AMD Radeon RX 7800 XT vs 6950 XT
VS
AMD Radeon RX 7800 XT
Navi 32
AMD Radeon RX 6950 XT
Navi 21
We compared two discrete desktop gaming GPUs: the Radeon RX 7800 XT with 3840 shaders against the 1 year and 4 months older 6950 XT that utilizes 5120 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 7800 XT
- 57% higher maximum theoretical performance (37.3 vs 23.7 TFLOPS)
- Manufactured using a more efficient 5 nm process technology
Reasons to consider the Radeon RX 6950 XT
- Performs slightly better (up to 15%) in 3DMark Steel Nomad Lite
- Shows 7% higher average frame rate in modern games at QHD resolution – 123 vs 115 FPS
- Achieves 28% more points in the GeekBench 6 Compute test (189K vs 148K)
- Has 33% more shading units (5120 vs 3840)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 197 135 111 86 |
210 140 121 90 |
| The Witcher 3 | 205 174 132 66 |
213 192 140 76 |
| Counter-Strike 2 | 297 206 147 80 |
299 216 150 82 |
| Far Cry 6 | 166 145 124 77 |
175 153 136 83 |
| Hogwarts Legacy | 122 101 79 45 |
129 107 83 46 |
| CoD: Modern Warfare III | 169 168 122 80 |
187 182 132 88 |
| Ghost of Tsushima | 124 105 85 54 |
138 113 96 57 |
| Cyberpunk 2077 | 132 121 80 39 |
147 134 89 41 |
| Shadow of the Tomb Raider | 212 199 151 77 |
229 212 158 83 |
| 1080p High | 180 | 192 |
| 1080p Ultra | 150 | 161 |
| 1440p Ultra | 115 | 123 |
| 4K Ultra | 67 | 72 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 20095 | 21610 |
| Solar Bay | 80667 | 89327 |
| Port Royal | 10917 | 11269 |
| Fire Strike | 50073 | 59854 |
| Wild Life Extreme | 37173 | 40959 |
| Night Raid | 160762 | 163309 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 300.7 img/sec | 382.1 img/sec |
| Face Detection | 200.5 img/sec | 259 img/sec |
| Horizon Detection | 5.77 Gpixels/sec | 6.93 Gpixels/sec |
| Edge Detection | 8.05 Gpixels/sec | 10.2 Gpixels/sec |
| Gaussian Blur | 6.44 Gpixels/sec | 8.39 Gpixels/sec |
| Feature Matching | 1.25 Gpixels/sec | 1.48 Gpixels/sec |
| Stereo Matching | 566.4 Gpixels/sec | 824.3 Gpixels/sec |
| Particle Physics | 20533.6 FPS | 26538.1 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1195 | 1083 |
| DirectX 11 | 250 FPS | 298 FPS |
| DirectX 12 | 96 FPS | 115 FPS |
| GPU Compute | 13617 Ops/s | 14128 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 7800 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-06-03 (RekrutV) | Geekbench 6 OpenCL | 156177 |
| 📘 2026-06-03 (RekrutV) | Steel Nomad Light | 19225 |
| 📘 2026-05-14 (RekrutV) | Geekbench 6 OpenCL | 152506 |
| 📘 2026-05-14 (RekrutV) | Steel Nomad Light | 18724 |
Radeon RX 6950 XT
No benchmark results yet
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) | 13913 | 14145 |
| Image Segmentation (HP) | 18416 | 18828 |
| Image Super Resolution (Q) | 31387 | 32309 |
| Face Detection (HP) | 51780 | 49133 |
| Pose Estimation (Q) | 177217 | 166767 |
| Text Classification (SP) | 3655 | 4491 |
| Machine Translation (HP) | 6216 | 6690 |
| Object Detection (SP) | 15073 | 15446 |
| Depth Estimation (Q) | 57318 | 56831 |
| Style Transfer (SP) | 347420 | 367328 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 7800 XT and 6950 XTGeneral
| Vendor | Amd | Amd |
| Build | Discrete | Discrete |
| Released | September 6, 2023 | May 10, 2022 |
| Launch price (MSRP) | $499 | $1099 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 3.0 | RDNA 2.0 |
| GPU Codename | Navi 32 | Navi 21 |
| Rival Equivalent | - GeForce RTX 4070 | - GeForce RTX 4070 SUPER |
| Successor | - Radeon RX 9070 XT | - |
| Recommended CPU | - Intel Core i5 13600K or above | - Intel Core i7 12700K or above |
Desktop GPU rating (26th and 24th place)
Graphics Processing Unit
| Base Clock | 1295 MHz | 1860 MHz |
| Boost Clock | 2430 MHz | 2310 MHz |
| Shading Units | 3840 | 5120 |
| Texture Mapping Units (TMUs) | 240 | 320 |
| Render Output Units (ROPs) | 96 | 128 |
| Ray-tracing Cores | 60 | 80 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 4MB shared |
| Instructions Per Cycle | 4 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 233 GPixel/s | 296 GPixel/s |
| Texture Fill Rate | 583 GTexel/s | 739 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 | 263 W | 335 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 5 nm | 7 nm |
| Die Size | 346 mm² | 520 mm² |
| Transistor Count | 28 billion | 26 billion |
| Transistor Density | 80.92 MTr/mm² | 50 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 16 GB |
| Memory Clock | 2438 MHz | 2250 MHz |
| Effective Memory Speed | 19500 Mbps | 18000 Mbps |
| Bus | 256-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 2.1 |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1 | 1.4a |
Cast your vote
Total votes: 29