AMD Radeon RX 9070 XT vs Nvidia GeForce RTX 5090
66
out 100
VS
97
out 100
Compared 2 processors: AMD Radeon RX 9070 XT, vs Nvidia GeForce RTX 5090. 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 | 237 162 142 109 | 332 242 231 183 |
 The Witcher 3 | 255 226 166 88 | 366 338 234 127 |
 Counter-Strike 2 | 323 219 160 81 | 379 271 209 98 |
 Far Cry 6 | 200 177 155 100 | 235 202 198 124 |
 Hogwarts Legacy | 152 128 104 56 | 244 210 167 96 |
 COD Modern Warfare 3 | 240 225 172 114 | 337 333 269 184 |
 Ghost of Tsushima | 156 129 112 71 | 221 190 170 114 |
 Cyberpunk 2077 | 185 160 110 51 | 259 231 166 77 |
 Shadow of the Tomb Raider | 279 260 195 106 | 334 306 238 128 |
| 1080p High | 225 | 301 |
| 1080p Ultra | 187 | 258 |
| 1440p Ultra | 146 | 209 |
| 4K Ultra | 86 | 126 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 30268 | 47515 |
| Solar Bay | 119007 | 213229 |
| Port Royal | 18715 | 37529 |
| Fire Strike | 66051 | 90200 |
| Night Raid | 199232 | 209016 |
| Background Blur | 427.4 frames/s | 333 frames/s |
| Face Detection | 251 frames/s | 298.5 frames/s |
| Horizon Detection | 6.77 Gpix/sec | 21.7 Gpix/sec |
| Edge Detection | 9.42 Gpix/sec | 33.7 Gpix/sec |
| Gaussian Blur | 9.35 Gpix/sec | 34.5 Gpix/sec |
| Feature Matching | 1.42 Gpix/sec | 2.53 Gpix/sec |
| Stereo Matching | 651.4 Gpix/sec | 2850 Gpix/sec |
| Particle Physics | 23630 fps | 59146.9 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 1347 | 1444 |
| DirectX 11 | 294 fps | 344 fps |
| DirectX 12 | 80 fps | 195 fps |
| GPU Compute | 15847 Ops/s | 28243 Ops/s |
| Aztec Ruins (Normal) | 1653.8 fps | 1397.2 fps |
| Car Chase | 1403.1 fps | 1150.3 fps |
| Manhattan 3.1.1 (1440p) | 1113.5 fps | 1178.2 fps |
| T-Rex | 4704.1 fps | 4812.3 fps |
| ALU 2 | 8678.1 fps | 5992.8 fps |
| Driver Overhead 2 | 313.1 fps | 269.7 fps |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
| Tessellation | 6928.5 | 5991.7 |
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 | High-end |
| Architecture | RDNA 4.0 | Blackwell 2.0 |
| Codename | Navi 48 | GB202-300-A1 |
| Price | 599 | 1999 |
GPU
| GPU Frequency | 1660 MHz | 2017 MHz |
| Boost GPU Frequency | 2970 MHz | 2407 MHz |
| Shader Units | 4096 | 21760 |
| TMUs | 256 | 680 |
| ROPs | 128 | 176 |
| Execution Units | 64 | 170 |
| Ray Tracing Cores | 64 | 170 |
| Tensor Cores | 128 | 680 |
| L1 cache | 128 KB/core | 128 KB/core |
| L2 cache | 4000 KB/core | 88 KB/core |
| Instructions per Clock | 4 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 380 Gpix/sec | 424 Gpix/sec |
| Texture Fill Rate | 760 GTex/s | 1637 GTex/s |
| FLOPS | 48.7 TFLOPS | 104.8 TFLOPS |
Process
| Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| TGP | 304 W | 575 W |
| Process | TSMC | TSMC |
| Process tech. | 4 nm | 4 nm |
| Transistor Size | 357 mm² | 750 mm² |
| Transistor count | 53.9 billion | 92.2 billion |
| Transistor density | 150.98 MTr/mm² | 122.93 MTr/mm² |
Memory
| Interface | GDDR6 | GDDR7 |
| Memory Frequency | 2518 MHz | 1750 MHz |
| Bus | 256 bit | 512 bit |
| ECC support | No | No |
| Effective Memory Speed | 20100 MB/s | 28000 MB/s |
| Memory Size | 16 GB | 32 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| CUDA | n/a | 10.1 |
| DisplayPort | 2.1a | 2.1a |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 4 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 5090 the clear winner in this comparison.
Survey
Total Votes: 6
