AMD Radeon RX 560 vs GeForce RTX 5090
VS
AMD Radeon RX 560
Polaris 21
Nvidia GeForce RTX 5090
GB202-300
We compared two discrete desktop gaming GPUs: the Radeon RX 560 4 GB with 1024 shaders against the 7 years and 10 months newer GeForce RTX 5090 32 GB that utilizes 170 pipelines and 21760 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the GeForce RTX 5090
- Performs significantly better (up to 29.8x) in 3DMark Steel Nomad Lite
- 40.3x higher maximum theoretical performance (104.8 vs 2.6 TFLOPS)
- Shows 18.8x higher average frame rate in modern games at QHD resolution – 207 vs 11 FPS
- Manufactured using a more efficient 4 nm process technology
- Ray-tracing support with 170 dedicated RT cores
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 32 17 13 - |
336 247 233 187 |
| The Witcher 3 | 15 15 - - |
364 327 237 123 |
| Counter-Strike 2 | 33 21 15 - |
363 265 202 99 |
| Far Cry 6 | 25 20 14 - |
237 202 190 121 |
| Hogwarts Legacy | 13 9 - - |
249 199 166 97 |
| CoD: Modern Warfare III | 26 21 17 9 |
334 322 260 184 |
| Ghost of Tsushima | 13 11 9 - |
221 185 175 113 |
| Cyberpunk 2077 | 12 12 - - |
261 233 160 77 |
| Shadow of the Tomb Raider | 21 21 14 - |
329 302 238 128 |
| 1080p High | 21 | 299 |
| 1080p Ultra | 16 | 254 |
| 1440p Ultra | 11 | 207 |
| 4K Ultra | - | 125 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 1854 | 46873 |
| Solar Bay | - | 236689 |
| Port Royal | - | 38202 |
| Fire Strike | 6492 | 87569 |
| Wild Life Extreme | 3605 | 108751 |
| Night Raid | 25402 | 206648 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 34 img/sec | 333 img/sec |
| Face Detection | 17.6 img/sec | 298.5 img/sec |
| Horizon Detection | 0.69 Gpixels/sec | 21.7 Gpixels/sec |
| Edge Detection | 1.43 Gpixels/sec | 33.7 Gpixels/sec |
| Gaussian Blur | 1.15 Gpixels/sec | 34.5 Gpixels/sec |
| Feature Matching | 0.2 Gpixels/sec | 2.53 Gpixels/sec |
| Stereo Matching | 65.5 Gpixels/sec | 2850 Gpixels/sec |
| Particle Physics | 2232.5 FPS | 59146.9 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 486 | 1410 |
| DirectX 11 | 25 FPS | 340 FPS |
| DirectX 12 | 21 FPS | 179 FPS |
| GPU Compute | 1412 Ops/s | 24383 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 1731 | 18948 |
| Image Segmentation (HP) | 2205 | 55109 |
| Image Super Resolution (Q) | 4705 | 58478 |
| Face Detection (HP) | 6423 | 114685 |
| Pose Estimation (Q) | 19379 | 344729 |
| Text Classification (SP) | 1172 | 4464 |
| Machine Translation (HP) | 1724 | 8184 |
| Object Detection (SP) | 1937 | 27802 |
| Depth Estimation (Q) | 8173 | 85572 |
| Style Transfer (SP) | 36502 | 687080 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 560 and GeForce RTX 5090General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | April 18, 2017 | January 7, 2025 |
| Launch price (MSRP) | $99 | $1999 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | Mid-range | High-end |
| Architecture | GCN 4.0 | Blackwell 2.0 |
| GPU Codename | Polaris 21 | GB202-300 |
| Rival Equivalent | - GeForce GTX 1050 | - |
| Recommended CPU | - Intel Core i5 8400 or above | - Intel Core Ultra 9 285K or above |
Desktop GPU rating (91st and 2nd place)
Graphics Processing Unit
| Base Clock | 1175 MHz | 2017 MHz |
| Boost Clock | 1275 MHz | 2407 MHz |
| Shading Units | 1024 | 21760 |
| Texture Mapping Units (TMUs) | 64 | 680 |
| Render Output Units (ROPs) | 16 | 176 |
| Compute Units (Pipelines) | - | 170 |
| Tensor Cores | No | 680 |
| Ray-tracing Cores | No | 170 |
| L1 Cache | 16KB per cluster | 128KB per cluster |
| L2 Cache | 1024KB shared | 96MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 20 GPixel/s | 424 GPixel/s |
| Texture Fill Rate | 82 GTexel/s | 1637 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x8 | PCIe 5.0 x16 |
| TGP | 75 W | 575 W |
| Manufacturing | GlobalFoundries | TSMC |
| Fabrication Process | 14 nm | 4 nm |
| Die Size | 123 mm² | 750 mm² |
| Transistor Count | 3 billion | 92.2 billion |
| Transistor Density | 24.39 MTr/mm² | 122.93 MTr/mm² |
Memory
| Memory Type | GDDR5 | GDDR7 |
| Memory Size | 4 GB | 32 GB |
| Memory Clock | 1750 MHz | 1750 MHz |
| Effective Memory Speed | 7000 Mbps | 28000 Mbps |
| Bus | 128-bit | 512-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| CUDA | - | 12.0 |
| Ray Tracing | No | Yes |
| DLSS | No | DLSS 4 |
| DisplayPort | 1.4a | 2.1b |
Cast your vote
Total votes: 7
