Quick/Comparisons
Both GPUs deliver solid gaming performance, with the Nvidia RTX 5000 Ada's 73 score slightly edging out the Radeon RX 7900 XT's 72, but the difference is negligible.
The Nvidia RTX 5000 Ada's strong workstation performance earns it the win, thanks to its 82 score, a full 12 points higher than the Radeon RX 7900 XT's 70.
The Radeon RX 7900 XT takes the lead in AI/ML tasks, with its 68 score outpacing the Nvidia RTX 5000 Ada's 54, indicating better performance in this area.
73 | Gaming | 72 |
82 | Workstation | 70 |
54 | AI/ML | 68 |
45 | Energy Efficiency | 45 |
73 | Quick Comparison Final Score | 70 |
| AD102 | Graphics Processor | Navi 31 |
| 12800 | Cores | 5376 |
| 400 / 176 | TMUs / ROPs | 336 / 192 |
| 7348.98 | Blender GPU | 3548.59 |
| 146 | Forza Horizon 5 | 157 |
| 186 | The Witcher 3 | 228 |
| 213 | Counter-Strike 2 | 223 |
| 151 | Far Cry 6 | 173 |
| 117 | Hogwarts Legacy | 126 |
| 179 | Call of Duty | 222 |
| 108 | Ghost of Tsushima | 129 |
| 148 | Cyberpunk 2077 | 158 |
| 242 | Tomb Raider | 247 |
| 166 | Average FPS | 185 |
| 196 | 1080p High | 219 |
| 166 | 1080p Ultra | 185 |
| 132 | 1440p Ultra | 144 |
| 78 | 4K Ultra | 85 |
| High | Margin of Error | Low |
| 260099 | GB6 Compute Score | 203754 |
| 286.6 img/sec | Background Blur | 419.8 img/sec |
| 220.4 img/sec | Face Detection | 240.5 img/sec |
| 9.93 Gpixels/sec | Horizon Detection | 8.72 Gpixels/sec |
| 13.7 Gpixels/sec | Edge Detection | 12 Gpixels/sec |
| 18.9 Gpixels/sec | Gaussian Blur | 9.88 Gpixels/sec |
| 2.2 Gpixels/sec | Feature Matching | 1.71 Gpixels/sec |
| 1580 Gpixels/sec | Stereo Matching | 701.7 Gpixels/sec |
| 41235.6 FPS | Particle Physics | 26631.4 FPS |
| OpenCL | API | OpenCL |
| 30196 | G3D Mark Score | 29015 |
| 998 | G2D Mark | 1241 |
| 273 FPS | DirectX 11 | 340 FPS |
| 106 FPS | DirectX 12 | 111 FPS |
| 20736 Ops/s | GPU Compute | 16851 Ops/s |
| 24715 | GB6 ML Single Precision | 39099 |
| 36753 | GB6 ML Half Precision | 47298 |
| 19649 | GB6 ML Quantized | 30875 |
| 9943 | Image Classification (SP) | 16951 |
| 19696 | Image Segmentation (HP) | 23234 |
| 32252 | Image Super Resolution (Q) | 41128 |
| 43098 | Face Detection (HP) | 67615 |
| 138689 | Pose Estimation (Q) | 237026 |
| 2893 | Text Classification (SP) | 4961 |
| 4064 | Machine Translation (HP) | 7043 |
| 12467 | Object Detection (SP) | 18737 |
| 50352 | Depth Estimation (Q) | 67746 |
| 265482 | Style Transfer (SP) | 457919 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 449 GPixel/s | Pixel Fill Rate | 460 GPixel/s |
| 1020 GTexel/s | Texture Fill Rate | 804 GTexel/s |
| 65.3 TFLOPS | FLOPS (FP32) | 51.5 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 32 GB | Memory Size | 20 GB |
| 2250 MHz | Memory Clock | 2500 MHz |
| 18000 Mbps | Effective Memory Speed | 20000 Mbps |
| 256-bit | Bus | 320-bit |
| No | ECC | No |
| 576 GB/s | Memory Bandwidth | 800 GB/s |
| PCIe 4.0 x16 | Interface | PCIe 4.0 x16 |
| 250 W | TGP | 300 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 609 mm² | Die Size | 529 mm² |
| 76 billion | Transistor Count | 57 billion |
| 124.79 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 8.9 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 3 | DLSS | No |
| 1.4a | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| August 9, 2023 | Released | December 13, 2023 |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Ada Lovelace | Architecture | RDNA 3.0 |
| AD102 | GPU Codename | Navi 31 |
| -Intel Core i9 14900Kor above | Recommended CPU | -Intel Core i7 13700Kor above |
| 29190 | Steel Nomad Lite Score | 24675 |
| 18675 | Time Spy | 27067 |
| 128428 | Solar Bay | 104912 |
| 17754 | Port Royal | 14358 |
| 62027 | Fire Strike | 67256 |
| 52866 | Wild Life Extreme | 48319 |
| 210443 | Night Raid | 176267 |
| 1155 MHz | Base Clock | 1387 MHz |
| 2550 MHz | Boost Clock | 2394 MHz |
| 12800 | Shading Units | 5376 |
| 400 | Texture Mapping Units (TMUs) | 336 |
| 176 | Render Output Units (ROPs) | 192 |
| 100 | Compute Units (Pipelines) | — |
| 400 | Tensor Cores | — |
| 100 | Ray-tracing Cores | 84 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 72MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |
Compare with something else?
Compare Nvidia RTX 5000 with another →