Quick/Comparisons
The Nvidia RTX Pro 6000 Blackwell's exceptional gaming performance is due to its 99 score, a full 35 points ahead of the Radeon RX 7900 GRE's 64.
The Nvidia RTX Pro 6000 Blackwell's perfect score in workstation performance makes it the clear winner for content creation, outpacing the Radeon RX 7900 GRE by 20 points.
The Nvidia RTX Pro 6000 Blackwell's 93 score in AI/ML compute, a full 34 points ahead of the Radeon RX 7900 GRE's 59, makes it the winner for this use case.
99 | Gaming | 64 |
100 | Workstation | 60 |
93 | AI/ML |
Compare with something else?
Compare Nvidia RTX Pro with another →59 |
49 | Energy Efficiency | 44 |
98 | Quick Comparison Final Score | 62 |
| GB202-300-A1 | Graphics Processor | Navi 31 |
| 24064 | Cores | 5120 |
| 752 / 190 | TMUs / ROPs | 320 / 160 |
| 16644.8 | Blender GPU | 2808.96 |
| 230 | Forza Horizon 5 | 143 |
| 304 | The Witcher 3 | 201 |
| 259 | Counter-Strike 2 | 217 |
| 198 | Far Cry 6 | 155 |
| 192 | Hogwarts Legacy | 109 |
| 301 | Call of Duty | 190 |
| 172 | Ghost of Tsushima | 116 |
| 221 | Cyberpunk 2077 | 138 |
| 303 | Tomb Raider | 221 |
| 242 | Average FPS | 166 |
| 282 | 1080p High | 198 |
| 242 | 1080p Ultra | 166 |
| 197 | 1440p Ultra | 128 |
| 118 | 4K Ultra | 74 |
| High | Margin of Error | Low |
| 419470 | GB6 Compute Score | 172224 |
| 366.1 img/sec | Background Blur | 352.4 img/sec |
| 248 img/sec | Face Detection | 229 img/sec |
| 23.3 Gpixels/sec | Horizon Detection | 6.42 Gpixels/sec |
| 35.2 Gpixels/sec | Edge Detection | 8.86 Gpixels/sec |
| 45 Gpixels/sec | Gaussian Blur | 7.89 Gpixels/sec |
| 2.47 Gpixels/sec | Feature Matching | 1.5 Gpixels/sec |
| 3040 Gpixels/sec | Stereo Matching | 662.8 Gpixels/sec |
| 42574.6 FPS | Particle Physics | 24012 FPS |
| OpenCL | API | OpenCL |
| 37305 | G3D Mark Score | 27367 |
| 1375 | G2D Mark | 1207 |
| 338 FPS | DirectX 11 | 300 FPS |
| 153 FPS | DirectX 12 | 110 FPS |
| 26895 Ops/s | GPU Compute | 15171 Ops/s |
| 50053 | GB6 ML Single Precision | 34533 |
| 74036 | GB6 ML Half Precision | 42224 |
| 37636 | GB6 ML Quantized | 26568 |
| 16903 | Image Classification (SP) | 15095 |
| 48518 | Image Segmentation (HP) | 21206 |
| 54618 | Image Super Resolution (Q) | 33962 |
| 103224 | Face Detection (HP) | 57614 |
| 338587 | Pose Estimation (Q) | 214748 |
| 3894 | Text Classification (SP) | 4325 |
| 7291 | Machine Translation (HP) | 6598 |
| 26498 | Object Detection (SP) | 16608 |
| 90853 | Depth Estimation (Q) | 57731 |
| 635289 | Style Transfer (SP) | 394987 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 497 GPixel/s | Pixel Fill Rate | 359 GPixel/s |
| 1968 GTexel/s | Texture Fill Rate | 718 GTexel/s |
| 126 TFLOPS | FLOPS (FP32) | 46 TFLOPS |
| GDDR7 | Memory Type | GDDR6 |
| 96 GB | Memory Size | 16 GB |
| 1750 MHz | Memory Clock | 2250 MHz |
| 28000 Mbps | Effective Memory Speed | 18000 Mbps |
| 512-bit | Bus | 256-bit |
| Yes | ECC | No |
| 1792 GB/s | Memory Bandwidth | 576 GB/s |
| PCIe 5.0 x16 | Interface | PCIe 4.0 x16 |
| 600 W | TGP | 260 W |
| TSMC | Manufacturing | TSMC |
| 5 nm | Fabrication Process | 5 nm |
| 750 mm² | Die Size | 529 mm² |
| 92.2 billion | Transistor Count | 57 billion |
| 122.93 MTr/mm² | Transistor Density | 107.75 MTr/mm² |
| 12.2 | DirectX | 12 |
| 1.4 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 2.2 |
| 12 | CUDA | — |
| Yes | Ray Tracing | Yes |
| DLSS 4 | DLSS | No |
| 2.1b | DisplayPort | 2.1 |
| Nvidia | Vendor | Amd |
| Discrete | Build | Discrete |
| March 18, 2026 | Released | — |
| Desktop | Case | Desktop |
| Professional | Purpose | Gaming |
| High-end | Segment | High-end |
| Blackwell 2.0 | Architecture | RDNA 3.0 |
| GB202-300-A1 | GPU Codename | Navi 31 |
| -AMD Ryzen 9 9955HX3Dor above | Recommended CPU | — |
| 50516 | Steel Nomad Lite Score | 21359 |
| 42437 | Time Spy | 22537 |
| 258808 | Solar Bay | 90757 |
| 39952 | Port Royal | 12461 |
| 72183 | Fire Strike | 56212 |
| 110070 | Wild Life Extreme | 41740 |
| 216213 | Night Raid | 169038 |
| 1590 MHz | Base Clock | 1287 MHz |
| 2617 MHz | Boost Clock | 2245 MHz |
| 24064 | Shading Units | 5120 |
| 752 | Texture Mapping Units (TMUs) | 320 |
| 190 | Render Output Units (ROPs) | 160 |
| 188 | Compute Units (Pipelines) | — |
| 752 | Tensor Cores | — |
| 188 | Ray-tracing Cores | 80 |
| 128KB per cluster | L1 Cache | 256KB per cluster |
| 128MB shared | L2 Cache | 6MB shared |
| 2 IPC | Instructions Per Cycle | 4 IPC |