Radeon RX 6400 VS Radeon RX 6500 XT
We are comparing the Radeon RX 6400 (AMD) with the Radeon RX 6500 XT (AMD). Scroll down to the pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Last Updated: September 15, 2026
Overall Comparison
KEY DIFFERENCES OF Radeon RX 6400 AND Radeon RX 6500 XT
Here’s how Radeon RX 6400 and Radeon RX 6500 XT stack up against each other in their most impactful areas.
Why Radeon RX 6500 XT is the best choice:
-
200% higher 4K Ultra FPS (15 vs 5)
-
222% higher 1440p Ultra FPS (29 vs 9)
-
283% higher 1080p Ultra FPS (46 vs 12)
-
21% higher Boost Clock (2815 MHz vs 2321 MHz)
-
24% higher PassMark G3D Mark score (9634 vs 7745)
SPECIFICATION TABLE COMPARISON OF Radeon RX 6400 AND Radeon RX 6500 XT
Below is the detailed specification table comparing Radeon RX 6400 and Radeon RX 6500 XT.
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 6400 | Radeon RX 6500 XT |
|---|---|---|
|
General Info
|
||
| GPU Name: | Radeon RX 6400 | Radeon RX 6500 XT |
| GPU Type: | Discrete | Discrete |
| Codename: | Navi 24 | Navi 24 |
| Vendor: | AMD | AMD |
| Foundry: | TSMC | TSMC |
| Architecture: | RDNA 2.0 | RDNA 2.0 |
| Generation: | Navi II (RX 6000) | Navi II (RX 6000) |
| Release Date: | January 19, 2022 | January 19, 2022 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x4 | PCIe 4.0 x4 |
| PCIe Version: | 4.0 | 4.0 |
| PCIe Lanes: | 4 | 4 |
| Process Size: | 6 nm | 6 nm |
| Transistors: | 5.4 billion | 5.4 billion |
| Density: | 50.5 MTr/mm² | 50.5 MTr/mm² |
| Die Size: | 107 mm² | 107 mm² |
| Total Graphics Power (TGP): | 53 W | 107 W |
|
Graphics Processor
|
||
| Compute Units: | 12 | 16 |
| Shading Units: | 768 | 1024 |
| Texture Mapping Units (TMUs): | 48 | 64 |
| Render Output Units (ROPs): | 32 | 32 |
| Ray Tracing Cores: | 12 | 16 |
| Base Clock: | 1923 MHz | 2310 MHz |
| Boost Clock: | 2321 MHz | 2815 MHz |
| L1 Cache: | 128 KB per Array | 128 KB per Array |
| L2 Cache: | 1024 KB | 1024 KB |
| L3 Cache: | 16 MB | 16 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 74.27 GPixel/s | 90.08 GPixel/s |
| Texture Fill Rate: | 111.4 GTexel/s | 180.2 GTexel/s |
| FP32 Performance: | 3.565 TFLOPs | 5.765 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6 | GDDR6 |
| Memory Size: | 4 GB | 4 GB |
| Memory Bus Width: | 64-bit | 64-bit |
| Memory Clock: | 2000 MHz | 2248 MHz |
| Effective Memory Speed: | 16000 Mbps | 18000 Mbps |
| Bandwidth: | 128 GB/s | 143.9 GB/s |
|
APIs
|
||
| DirectX: | 12 Ultimate (12_2) | 12.2 |
| Vulkan: | 1.4 | 1.4 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 2.2 | 2.2 |
| Ray Tracing: | 1 | 1 |
| DisplayPort: | 1.4a | 1.4a |
| HDMI: | 2.1 | 2.1 |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 12 | 46 |
| 1440p Ultra (FPS): | 9 | 29 |
| 4K Ultra (FPS): | 5 | 15 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | — | 4767 |
| Time Spy | — | 4945 |
| Solar Bay | — | 19998 |
| Port Royal | — | 368 |
| Fire Strike | — | 15573 |
| Wild Life Extreme | — | 8980 |
| Night Raid | — | 65398 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | — | 53081 |
| Background Blur | — | 130.3 img/sec |
| Face Detection | — | 70.1 img/sec |
| Horizon Detection | — | 1.59 Gpixels/sec |
| Edge Detection | — | 2.21 Gpixels/sec |
| Gaussian Blur | — | 2.02 Gpixels/sec |
| Feature Matching | — | 0.65 Gpixels/sec |
| Stereo Matching | — | 223 Gpixels/sec |
| Particle Physics | — | 7470.5 |
|
Passmark Graphics
|
||
| G3D Mark | 7745 | 9634 |
| G2D Mark | 738 | 818 |
| DirectX 11 | 70 | 90 |
| DirectX 12 | 31 | 38 |
| GPU Compute | 2788 | 4345 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | — | 52.40 |
| Aztec Ruins Normal | — | 360.90 |
| Car Chase | — | 373.90 |
| Manhattan 3.1.1 (1440p) | — | 281.00 |
| T-Rex | — | 1305.60 |
| Tessellation | — | 1300.50 |
| ALU 2 | — | 1331.20 |
| Driver Overhead 2 | — | 259.20 |
| API | — | OpenGL |
| OS | — | Windows |
|
Blender (Rendering)
|
||
| Blender Score | — | 424 |
|
GeekBench 6 ML
|
||
| Single Precision | — | 10359 |
| Half Precision | — | 12861 |
| Quantized | — | 7842 |
| Image Classification | — | 3867 |
| Image Segmentation | — | 5136 |
| Image Super Resolution | — | 11758 |
| Face Detection | — | 14844 |
| Pose Estimation | — | 42787 |
| Text Classification | — | 1986 |
| Machine Translation | — | 2665 |
| Object Detection | — | 4251 |
| Depth Estimation | — | 19707 |
| Style Transfer | — | 101802 |
| Framework | — | ONNX |
| Backend | — | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 2856 | — |
| 1440p Vulkan | 1803 | — |
| 2160p Vulkan | 4620 | — |
| 1080p OpenGL | 3004 | — |
| 1440p OpenGL | 1848 | — |
| 2160p OpenGL | 881 | 781 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF Radeon RX 6400 AND Radeon RX 6500 XT
The charts below visualize how Radeon RX 6400 and Radeon RX 6500 XT stack up in key performance metrics.
Radar Chart Comparison
Bullet Chart Comparison
Release Timeline of Radeon RX 6400 and Radeon RX 6500 XT
Radeon RX 6400 and Radeon RX 6500 XT were released on the same day.
Value For Money Calculator
Prices use available launch or current data. Enter your own prices to see which GPU gives better value.
Radeon RX 6400
Radeon RX 6500 XT
Calculating...
Domain Score Summary
Scores 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 6500 XT edges out overall compared to the Radeon RX 6400. Its strongest advantages are in Gaming Performance, AI & Machine Learning and Workstation. They are still fairly close in Hardware Architecture.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.
Disclaimer: Specs, pricing, and benchmarks are sourced from official manufacturer data and verified test results. While we strive for precision, product details and pricing may change. Comparigon may earn an affiliate commission on qualifying purchases.