Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's 99 score leaves the Radeon RX 6600 XT's 29 score in the dust, thanks to its superior performance in demanding games.
The Nvidia RTX Pro 6000 Blackwell's 100 score in workstation performance is unmatched by the Radeon RX 6600 XT's 33 score, making it the clear winner for content creation tasks.
The Nvidia RTX Pro 6000 Blackwell's 93 score in AI/ML compute is significantly higher than the Radeon RX 6600 XT's 26 score, thanks to its dedicated AI tensor cores and overall architecture.
99 | Gaming | 29 |
100 | Workstation | 33 |
93 | AI/ML | 26 |
49 | Energy Efficiency | 43 |
98 | Quick Comparison Final Score | 30 |
| GB202-300-A1 | Graphics Processor | Navi 23 |
| 24064 | Cores | 2048 |
| 752 / 190 | TMUs / ROPs | 128 / 64 |
| 16644.8 | Blender GPU | 1068.29 |
| 230 | Forza Horizon 5 | 75 |
| 304 | The Witcher 3 | 97 |
| 259 | Counter-Strike 2 | 130 |
| 198 | Far Cry 6 | 90 |
| 192 | Hogwarts Legacy | 59 |
| 301 | Call of Duty | 88 |
| 172 | Ghost of Tsushima | 60 |
| 221 | Cyberpunk 2077 | 65 |
| 303 | Tomb Raider | 106 |
| 242 | Average FPS | 86 |
| 282 | 1080p High | 109 |
| 242 | 1080p Ultra | 86 |
| 197 | 1440p Ultra | 59 |
| 118 | 4K Ultra | 33 |
| High | Margin of Error | Low |
| 419470 | GB6 Compute Score | 84088 |
| 366.1 img/sec | Background Blur | 208 img/sec |
| 248 img/sec | Face Detection | 114.6 img/sec |
| 23.3 Gpixels/sec | Horizon Detection | 2.91 Gpixels/sec |
| 35.2 Gpixels/sec | Edge Detection | 3.71 Gpixels/sec |
| 45 Gpixels/sec | Gaussian Blur | 3.38 Gpixels/sec |
| 2.47 Gpixels/sec | Feature Matching | 0.94 Gpixels/sec |
| 3040 Gpixels/sec | Stereo Matching | 306 Gpixels/sec |
| 42574.6 FPS | Particle Physics | 11198.1 FPS |
| OpenCL | API | OpenCL |
| 37305 | G3D Mark Score | 16449 |
| 1375 | G2D Mark | 914 |
| 338 FPS | DirectX 11 | 163 FPS |
| 153 FPS | DirectX 12 | 61 FPS |
| 26895 Ops/s | GPU Compute | 7430 Ops/s |
| 50053 | GB6 ML Single Precision | 15318 |
| 74036 | GB6 ML Half Precision | 17737 |
| 37636 | GB6 ML Quantized | 11021 |
| 16903 | Image Classification (SP) | 6815 |
| 48518 | Image Segmentation (HP) | 8295 |
| 54618 | Image Super Resolution (Q) | 18041 |
| 103224 | Face Detection (HP) | 21268 |
| 338587 | Pose Estimation (Q) | 71311 |
| 3894 | Text Classification (SP) | 1967 |
| 7291 | Machine Translation (HP) | 3539 |
| 26498 | Object Detection (SP) | 6006 |
| 90853 | Depth Estimation (Q) | 28767 |
| 635289 | Style Transfer (SP) | 169389 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 497 GPixel/s | Pixel Fill Rate | 166 GPixel/s |
| 1968 GTexel/s | Texture Fill Rate | 331 GTexel/s |
| 126 TFLOPS | FLOPS (FP32) | 10.6 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 96 GB | Memory Size | 8 GB |
| 1750 MHz | Memory Clock | 2000 MHz |
| 28000 Mbps | Effective Memory Speed | 16000 Mbps |
| 512-bit | Bus | 128-bit |
| Yes | ECC | No |
| 1792 GB/s | Memory Bandwidth | 256 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x8 |
| 600 W | TGP | 160 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 | July 30, 2021 |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | Mid-range |
| Blackwell 2.0 | Architecture | RDNA 2.0 |
| GB202-300-A1 | GPU Codename | Navi 23 |
| -AMD Ryzen 9 9955HX3Dor above | Recommended CPU | -Intel Core i5 13600or above |
| 50516 | Steel Nomad Lite Score | 8988 |
| 42437 | Time Spy | 9638 |
| 258808 | Solar Bay | 37707 |
| 39952 | Port Royal | 4633 |
| 72183 | Fire Strike | 28661 |
| 110070 | Wild Life Extreme | 17380 |
| 216213 | Night Raid | 114347 |
| 1590 MHz | Base Clock | 1968 MHz |
| 2617 MHz | Boost Clock | 2589 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 →