AMD Radeon RX 9070 vs Nvidia GeForce RTX 5070
62
out 100
VS
61
out 100
Compared 2 processors: AMD Radeon RX 9070, vs Nvidia GeForce RTX 5070. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | 235 158 133 102 | 192 140 127 98 |
 The Witcher 3 | 237 213 157 82 | 212 180 134 70 |
 Counter-Strike 2 | 315 214 160 80 | 284 215 157 82 |
 Far Cry 6 | 191 168 147 94 | 161 148 127 82 |
 Hogwarts Legacy | 143 121 95 55 | 137 115 92 50 |
 COD Modern Warfare 3 | 222 211 156 105 | 181 172 133 88 |
 Ghost of Tsushima | 146 125 109 66 | 123 107 88 56 |
 Cyberpunk 2077 | 171 154 107 47 | 161 141 99 44 |
 Shadow of the Tomb Raider | 266 242 186 98 | 250 241 181 101 |
| 1080p High | 214 | 189 |
| 1080p Ultra | 178 | 162 |
| 1440p Ultra | 139 | 126 |
| 4K Ultra | 81 | 75 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 27004 | 22613 |
| Solar Bay | 105078 | 103768 |
| Port Royal | 16158 | 14312 |
| Fire Strike | 60559 | 57793 |
| Night Raid | 170494 | 172986 |
| Background Blur | 377.5 frames/s | 254.4 frames/s |
| Face Detection | 221.3 frames/s | 180.6 frames/s |
| Horizon Detection | 6.4 Gpix/sec | 7.91 Gpix/sec |
| Edge Detection | 8.99 Gpix/sec | 10.2 Gpix/sec |
| Gaussian Blur | 8.52 Gpix/sec | 10.7 Gpix/sec |
| Feature Matching | 1.36 Gpix/sec | 1.84 Gpix/sec |
| Stereo Matching | 606 Gpix/sec | 975.7 Gpix/sec |
| Particle Physics | 8521.2 fps | 27816.5 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1274 | 1297 |
| DirectX 11 | 281 fps | 277 fps |
| DirectX 12 | 72 fps | 108 fps |
| GPU Compute | 14704 Ops/s | 15779 Ops/s |
| Image Classification (SP) | 15375 | 12270 |
| Image Segmentation (HP) | 37834 | 30237 |
| Horizon Detection | 43910 | 35585 |
| Face Detection (HP) | 67858 | 62662 |
| Pose Estimation (Q) | 172939 | 145190 |
| Text Classification (SP) | 4469 | 4198 |
| Machine Translation (HP) | 8499 | 6233 |
| Object Detection (SP) | 15393 | 16709 |
| Depth Estimation (Q) | 66890 | 58300 |
| Style Transfer (SP) | 365633 | 246598 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Blender
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | AMD | Nvidia |
| Build | Discrete | Discrete |
| Announced | January, 7, 2025 | January, 7, 2025 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 4.0 | Blackwell 2.0 |
| Codename | Navi 48 XL | GB205-300 |
GPU
| GPU Frequency | 1330 MHz | 2325 MHz |
| Boost GPU Frequency | 2520 MHz | 2512 MHz |
| Shader Units | 3584 | 6144 |
| TMUs | 224 | 192 |
| ROPs | 128 | 80 |
| Execution Units | 56 | 48 |
| Ray Tracing Cores | 56 | 48 |
| Tensor Cores | 112 | 192 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 4000 KB/core | 48000 KB/core |
| Instructions per Clock | 4 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 323 Gpix/sec | 201 Gpix/sec |
| Texture Fill Rate | 564 GTex/s | 482 GTex/s |
| FLOPS | 36.1 TFLOPS | 30.9 TFLOPS |
Process
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| TGP | 220 W | 250 W |
| Process | TSMC | TSMC |
| Process tech. | 4 nm | 4 nm |
| Transistor Size | 356.5 mm² | 263 mm² |
| Transistor count | 53.9 billion | 31.1 billion |
| Transistor density | 151.19 MTr/mm² | 118.25 MTr/mm² |
Memory
| Interface | GDDR6 | GDDR7 |
| Memory Frequency | 2518 MHz | 1750 MHz |
| Bus | 256 bit | 192 bit |
| ECC support | No | No |
| Effective Memory Speed | 20100 MB/s | 28000 MB/s |
| Memory Size | 16 GB | 12 GB |
Max Throughput
API
| DirectX | 12 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| CUDA | No | 12.0 |
| DisplayPort | 2.1a | 2.1b |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 4 |
Results
No clear favorite identified yet; updates may follow as new data arrives.
Survey
Total Votes: 7
