GeForce RTX 5090 vs RTX 4090
VS
Nvidia GeForce RTX 5090
GB202-300
Nvidia GeForce RTX 4090
AD102
We compared two discrete desktop gaming GPUs: the GeForce RTX 5090 32 GB with 170 pipelines and 21760 shaders against the 2 years and 4 months older RTX RTX 4090 24 GB that utilizes 128 pipelines and 16384 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 better (up to 25%) in 3DMark Steel Nomad Lite
- Shows 17% higher average frame rate in modern games at QHD resolution – 207 vs 177 FPS
- 27% higher maximum theoretical performance (104.8 vs 82.6 TFLOPS)
- Manufactured using a more efficient 4 nm process technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 336 247 233 187 |
275 199 193 155 |
| The Witcher 3 | 364 327 237 123 |
292 268 191 101 |
| Counter-Strike 2 | 363 265 202 99 |
339 238 188 90 |
| Far Cry 6 | 237 202 190 121 |
203 179 170 104 |
| Hogwarts Legacy | 249 199 166 97 |
200 163 132 74 |
| CoD: Modern Warfare III | 334 322 260 184 |
266 263 219 151 |
| Ghost of Tsushima | 221 185 175 113 |
188 152 137 91 |
| Cyberpunk 2077 | 261 233 160 77 |
226 208 143 66 |
| Shadow of the Tomb Raider | 329 302 238 128 |
302 284 222 118 |
| 1080p High | 299 | 255 |
| 1080p Ultra | 254 | 217 |
| 1440p Ultra | 207 | 177 |
| 4K Ultra | 125 | 106 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 46873 | 36299 |
| Solar Bay | 236689 | 187525 |
| Port Royal | 38202 | 26127 |
| Fire Strike | 87569 | 72432 |
| Wild Life Extreme | 108751 | 85218 |
| Night Raid | 206648 | 195813 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 333 img/sec | 318.9 img/sec |
| Face Detection | 298.5 img/sec | 222.8 img/sec |
| Horizon Detection | 21.7 Gpixels/sec | 14.2 Gpixels/sec |
| Edge Detection | 33.7 Gpixels/sec | 21 Gpixels/sec |
| Gaussian Blur | 34.5 Gpixels/sec | 23.9 Gpixels/sec |
| Feature Matching | 2.53 Gpixels/sec | 2.38 Gpixels/sec |
| Stereo Matching | 2850 Gpixels/sec | 1950 Gpixels/sec |
| Particle Physics | 59146.9 FPS | 48090.4 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1410 | 1303 |
| DirectX 11 | 341 FPS | 323 FPS |
| DirectX 12 | 179 FPS | 151 FPS |
| GPU Compute | 24360 Ops/s | 26022 Ops/s |
Blender
Blender GPU
Recent User Tests
GeForce RTX 5090
No benchmark results yet
GeForce RTX 4090
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-04-03 (afroman420IU) | Cinebench 2024 | 32578 |
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) | 18948 | 15600 |
| Image Segmentation (HP) | 55109 | 36657 |
| Image Super Resolution (Q) | 58478 | 48114 |
| Face Detection (HP) | 114685 | 78111 |
| Pose Estimation (Q) | 344729 | 289639 |
| Text Classification (SP) | 4464 | 4074 |
| Machine Translation (HP) | 8184 | 6349 |
| Object Detection (SP) | 27802 | 21186 |
| Depth Estimation (Q) | 85572 | 75599 |
| Style Transfer (SP) | 687080 | 601428 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of GeForce RTX 5090 and RTX 4090General
| Vendor | Nvidia | Nvidia |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | September 20, 2022 |
| Launch price (MSRP) | $1999 | $1599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | Blackwell 2.0 | Ada Lovelace |
| GPU Codename | GB202-300 | AD102 |
| Successor | - | - GeForce RTX 5090 |
| Recommended CPU | - Intel Core Ultra 9 285K or above | - Intel Core i9 14900K or above |
Desktop GPU rating (2nd and 3rd place)
Graphics Processing Unit
| Base Clock | 2017 MHz | 2235 MHz |
| Boost Clock | 2407 MHz | 2520 MHz |
| Shading Units | 21760 | 16384 |
| Texture Mapping Units (TMUs) | 680 | 512 |
| Render Output Units (ROPs) | 176 | 176 |
| Compute Units (Pipelines) | 170 | 128 |
| Tensor Cores | 680 | 512 |
| Ray-tracing Cores | 170 | 128 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 96MB shared | 72MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 424 GPixel/s | 444 GPixel/s |
| Texture Fill Rate | 1637 GTexel/s | 1290 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| TGP | 575 W | 450 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 5 nm |
| Die Size | 750 mm² | 609 mm² |
| Transistor Count | 92.2 billion | 76.3 billion |
| Transistor Density | 122.93 MTr/mm² | 125.29 MTr/mm² |
Memory
| Memory Type | GDDR7 | GDDR6X |
| Memory Size | 32 GB | 24 GB |
| Memory Clock | 1750 MHz | 2625 MHz |
| Effective Memory Speed | 28000 Mbps | 21000 Mbps |
| Bus | 512-bit | 384-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| CUDA | 12.0 | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | DLSS 4 | DLSS 3 |
| DisplayPort | 2.1b | 1.4a |
Cast your vote
Total votes: 897
