance for image generation tasks. It includes several tests, with the Stable Diffusion XL (FP16) test we used here being the most demanding. The test is designed to evaluate a wide range of hardware from low power NPUs to high-end discrete GPUs and it can be configured to use different inference engines like NVIDIA TensorRT, Intel OpenVINO, and ONNX with DirectML. Unfortunately, the TensorRT engine hasn’t been updated for Blackwell just yet, but we tested it with ONNX to provide a point of reference versus the RTX 40 series cards.
For some unknown reason this test wouldn't run on the MSI GeForce RTX 5070 Gaming Trio, despite using the exact same software and system configuration as the GeForce RTX 5070 FE (and it worked properly on every other card). In any case, the Radeon RX 9070 and 9070 XT do much better with image generation and are competitive with GeForce cards in the RTX 4070 - 5070 Ti range.
For some unknown reason this test wouldn't run on the MSI GeForce RTX 5070 Gaming Trio, despite using the exact same software and system configuration as the GeForce RTX 5070 FE (and it worked properly on every other card). In any case, the Radeon RX 9070 and 9070 XT do much better with image generation and are competitive with GeForce cards in the RTX 4070 - 5070 Ti range.
Blender v4.3 GPU Rendering Benchmarks
Blender is a free and open source 3D creation suite that can handle everything from modeling, rigging, and animation, through simulation, rendering, compositing, motion tracking, and even video editing or game creation. The developers offer a standalone benchmark tool that will track performance while rendering a handful of models. We used all three of the default models for these tests...
The Radeon RX 9070 and 9070 XT performed okay in Blender, with the XT and vanilla 9070 sandwiching the RDNA 3-based Radeon RX 7900 XTX, but ultimately only outrunning the much older GeForce RTX 3070 Ti. Blender's support for NVIDIA's RT cores shines through here with all of the GeForce RTX 40 and 50 series cards taking the top spots.
Blackmagic RAW Speed Test Results
The Blackmagic RAW Speed Test is a CPU and GPU benchmarking tool that determines the speed of decoding full-resolution Blackmagic RAW video frames. The tool can be used to evaluate performance at various resolutions and bitrates on the CPU or using OpenCL or CUDA on a GPU. We're reporting four results here, at 8K and 4K resolutions, but at differing bitrates and compression levels.
AMD's new media engine is both faster and offers better image quality than previous-gen cards, but at both resolutions and compression levels, the Radeon RX 9070 and 9070 XT trail all of the GeForce cards when decoding Blackmagic RAW video files.
