AMD Radeon RX 7900 XT vs GeForce RTX 4070
VS
AMD Radeon RX 7900 XT
Navi 31
Nvidia GeForce RTX 4070
AD104
We compared two discrete desktop gaming GPUs: the Radeon RX 7900 XT 20 GB with 5376 shaders against the 8 months older GeForce RTX 4070 12 GB that utilizes 46 pipelines and 5888 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 Radeon RX 7900 XT
- Performs better (up to 36%) in 3DMark Steel Nomad Lite
- 77% higher maximum theoretical performance (51.5 vs 29.1 TFLOPS)
- Shows 34% higher average frame rate in modern games at QHD resolution – 142 vs 106 FPS
- Includes 8 GB more video memory
- Has 59% higher memory bandwidth: 800 vs 504 GB/s
- Achieves 22% more points in the GeekBench 6 Compute test (203K vs 167K)
Reasons to consider the GeForce RTX 4070
- Supports Nvidia DLSS 3 technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 235 160 141 107 |
172 115 102 79 |
| The Witcher 3 | 249 225 160 87 |
194 159 114 61 |
| Counter-Strike 2 | 311 222 157 81 |
272 205 149 81 |
| Far Cry 6 | 196 168 151 100 |
149 133 115 68 |
| Hogwarts Legacy | 153 124 98 56 |
117 97 77 39 |
| CoD: Modern Warfare III | 228 214 163 108 |
149 145 107 69 |
| Ghost of Tsushima | 150 126 109 69 |
106 88 72 43 |
| Cyberpunk 2077 | 181 156 108 49 |
129 119 75 37 |
| Shadow of the Tomb Raider | 271 258 189 101 |
211 190 145 80 |
| 1080p High | 219 | 167 |
| 1080p Ultra | 184 | 139 |
| 1440p Ultra | 142 | 106 |
| 4K Ultra | 84 | 62 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 27106 | 17799 |
| Solar Bay | 105357 | 82861 |
| Port Royal | 14360 | 11156 |
| Fire Strike | 67227 | 44067 |
| Wild Life Extreme | 48410 | 35472 |
| Night Raid | 176232 | 153385 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 419.8 img/sec | 233 img/sec |
| Face Detection | 240.5 img/sec | 141.7 img/sec |
| Horizon Detection | 8.72 Gpixels/sec | 6.62 Gpixels/sec |
| Edge Detection | 12 Gpixels/sec | 9.19 Gpixels/sec |
| Gaussian Blur | 9.88 Gpixels/sec | 9.2 Gpixels/sec |
| Feature Matching | 1.71 Gpixels/sec | 1.78 Gpixels/sec |
| Stereo Matching | 701.7 Gpixels/sec | 845.4 Gpixels/sec |
| Particle Physics | 26631.4 FPS | 25043.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1247 | 1165 |
| DirectX 11 | 341 FPS | 243 FPS |
| DirectX 12 | 112 FPS | 103 FPS |
| GPU Compute | 16878 Ops/s | 14561 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 7900 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-01-01 (Mr Scare) | Cinebench 2024 | 11648 |
GeForce RTX 4070
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-14 (kashitsu) | Cinebench 2024 | 18051 |
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) | 16951 | 10246 |
| Image Segmentation (HP) | 23234 | 26153 |
| Image Super Resolution (Q) | 41128 | 32054 |
| Face Detection (HP) | 67615 | 51337 |
| Pose Estimation (Q) | 237026 | 124617 |
| Text Classification (SP) | 4961 | 3703 |
| Machine Translation (HP) | 7043 | 5484 |
| Object Detection (SP) | 18737 | 13134 |
| Depth Estimation (Q) | 67746 | 50548 |
| Style Transfer (SP) | 457919 | 263477 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 7900 XT and GeForce RTX 4070General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | December 13, 2023 | April 13, 2023 |
| Launch price (MSRP) | $899 | $599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 3.0 | Ada Lovelace |
| GPU Codename | Navi 31 | AD104 |
| Rival Equivalent | - GeForce RTX 4080 | - Radeon RX 7900 XT |
| Successor | - | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i7 13700K or above | - Intel Core i7 14700K or above |
Desktop GPU rating (11th and 30th place)
Graphics Processing Unit
| Base Clock | 1387 MHz | 1920 MHz |
| Boost Clock | 2394 MHz | 2475 MHz |
| Shading Units | 5376 | 5888 |
| Texture Mapping Units (TMUs) | 336 | 184 |
| Render Output Units (ROPs) | 192 | 64 |
| Compute Units (Pipelines) | - | 46 |
| Tensor Cores | - | 184 |
| Ray-tracing Cores | 84 | 46 |
| L1 Cache | 256KB per cluster | 128KB per cluster |
| L2 Cache | 6MB shared | 36MB shared |
| Instructions Per Cycle | 4 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 460 GPixel/s | 158 GPixel/s |
| Texture Fill Rate | 804 GTexel/s | 455 GTexel/s |
FLOPS (FP32)
Differences in GPUs' instructions per clock make TFLOPS values not directly comparable.
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 300 W | 200 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 5 nm |
| Die Size | 529 mm² | 294 mm² |
| Transistor Count | 57 billion | 35 billion |
| Transistor Density | 107.75 MTr/mm² | 119.05 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 20 GB | 12 GB |
| Memory Clock | 2500 MHz | 1313 MHz |
| Effective Memory Speed | 20000 Mbps | 21000 Mbps |
| Bus | 320-bit | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 3.0 |
| CUDA | - | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 3 |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 15