AMD Radeon RX 6950 XT vs GeForce RTX 4070
VS
AMD Radeon RX 6950 XT
Navi 21
Nvidia GeForce RTX 4070
AD104
We compared two discrete desktop gaming GPUs: the Radeon RX 6950 XT 16 GB with 5120 shaders against the 11 months newer 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 6950 XT
- Performs slightly better (up to 15%) in 3DMark Steel Nomad Lite
- Shows 16% higher average frame rate in modern games at QHD resolution – 123 vs 106 FPS
- Includes 4 GB more video memory
Reasons to consider the GeForce RTX 4070
- Manufactured using a more efficient 5 nm process technology
- 23% higher maximum theoretical performance (29.1 vs 23.7 TFLOPS)
- Supports Nvidia DLSS 3 technology
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 210 140 121 90 |
172 115 102 79 |
| The Witcher 3 | 213 192 140 76 |
194 159 114 61 |
| Counter-Strike 2 | 299 216 150 82 |
272 205 149 81 |
| Far Cry 6 | 175 153 136 83 |
149 133 115 68 |
| Hogwarts Legacy | 129 107 83 46 |
117 97 77 39 |
| CoD: Modern Warfare III | 187 182 132 88 |
149 145 107 69 |
| Ghost of Tsushima | 138 113 96 57 |
106 88 72 43 |
| Cyberpunk 2077 | 147 134 89 41 |
129 119 75 37 |
| Shadow of the Tomb Raider | 229 212 158 83 |
211 190 145 80 |
| 1080p High | 192 | 167 |
| 1080p Ultra | 161 | 139 |
| 1440p Ultra | 123 | 106 |
| 4K Ultra | 72 | 62 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 21610 | 17799 |
| Solar Bay | 89327 | 82861 |
| Port Royal | 11269 | 11156 |
| Fire Strike | 59854 | 44067 |
| Wild Life Extreme | 40959 | 35472 |
| Night Raid | 163309 | 153385 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 382.1 img/sec | 233 img/sec |
| Face Detection | 259 img/sec | 141.7 img/sec |
| Horizon Detection | 6.93 Gpixels/sec | 6.62 Gpixels/sec |
| Edge Detection | 10.2 Gpixels/sec | 9.19 Gpixels/sec |
| Gaussian Blur | 8.39 Gpixels/sec | 9.2 Gpixels/sec |
| Feature Matching | 1.48 Gpixels/sec | 1.78 Gpixels/sec |
| Stereo Matching | 824.3 Gpixels/sec | 845.4 Gpixels/sec |
| Particle Physics | 26538.1 FPS | 25043.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1083 | 1165 |
| DirectX 11 | 298 FPS | 243 FPS |
| DirectX 12 | 115 FPS | 103 FPS |
| GPU Compute | 14128 Ops/s | 14561 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 6950 XT
No benchmark results yet
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) | 14145 | 10246 |
| Image Segmentation (HP) | 18828 | 26153 |
| Image Super Resolution (Q) | 32309 | 32054 |
| Face Detection (HP) | 49133 | 51337 |
| Pose Estimation (Q) | 166767 | 124617 |
| Text Classification (SP) | 4491 | 3703 |
| Machine Translation (HP) | 6690 | 5484 |
| Object Detection (SP) | 15446 | 13134 |
| Depth Estimation (Q) | 56831 | 50548 |
| Style Transfer (SP) | 367328 | 263477 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 6950 XT and GeForce RTX 4070General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | May 10, 2022 | April 13, 2023 |
| Launch price (MSRP) | $1099 | $599 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 2.0 | Ada Lovelace |
| GPU Codename | Navi 21 | AD104 |
| Rival Equivalent | - GeForce RTX 4070 SUPER | - Radeon RX 7900 XT |
| Successor | - | - GeForce RTX 5070 |
| Recommended CPU | - Intel Core i7 12700K or above | - Intel Core i7 14700K or above |
Desktop GPU rating (24th and 30th place)
Graphics Processing Unit
| Base Clock | 1860 MHz | 1920 MHz |
| Boost Clock | 2310 MHz | 2475 MHz |
| Shading Units | 5120 | 5888 |
| Texture Mapping Units (TMUs) | 320 | 184 |
| Render Output Units (ROPs) | 128 | 64 |
| Compute Units (Pipelines) | - | 46 |
| Tensor Cores | - | 184 |
| Ray-tracing Cores | 80 | 46 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 36MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 296 GPixel/s | 158 GPixel/s |
| Texture Fill Rate | 739 GTexel/s | 455 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 335 W | 200 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 7 nm | 5 nm |
| Die Size | 520 mm² | 294 mm² |
| Transistor Count | 26 billion | 35 billion |
| Transistor Density | 50 MTr/mm² | 119.05 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6X |
| Memory Size | 16 GB | 12 GB |
| Memory Clock | 2250 MHz | 1313 MHz |
| Effective Memory Speed | 18000 Mbps | 21000 Mbps |
| Bus | 256-bit | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| CUDA | - | 8.9 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 3 |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 8