AMD Radeon RX 6950 XT vs 6900 XT
AMD Radeon RX 6950 XT
Navi 21
AMD Radeon RX 6900 XT
Navi 21
We compared two discrete desktop gaming GPUs: the Radeon RX 6950 XT with 5120 shaders against the 1 year and 6 months older 6900 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 6950 XT
- Achieves 53% more points in the GeekBench 6 Compute test (189K vs 124K)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 210 140 121 90 |
212 139 117 90 |
| The Witcher 3 | 213 192 140 76 |
209 186 138 71 |
| Counter-Strike 2 | 299 216 150 82 |
296 213 153 81 |
| Far Cry 6 | 175 153 136 83 |
173 147 131 83 |
| Hogwarts Legacy | 129 107 83 46 |
129 107 80 46 |
| CoD: Modern Warfare III | 187 182 132 88 |
186 178 128 85 |
| Ghost of Tsushima | 138 113 96 57 |
129 112 92 55 |
| Cyberpunk 2077 | 147 134 89 41 |
142 127 86 42 |
| Shadow of the Tomb Raider | 229 212 158 83 |
228 213 161 80 |
| 1080p High | 192 | 189 |
| 1080p Ultra | 161 | 158 |
| 1440p Ultra | 123 | 121 |
| 4K Ultra | 72 | 70 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 21610 | 20817 |
| Solar Bay | 89327 | 86965 |
| Port Royal | 11269 | 10543 |
| Fire Strike | 59854 | 57312 |
| Wild Life Extreme | 40959 | 39345 |
| Night Raid | 163309 | 159536 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 382.1 img/sec | 231.6 img/sec |
| Face Detection | 259 img/sec | 152.5 img/sec |
| Horizon Detection | 6.93 Gpixels/sec | 4.26 Gpixels/sec |
| Edge Detection | 10.2 Gpixels/sec | 5.75 Gpixels/sec |
| Gaussian Blur | 8.39 Gpixels/sec | 5.87 Gpixels/sec |
| Feature Matching | 1.48 Gpixels/sec | 1.12 Gpixels/sec |
| Stereo Matching | 824.3 Gpixels/sec | 618.7 Gpixels/sec |
| Particle Physics | 26538.1 FPS | 17973.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1083 | 1063 |
| DirectX 11 | 298 FPS | 279 FPS |
| DirectX 12 | 115 FPS | 111 FPS |
| GPU Compute | 14128 Ops/s | 14295 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 6950 XT
No benchmark results yet
Radeon RX 6900 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-12-04 -> phillybass | Cinebench 2024 | 8430 |
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 | 13868 |
| Image Segmentation (HP) | 18828 | 17467 |
| Image Super Resolution (Q) | 32309 | 32396 |
| Face Detection (HP) | 49133 | 47808 |
| Pose Estimation (Q) | 166767 | 178873 |
| Text Classification (SP) | 4491 | 4358 |
| Machine Translation (HP) | 6690 | 7910 |
| Object Detection (SP) | 15446 | 15394 |
| Depth Estimation (Q) | 56831 | 57351 |
| Style Transfer (SP) | 367328 | 372610 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 6950 XT and 6900 XTGeneral
| Vendor | Amd | Amd |
| Build | Discrete | Discrete |
| Released | May 10, 2022 | December 8, 2020 |
| Launch price (MSRP) | $1099 | $999 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 2.0 | RDNA 2.0 |
| GPU Codename | Navi 21 | Navi 21 |
| Rival Equivalent | - GeForce RTX 4070 SUPER | - GeForce RTX 4070 |
| Successor | - | - Radeon RX 7900 XT |
| Recommended CPU | - Intel Core i7 12700K or above | - Intel Core i7 12700K or above |
Desktop GPU rating (24th and 27th place)
Graphics Processing Unit
| Base Clock | 1860 MHz | 1825 MHz |
| Boost Clock | 2310 MHz | 2250 MHz |
| Shading Units | 5120 | 5120 |
| Texture Mapping Units (TMUs) | 320 | 320 |
| Render Output Units (ROPs) | 128 | 128 |
| Ray-tracing Cores | 80 | 80 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 4MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 296 GPixel/s | 288 GPixel/s |
| Texture Fill Rate | 739 GTexel/s | 720 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| TGP | 335 W | 300 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 7 nm | 7 nm |
| Die Size | 520 mm² | 520 mm² |
| Transistor Count | 26 billion | 26 billion |
| Transistor Density | 50 MTr/mm² | 50 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 16 GB |
| Memory Clock | 2250 MHz | 2000 MHz |
| Effective Memory Speed | 18000 Mbps | 16000 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 | 2.1 | 2.1 |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 1.4a | 1.4a |
Cast your vote
Total votes: 17