AMD Radeon RX 9070 XT vs RX 6800
VS
AMD Radeon RX 9070 XT
Navi 48
AMD Radeon RX 6800
Navi 21
We compared two discrete desktop gaming GPUs: the Radeon RX 9070 XT with 64 pipelines and 4096 shaders against the 4 years and 3 months older RX 6800 that utilizes 3840 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 9070 XT
- Performs significantly better (up to 81%) in 3DMark Steel Nomad Lite
- 3x higher maximum theoretical performance (48.7 vs 16.2 TFLOPS)
- Manufactured using a more efficient 4 nm process technology
- Shows 58% higher average frame rate in modern games at QHD resolution – 152 vs 96 FPS
- Achieves 35% more points in the GeekBench 6 Compute test (182K vs 135K)
- Has 26% higher memory bandwidth: 644.6 vs 512 GB/s
- Features 128 tensor cores for effective deep learning and AI workloads
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 242 169 149 109 |
175 114 95 66 |
| The Witcher 3 | 267 237 167 89 |
172 148 108 57 |
| Counter-Strike 2 | 325 224 163 82 |
265 193 131 75 |
| Far Cry 6 | 198 176 163 104 |
146 129 106 61 |
| Hogwarts Legacy | 162 133 107 58 |
106 86 68 36 |
| CoD: Modern Warfare III | 240 232 174 118 |
146 135 97 63 |
| Ghost of Tsushima | 158 137 116 73 |
110 89 70 43 |
| Cyberpunk 2077 | 190 171 119 53 |
113 98 65 32 |
| Shadow of the Tomb Raider | 280 265 207 107 |
179 168 122 63 |
| 1080p High | 229 | 157 |
| 1080p Ultra | 194 | 129 |
| 1440p Ultra | 152 | 96 |
| 4K Ultra | 88 | 55 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 29556 | 16227 |
| Solar Bay | 122220 | 64715 |
| Port Royal | 18363 | 8145 |
| Fire Strike | 66319 | 44367 |
| Wild Life Extreme | 54672 | 29767 |
| Night Raid | 194947 | 142456 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 427.4 img/sec | 298.6 img/sec |
| Face Detection | 251 img/sec | 186.2 img/sec |
| Horizon Detection | 6.77 Gpixels/sec | 4.75 Gpixels/sec |
| Edge Detection | 9.42 Gpixels/sec | 6.68 Gpixels/sec |
| Gaussian Blur | 9.35 Gpixels/sec | 5.58 Gpixels/sec |
| Feature Matching | 1.42 Gpixels/sec | 1.16 Gpixels/sec |
| Stereo Matching | 651.4 Gpixels/sec | 579 Gpixels/sec |
| Particle Physics | 23630 FPS | 18755.1 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1310 | 1002 |
| DirectX 11 | 295 FPS | 211 FPS |
| DirectX 12 | 77 FPS | 90 FPS |
| GPU Compute | 16100 Ops/s | 10748 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 9070 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-07-12 (luizmdd) | Cinebench 2024 | 50113 |
| 📘 2026-07-04 -> StevenS | Geekbench 6 OpenCL | 179283 |
| 📘 2026-07-04 -> StevenS | Steel Nomad Light | 27505 |
| 📘 2025-10-15 (adv) | Geekbench 6 OpenCL | 175418 |
Radeon RX 6800
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) | 18001 | 11245 |
| Image Segmentation (HP) | 25174 | 13617 |
| Image Super Resolution (Q) | 45714 | 27747 |
| Face Detection (HP) | 74776 | 38124 |
| Pose Estimation (Q) | 196137 | 119493 |
| Text Classification (SP) | 5163 | 2425 |
| Machine Translation (HP) | 8677 | 5228 |
| Object Detection (SP) | 19602 | 11986 |
| Depth Estimation (Q) | 74879 | 46083 |
| Style Transfer (SP) | 411302 | 281860 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 9070 XT and RX 6800General
| Vendor | Amd | Amd |
| Build | Discrete | Discrete |
| Released | January 7, 2025 | October 28, 2020 |
| Launch price (MSRP) | $599 | $579 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | RDNA 4.0 | RDNA 2.0 |
| GPU Codename | Navi 48 | Navi 21 |
| Rival Equivalent | - GeForce RTX 5070 Ti | - GeForce RTX 3060 Ti |
| Recommended CPU | - Intel Core Ultra 5 245K or above | - Intel Core i5 12600 or above |
Desktop GPU rating (12th and 39th place)
Graphics Processing Unit
| Base Clock | 1660 MHz | 1700 MHz |
| Boost Clock | 2970 MHz | 2105 MHz |
| Shading Units | 4096 | 3840 |
| Texture Mapping Units (TMUs) | 256 | 240 |
| Render Output Units (ROPs) | 128 | 96 |
| Compute Units (Pipelines) | 64 | - |
| Tensor Cores | 128 | No |
| Ray-tracing Cores | 64 | 60 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 8MB shared | 4MB shared |
| Instructions Per Cycle | 4 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 380 GPixel/s | 202 GPixel/s |
| Texture Fill Rate | 760 GTexel/s | 505 GTexel/s |
FLOPS (FP32)
Differences in GPUs' instructions per clock make TFLOPS values not directly comparable.
Physical
| Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| TGP | 304 W | 250 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 4 nm | 7 nm |
| Die Size | 357 mm² | 520 mm² |
| Transistor Count | 53.9 billion | 26 billion |
| Transistor Density | 150.98 MTr/mm² | 50 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR6 |
| Memory Size | 16 GB | 16 GB |
| Memory Clock | 2518 MHz | 2000 MHz |
| Effective Memory Speed | 20100 Mbps | 16000 Mbps |
| Bus | 256-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12.2 | 12 |
| Vulkan | 1.4 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.2 | 2.1 |
| CUDA | No | - |
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
| DisplayPort | 2.1a | 1.4a |
Cast your vote
Total votes: 6
