Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's exceptional gaming performance is unmatched, thanks to its 99 score, while the Radeon RX 6650 XT trails far behind with a 30 score.
The Nvidia RTX Pro 6000 Blackwell's perfect score in workstation performance makes it the clear winner, while the Radeon RX 6650 XT's 34 score is respectable but not enough to catch up.
Although the Nvidia RTX Pro 6000 Blackwell's AI/ML score is only 2 points higher, its 93 score is still significantly better than the Radeon RX 6650 XT's 31 score, thanks to its capable AI/ML compute.
99 | Gaming | 30 |
100 | Workstation | 34 |
93 | AI/ML | 31 |
49 | Energy Efficiency | 39 |
98 | Quick Comparison Final Score | 31 |
| GB202-300-A1 | Graphics Processor | Navi 23 |
| 24064 | Cores | 2048 |
| 752 / 190 | TMUs / ROPs | 128 / 64 |
| 16644.8 | Blender GPU | 1138.24 |
| 230 | Forza Horizon 5 | 76 |
| 304 | The Witcher 3 | 101 |
| 259 | Counter-Strike 2 | 130 |
| 198 | Far Cry 6 | 93 |
| 192 | Hogwarts Legacy | 59 |
| 301 | Call of Duty | 87 |
| 172 | Ghost of Tsushima | 63 |
| 221 | Cyberpunk 2077 | 65 |
| 303 | Tomb Raider | 111 |
| 242 | Average FPS | 87 |
| 282 | 1080p High | 112 |
| 242 | 1080p Ultra | 87 |
| 197 | 1440p Ultra | 61 |
| 118 | 4K Ultra | 32 |
| High | Margin of Error | Low |
| 419470 | GB6 Compute Score | 90831 |
| 366.1 img/sec | Background Blur | 220.1 img/sec |
| 248 img/sec | Face Detection | 128.3 img/sec |
| 23.3 Gpixels/sec | Horizon Detection | 2.94 Gpixels/sec |
| 35.2 Gpixels/sec | Edge Detection | 4.13 Gpixels/sec |
| 45 Gpixels/sec | Gaussian Blur | 3.68 Gpixels/sec |
| 2.47 Gpixels/sec | Feature Matching | 0.94 Gpixels/sec |
| 3040 Gpixels/sec | Stereo Matching | 408.2 Gpixels/sec |
| 42574.6 FPS | Particle Physics | 10694.7 FPS |
| OpenCL | API | OpenCL |
| 37305 | G3D Mark Score | 17117 |
| 1375 | G2D Mark | 924 |
| 338 FPS | DirectX 11 | 168 FPS |
| 153 FPS | DirectX 12 | 62 FPS |
| 26895 Ops/s | GPU Compute | 7461 Ops/s |
| 50053 | GB6 ML Single Precision | 17945 |
| 74036 | GB6 ML Half Precision | 21242 |
| 37636 | GB6 ML Quantized | 13940 |
| 16903 | Image Classification (SP) | 8220 |
| 48518 | Image Segmentation (HP) | 9263 |
| 54618 | Image Super Resolution (Q) | 20723 |
| 103224 | Face Detection (HP) | 27074 |
| 338587 | Pose Estimation (Q) | 76541 |
| 3894 | Text Classification (SP) | 2796 |
| 7291 | Machine Translation (HP) | 4281 |
| 26498 | Object Detection (SP) | 6880 |
| 90853 | Depth Estimation (Q) | 33354 |
| 635289 | Style Transfer (SP) | 185358 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 497 GPixel/s | Pixel Fill Rate | 169 GPixel/s |
| 1968 GTexel/s | Texture Fill Rate | 337 GTexel/s |
| 126 TFLOPS | FLOPS (FP32) | 10.8 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 96 GB | Memory Size | 8 GB |
| 1750 MHz | Memory Clock | 2190 MHz |
| 28000 Mbps | Effective Memory Speed | 17500 Mbps |
| 512-bit | Bus | 128-bit |
| Yes | ECC | No |
| 1792 GB/s | Memory Bandwidth | 280.3 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x8 |
| 600 W | TGP | 176 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 7 nm |
| 750 mm² | Die Size | 237 mm² |
| 92.2 billion | Transistor Count | 11 billion |
| 122.93 MTr/mm² | Transistor Density | 46.41 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.1 |
| 12 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 1.4a |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| March 18, 2026 | Released | May 10, 2022 |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | RDNA 2.0 |
| GB202-300-A1 | GPU Codename | Navi 23 |
| -AMD Ryzen 9 9955HX3Dor above | Recommended CPU | -Intel Core i5 12600Kor above |
| 50516 | Steel Nomad Lite Score | 9265 |
| 42437 | Time Spy | 9897 |
| 258808 | Solar Bay | 38892 |
| 39952 | Port Royal | 4897 |
| 72183 | Fire Strike | 29357 |
| 110070 | Wild Life Extreme | 18034 |
| 216213 | Night Raid | 116256 |
| 1590 MHz | Base Clock | 2055 MHz |
| 2617 MHz | Boost Clock | 2635 MHz |
| 24064 | Shading Units | 2048 |
| 752 | Texture Mapping Units (TMUs) | 128 |
| 190 | Render Output Units (ROPs) | 64 |
| 188 | Compute Units (Pipelines) | — |
| 752 | Tensor Cores | No |
| 188 | Ray-tracing Cores | 32 |
| 128KB per cluster | L1 Cache | 128KB per cluster |
| 128MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |
Compare with something else?
Compare Nvidia RTX Pro with another →