AMD Radeon RX 6800 XT vs GeForce RTX 5070
VS
AMD Radeon RX 6800 XT
Navi 21
Nvidia GeForce RTX 5070
GB205-300
We compared two discrete desktop gaming GPUs: the Radeon RX 6800 XT 16 GB with 4608 shaders against the 4 years and 2 months newer GeForce RTX 5070 12 GB that utilizes 48 pipelines and 6144 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 6800 XT
- Includes 4 GB more video memory
Reasons to consider the GeForce RTX 5070
- Performs better (up to 32%) in 3DMark Steel Nomad Lite
- Manufactured using a more efficient 4 nm process technology
- 49% higher maximum theoretical performance (30.9 vs 20.7 TFLOPS)
- Shows 15% higher average frame rate in modern games at QHD resolution – 128 vs 111 FPS
- Supports Nvidia DLSS 4 technology
- Achieves 38% more points in the GeekBench 6 Compute test (190K vs 138K)
- Has 31% higher memory bandwidth: 672 vs 512 GB/s
- Has 33% more shading units (6144 vs 4608)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 198 131 109 83 |
197 140 130 97 |
| The Witcher 3 | 192 173 127 68 |
216 183 131 71 |
| Counter-Strike 2 | 285 203 145 80 |
293 210 160 81 |
| Far Cry 6 | 164 144 120 75 |
164 145 128 82 |
| Hogwarts Legacy | 120 96 76 42 |
140 117 92 51 |
| CoD: Modern Warfare III | 168 160 116 76 |
178 171 136 89 |
| Ghost of Tsushima | 125 104 84 53 |
123 107 89 58 |
| Cyberpunk 2077 | 129 116 79 36 |
164 144 99 43 |
| Shadow of the Tomb Raider | 209 191 142 74 |
253 238 189 98 |
| 1080p High | 177 | 192 |
| 1080p Ultra | 146 | 162 |
| 1440p Ultra | 111 | 128 |
| 4K Ultra | 65 | 74 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 19379 | 22708 |
| Solar Bay | 78685 | 107004 |
| Port Royal | 9715 | 14498 |
| Fire Strike | 53014 | 58324 |
| Wild Life Extreme | 35635 | 43879 |
| Night Raid | 155323 | 172064 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 335.7 img/sec | 254.4 img/sec |
| Face Detection | 221.1 img/sec | 180.6 img/sec |
| Horizon Detection | 6.16 Gpixels/sec | 7.91 Gpixels/sec |
| Edge Detection | 8.96 Gpixels/sec | 10.2 Gpixels/sec |
| Gaussian Blur | 7.44 Gpixels/sec | 10.7 Gpixels/sec |
| Feature Matching | 1.31 Gpixels/sec | 1.84 Gpixels/sec |
| Stereo Matching | 263 Gpixels/sec | 975.7 Gpixels/sec |
| Particle Physics | 14755 FPS | 27816.5 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Passmark Graphics
G3D Mark Score
| G2D Mark | 1046 | 1289 |
| DirectX 11 | 265 FPS | 279 FPS |
| DirectX 12 | 100 FPS | 106 FPS |
| GPU Compute | 13077 Ops/s | 14323 Ops/s |
Blender
Blender GPU
Recent User Tests
Radeon RX 6800 XT
| Date | Benchmark | Result |
|---|---|---|
| 📘 2026-06-10 (XYQUE) | Cinebench 2024 | 41600 |
GeForce RTX 5070
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) | 11942 | 12270 |
| Image Segmentation (HP) | 7603 | 30237 |
| Image Super Resolution (Q) | 30511 | 35585 |
| Face Detection (HP) | 42862 | 62662 |
| Pose Estimation (Q) | 160019 | 145190 |
| Text Classification (SP) | 4247 | 4198 |
| Machine Translation (HP) | 6279 | 6233 |
| Object Detection (SP) | 13910 | 16709 |
| Depth Estimation (Q) | 51794 | 58300 |
| Style Transfer (SP) | 324124 | 246598 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 6800 XT and GeForce RTX 5070General
| Vendor | Amd | Nvidia |
| Build | Discrete | Discrete |
| Released | November 18, 2020 | January 7, 2025 |
| Launch price (MSRP) | $649 | $549 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | RDNA 2.0 | Blackwell 2.0 |
| GPU Codename | Navi 21 | GB205-300 |
| Rival Equivalent | - GeForce RTX 4070 | - Radeon RX 9070 |
| Successor | - Radeon RX 9070 XT | - |
| Recommended CPU | - Intel Core i7 12700K or above | - Intel Core Ultra 5 245K or above |
Desktop GPU rating (31st and 17th place)
Graphics Processing Unit
| Base Clock | 1825 MHz | 2160 MHz |
| Boost Clock | 2250 MHz | 2512 MHz |
| Shading Units | 4608 | 6144 |
| Texture Mapping Units (TMUs) | 288 | 192 |
| Render Output Units (ROPs) | 128 | 80 |
| Compute Units (Pipelines) | - | 48 |
| Tensor Cores | - | 192 |
| Ray-tracing Cores | 72 | 48 |
| L1 Cache | 128KB per cluster | 128KB per cluster |
| L2 Cache | 4MB shared | 48MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 288 GPixel/s | 201 GPixel/s |
| Texture Fill Rate | 648 GTexel/s | 482 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| TGP | 300 W | 250 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 7 nm | 4 nm |
| Die Size | 520 mm² | 263 mm² |
| Transistor Count | 26 billion | 31.1 billion |
| Transistor Density | 50 MTr/mm² | 118.25 MTr/mm² |
Memory
| Memory Type | GDDR6 | GDDR7 |
| Memory Size | 16 GB | 12 GB |
| Memory Clock | 2000 MHz | 1750 MHz |
| Effective Memory Speed | 16000 Mbps | 28000 Mbps |
| Bus | 256-bit | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| DirectX | 12 | 12.2 |
| Vulkan | 1.3 | 1.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| CUDA | - | 12.0 |
| Ray Tracing | Yes | Yes |
| DLSS | No | DLSS 4 |
| DisplayPort | 1.4a | 2.1b |
Cast your vote
Total votes: 23