GeForce RTX 3090 Ti VS Radeon RX 6950 XT
We are comparing the GeForce RTX 3090 Ti (NVIDIA) with the Radeon RX 6950 XT (AMD). Scroll down to the pros and cons of each graphics card, in-depth specs, and gaming benchmarks.
Last Updated: November 20, 2026
Overall Comparison
KEY DIFFERENCES OF GeForce RTX 3090 Ti AND Radeon RX 6950 XT
Here’s how GeForce RTX 3090 Ti and Radeon RX 6950 XT stack up against each other in their most impactful areas.
Reasons to consider the GeForce RTX 3090 Ti
-
4% higher 4K Ultra FPS (75 vs 72)
-
32% higher 3DMark Port Royal score (14889 vs 11251)
-
4% higher PassMark G3D Mark score (29340 vs 28089)
-
22% higher Geekbench 6 OpenCL score (232083 vs 189857)
-
121% higher Blender score (6098 vs 2761)
Reasons to consider the Radeon RX 6950 XT
-
24% higher Boost Clock (2310 MHz vs 1860 MHz)
-
13% smaller process node (7 nm vs 8 nm)
SPECIFICATION TABLE COMPARISON OF GeForce RTX 3090 Ti AND Radeon RX 6950 XT
Below is the detailed specification table comparing GeForce RTX 3090 Ti and Radeon RX 6950 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 | GeForce RTX 3090 Ti | Radeon RX 6950 XT |
|---|---|---|
|
General Info
|
||
| GPU Name: | GeForce RTX 3090 Ti | Radeon RX 6950 XT |
| GPU Type: | Discrete | Discrete |
| Codename: | GA102 | Navi 21 |
| Vendor: | NVIDIA | AMD |
| Foundry: | Samsung | TSMC |
| Architecture: | Ampere | RDNA 2.0 |
| Generation: | GeForce 30 | Navi II (RX 6000) |
| Release Date: | January 27, 2022 | May 10, 2022 |
|
Board Design
|
||
| Bus Interface: | PCIe 4.0 x16 | PCIe 4.0 x16 |
| PCIe Version: | 4.0 | 4.0 |
| PCIe Lanes: | x16 | x16 |
| Process Size: | 8 nm | 7 nm |
| Transistors: | 28.3 billion | 26 billion |
| Density: | 45.1 MTr/mm² | 50 MTr/mm² |
| Die Size: | 628 mm² | 520 |
| Board Length: | 336 mm | 267 mm |
| Board Width: | 61 mm | 50 mm |
| Board Height: | 140 mm | 120 mm |
| Total Graphics Power (TGP): | 450 W | 335 W |
|
Graphics Processor
|
||
| Compute Units: | 84 | 80 |
| Shading Units: | 10752 | 5120 |
| Texture Mapping Units (TMUs): | 336 | 320 |
| Render Output Units (ROPs): | 112 | 128 |
| Tensor Cores: | 336 | — |
| Ray Tracing Cores: | 84 | 80 |
| Base Clock: | 1560 MHz | 1860 |
| Boost Clock: | 1860 MHz | 2310 |
| L1 Cache: | 128 KB per SM | 128 KB per Array |
| L2 Cache: | 6 MB | 4 MB |
| L3 Cache: | — | 128 MB |
|
Raw Performance
|
||
| Pixel Fill Rate: | 208.3 GPixel/s | 295.7 GPixel/s |
| Texture Fill Rate: | 625.0 GTexel/s | 739.2 GTexel/s |
| FP32 Performance: | 40.00 TFLOPs | 23.65 TFLOPs |
|
Memory
|
||
| Memory Type: | GDDR6X | GDDR6 |
| Memory Size: | 24 GB | 16 GB |
| Memory Bus Width: | 384-bit | 256-bit |
| Memory Clock: | 1313 MHz | 2250 |
| Effective Memory Speed: | 21000 Mbps | 18000 |
| Bandwidth: | 1008 GB/s | 576 |
|
APIs
|
||
| DirectX: | 12.2 | 12 |
| Vulkan: | 1.4 | 1.3 |
| OpenGL: | 4.6 | 4.6 |
| OpenCL: | 3.0 | 2.1 |
| CUDA: | 8.6 | — |
| Ray Tracing: | Yes | Yes |
| DLSS: | DLSS 2 | No |
| DisplayPort: | 1.4a | 1.4a |
| HDMI: | 2.1 | 2.1 |
|
Gaming FPS
|
||
| 1080p Ultra (FPS): | 162 | 161 |
| 1440p Ultra (FPS): | 127 | 124 |
| 4K Ultra (FPS): | 75 | 72 |
|
Benchmarks
|
||
|
3D Mark
|
||
| Steel Nomad Lite | 24355 | 20884 |
| Time Spy | 21851 | 21589 |
| Solar Bay | 109181 | 89220 |
| Port Royal | 14889 | 11251 |
| Fire Strike | 51956 | 59894 |
| Wild Life Extreme | 48863 | 40937 |
| Night Raid | 156306 | 163732 |
|
GeekBench 6 OpenCL
|
||
| Compute Score | 232083 | 189857 |
| Background Blur | 362.7 | 382.1 |
| Face Detection | 227.9 | 259 |
