Radeon RX 7800 XT VS Radeon RX 9070
We are comparing the Radeon RX 7800 XT ( AMD ) head-to-head with the Radeon RX 9070 ( AMD ) . You’ll get the key pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Note: This comparison of Radeon RX 7800 XT vs. Radeon RX 9070 is based on Comparigon's analysis and is for informational purposes only.
Last Updated: July 6, 2026
KEY DIFFERENCES OF Radeon RX 7800 XT AND Radeon RX 9070
Here’s how Radeon RX 7800 XT and Radeon RX 9070 stack up against each other in their most impactful areas. Use these bullets to see at a glance which graphics card excels where.
Reasons to consider the Radeon RX 7800 XT
-
3% higher FP32 Compute (37.32 TFLOPS vs 36.13 TFLOPS)
Reasons to consider the Radeon RX 9070
-
26% higher 4K Ultra FPS (83 vs 66)
-
22% higher 1440p Ultra FPS (139 vs 114)
-
21% higher 1080p Ultra FPS (180 vs 149)
-
4% higher Boost Clock (2520 MHz vs 2430 MHz)
-
34% higher 3DMark Time Spy score (26923 vs 20090)
SPECIFICATION TABLE COMPARISON OF Radeon RX 7800 XT AND Radeon RX 9070
Below is the detailed specification table comparing Radeon RX 7800 XT and Radeon RX 9070.
Note: Highlighted specs mean that GPU wins that spec row.
If neither side is highlighted, it is a tie or there is not enough data for both specs.
| Specification | Radeon RX 7800 XT | Radeon RX 9070 |
|---|---|---|
|
General Info
|
||
| GPU Name: | Radeon RX 7800 XT | Radeon RX 9070 |
| GPU Type: | Discrete | Discrete |
| Codename: | Navi 32 | Navi 48 |
| Vendor: | AMD | AMD |
| Foundry: | TSMC | TSMC |
| Architecture: | RDNA 3.0 | RDNA 4.0 |
| Generation: | Navi III (RX 7000) | Navi IV (RX 9000) |
| Release Date: | August 25, 2023 | March 6, 2025 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x16 | PCIe 5.0 x16 |
| PCIe Version: | 4.0 | 5.0 |
| PCIe Lanes: | x16 | x16 |
| Process Size: | 5 nm | 4 nm |
| Transistors: | 28.1 billion | 53.9 billion |
| Density: | 81.2 MTr/mm² | 151.19 MTr/mm² |
| Die Size: | 346 mm² | 356.5 |
| Board Length: | 267 mm | — |
| Board Width: | 50 mm | — |
| Board Height: | 111 mm | — |
| Total Graphics Power (TGP): | 263 W | 220 W |
|
Graphics Processor
|
||
| Compute Units: | 60 | 56 |
| Shading Units: | 3840 | 3584 |
| Texture Mapping Units (TMUs): | 240 | 224 |
| Render Output Units (ROPs): | 96 | 128 |
| Tensor Cores: | 120 | 112 |
| Ray Tracing Cores: | 60 | 56 |
| Base Clock: | 1295 MHz | 1330 |
| Boost Clock: | 2430 MHz | 2520 |
| L1 Cache: | 128 KB per Array | 128 KB per cluster |
| L2 Cache: | 4 MB | 8 MB |
| L3 Cache: | 64 MB | 64 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 233.3 GPixel/s | 322.6 GPixel/s |
| Texture Fill Rate: | 583.2 GTexel/s | 564.5 GTexel/s |
| FP32 Performance: | 37.32 TFLOPs | 36.13 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6 |
| Memory Size: | 16 GB | 16 GB |
| Memory Bus Width: | 256-bit | 256-bit |
| Memory Clock: | 2438 MHz | 2518 |
| Effective Memory Speed: | 19500 Mbps | 20100 |
| Bandwidth: | 624.1 GB/s | 640 |
|
APIs
|
||
| DirectX: | 12.2 | 12 |
| Vulkan: | 1.4 | 1.3 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 2.2 | 2.2 |
| CUDA: | No | No |
| Ray Tracing: | Yes | Yes |
| DLSS: | No | No |
| DisplayPort: | 2.1 | 2.1a |
| HDMI: | 2.1a | 2.1b |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 149 | 180 |
| 1440p Ultra (FPS): | 114 | 139 |
| 4K Ultra (FPS): | 66 | 83 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 18083 | 22669 |
| Time Spy | 20090 | 26923 |
| Solar Bay | 79881 | 105195 |
| Port Royal | 10915 | 16114 |
| Fire Strike | 50010 | 60172 |
| Wild Life Extreme | 36823 | 48175 |
| Night Raid | 160044 | 176602 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 148335 | 149949 |
| Background Blur | 300.7 | 377.5 |
| Face Detection | 200.5 | 221.3 |
| Horizon Detection | 5.77 | 6.4 |
| Edge Detection | 8.05 | 8.99 |
| Gaussian Blur | 6.44 | 8.52 |
| Feature Matching | 1.25 | 1.36 |
| Stereo Matching | 566.4 | 606 |
| Particle Physics | 20533.6 | 8521.2 |
|
Passmark Graphics
|
||
| G3D Mark | 24311 | 25420 |
| G2D Mark | 1190 | 1272 |
| DirectX 11 | 249 | 279 |
| DirectX 12 | 94 | 74 |
| GPU Compute | 13559 | 14801 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 230.10 | 274.70 |
| Aztec Ruins Normal | 1315.80 | 1412.60 |
| Car Chase | 1192.40 | 1332.40 |
| Manhattan 3.1.1 (1440p) | 955.30 | 1061.20 |
| T-Rex | 3880.70 | 4127.00 |
| Tessellation | 5363.20 | 6097.50 |
| ALU 2 | 6542.40 | 7774.70 |
| Driver Overhead 2 | 351.10 | 276.10 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 2411 | 2729 |
|
GeekBench 6 ML
|
||
| Single Precision | 31216 | 37056 |
| Half Precision | 37266 | 54866 |
| Quantized | 24564 | 29946 |
| Image Classification | 13913 | 15375 |
| Image Segmentation | 18416 | 37834 |
| Image Super Resolution | 31387 | 43910 |
| Face Detection | 51780 | 67858 |
| Pose Estimation | 177217 | 172939 |
| Text Classification | 3655 | 4469 |
| Machine Translation | 6216 | 8499 |
| Object Detection | 15073 | 15393 |
| Depth Estimation | 57318 | 66890 |
| Style Transfer | 347420 | 365633 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 12290 | 17149 |
| 1440p Vulkan | 9350 | 12146 |
| 2160p Vulkan | 4772 | 5814 |
| 1080p OpenGL | 12574 | 17615 |
| 1440p OpenGL | 9428 | 11876 |
| 2160p OpenGL | 5064 | 5810 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF Radeon RX 7800 XT AND Radeon RX 9070
The charts below visualize how Radeon RX 7800 XT and Radeon RX 9070 stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Value For Money Calculator
Prices use available launch or current data. Enter your own prices to see which GPU gives better value.
Radeon RX 7800 XT
Radeon RX 9070
Calculating...
Domain Score Summary
Note: Scores (0 to 100) are generated by Comparigon’s scoring algorithm and are intended as a high-level guide. They may not map 1-to-1 with the individual spec-by-spec comparisons shown in the table.
Our Verdict
In conclusion, the Radeon RX 9070 is clearly better overall compared to the Radeon RX 7800 XT. It comes out ahead across every comparable key area.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.