| Horizon Detection | 11.3 | 6.93 |
| Edge Detection | 15.9 | 10.2 |
| Gaussian Blur | 12.1 | 8.39 |
| Feature Matching | 1.56 | 1.48 |
| Stereo Matching | 1080 | 824.3 |
| Particle Physics | 31024.6 | 26538.1 |
|
Passmark Graphics
|
||
| G3D Mark | 29340 | 28089 |
| G2D Mark | 1228 | 1076 |
| DirectX 11 | 239 | 299 |
| DirectX 12 | 122 | 115 |
| GPU Compute | 16657 | 14177 |
|
GFXBench 5
|
||
| Aztec Ruins High (4K) | 249.00 | 305.60 |
| Aztec Ruins Normal | 1005.10 | 1467.20 |
| Car Chase | 897.20 | 1336.50 |
| Manhattan 3.1.1 (1440p) | 781.70 | 1142.60 |
| T-Rex | 4109.90 | 4554.60 |
| Tessellation | 7000.80 | 3895.60 |
| ALU 2 | 7102.50 | 6842.60 |
| Driver Overhead 2 | 274.90 | 288.20 |
| API | OpenGL | OpenGL |
| OS | Windows | Windows |
|
Blender (Rendering)
|
||
| Blender Score | 6098 | 2761 |
|
GeekBench 6 ML
|
||
| Single Precision | 26701 | 33294 |
| Half Precision | 38573 | 36737 |
| Quantized | 15995 | 24655 |
| Image Classification | 10246 | 14145 |
| Image Segmentation | 22830 | 18828 |
| Image Super Resolution | 23532 | 32309 |
| Face Detection | 48657 | 49133 |
| Pose Estimation | 147241 | 166767 |
| Text Classification | 2917 | 4491 |
| Machine Translation | 4427 | 6690 |
| Object Detection | 13323 | 15446 |
| Depth Estimation | 40055 | 56831 |
| Style Transfer | 298683 | 367328 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
|
FurMark
|
||
| 1080p Vulkan | 14720 | 16129 |
| 1440p Vulkan | 9754 | 11345 |
| 2160p Vulkan | 5128 | 6021 |
| 1080p OpenGL | 15145 | 17817 |
| 1440p OpenGL | 9990 | 12238 |
| 2160p OpenGL | 5442 | 6412 |
Tip: ▲ indicates a higher-is-better spec advantage, while ▼ indicates a lower-is-better advantage.
PERFORMANCE CHART COMPARISON OF GeForce RTX 3090 Ti AND Radeon RX 6950 XT
The charts below visualize how GeForce RTX 3090 Ti and Radeon RX 6950 XT 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.
GeForce RTX 3090 Ti
Radeon RX 6950 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 6950 XT edges out overall compared to the GeForce RTX 3090 Ti. Its strongest advantages are in AI & Machine Learning and Energy Efficiency. The GeForce RTX 3090 Ti is the better fit if your top priority is Hardware Architecture and Workstation.
Try to Compare Again One of These GPUs With Another GPU
Pick which GPU to keep, then search for the other GPU to compare.
Frequently Asked Questions about GeForce RTX 3090 Ti vs Radeon RX 6950 XT
GeForce RTX 3090 Ti scores 1.2% higher than Radeon RX 6950 XT in 3DMark Time Spy (21,851 vs 21,589).
GeForce RTX 3090 Ti scores 32.3% higher than Radeon RX 6950 XT in 3DMark Port Royal (14,889 vs 11,251).
GeForce RTX 3090 Ti scores 22.2% higher than Radeon RX 6950 XT in Geekbench 6 OpenCL (232,083 vs 189,857).
GeForce RTX 3090 Ti has 50% more graphics memory than Radeon RX 6950 XT (24 GB vs 16 GB).
GeForce RTX 3090 Ti has 75% higher memory bandwidth than Radeon RX 6950 XT (1008 GB/s vs 576 GB/s).
GeForce RTX 3090 Ti lists GDDR6X for memory type, while Radeon RX 6950 XT lists GDDR6 for memory type.
GeForce RTX 3090 Ti lists 450 W for graphics power, while Radeon RX 6950 XT lists 335 W for graphics power.
GeForce RTX 3090 Ti scores 120.9% higher than Radeon RX 6950 XT in Blender (6,098 vs 2,761).
Both list PCIe 4.0 x16 for bus interface.
GeForce RTX 3090 Ti was released on January 27, 2022. Radeon RX 6950 XT was released on May 10, 2022. Radeon RX 6950 XT was released 103 days after GeForce RTX 3090 Ti.
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.