Nvidia RTX Pro 6000 Blackwell vs Radeon RX 9070

[ VERDICT ] Winner: Nvidia RTX Pro 6000 Blackwell (98/100)

Nvidia RTX Pro 6000 Blackwell leads overall with a score of 98/100 compared to Radeon RX 9070 (62/100), offering superior measured performance and technical specifications.

Benchmark Performance Comparison

Normalized Lab Scores
Benchmark measurements and scores across compared devices
Benchmark Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Efficiency 49.0 Poor WINNER 48.0 Poor
Gaming 99.0 Excellent WINNER 66.0 Average

Detailed Technical Specifications

3D Mark

3D Mark specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Fire Strike 75325 60053
Night Raid 214655 177554
Port Royal 39888 15939
Solar Bay 255911 106118
Time Spy 42614 26693
Wild Life Extreme 110070 48323

API

API specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
CUDA 12 No
DLSS DLSS 4 No
DirectX 12.2 12
DisplayPort 2.1b 2.1a
OpenCL 3.0 2.2
OpenGL 4.6 4.6
Ray Tracing Yes Yes
Vulkan 1.4 1.3

Games

Games specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
1080p High 284 213
1080p Ultra 242 178
1440p Ultra 196 139
4K Ultra 118 82
CoD: Modern Warfare III 305296252176 219212157107
Counter-Strike 2 36226320393 30721515884
Cyberpunk 2077 25322116071 17414910247
Far Cry 6 221198185112 19216314895
Forza Horizon 5 309235215175 229156137102
Ghost of Tsushima 206170158107 14612210565
Hogwarts Legacy 23518915089 1461199752
Margin of Error High Low
Shadow of the Tomb Raider 319298224121 26224818899
The Witcher 3 343311216116 24021615984

GeekBench 6 ML

GeekBench 6 ML specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Backend DirectML DirectML
Depth Estimation (Q) 90853 66890
Face Detection (HP) 103224 67858
Framework ONNX ONNX
Image Classification (SP) 16903 15375
Image Segmentation (HP) 48518 37834
Image Super Resolution (Q) 54618 43910
Machine Translation (HP) 7291 8499
Object Detection (SP) 26498 15393
Pose Estimation (Q) 338587 172939
Style Transfer (SP) 635289 365633
Text Classification (SP) 3894 4469

GeekBench 6 OpenCL

GeekBench 6 OpenCL specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
API OpenCL OpenCL
Background Blur 366.1 img/sec 377.5 img/sec
Edge Detection 35.2 Gpixels/sec 8.99 Gpixels/sec
Face Detection 248 img/sec 221.3 img/sec
Feature Matching 2.47 Gpixels/sec 1.36 Gpixels/sec
Gaussian Blur 45 Gpixels/sec 8.52 Gpixels/sec
Horizon Detection 23.3 Gpixels/sec 6.4 Gpixels/sec
Particle Physics 42574.6 FPS 8521.2 FPS
Stereo Matching 3040 Gpixels/sec 606 Gpixels/sec

General

General specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Architecture Blackwell 2.0 RDNA 4.0
Build Discrete Discrete
Case Desktop Desktop
GPU Codename GB202-300-A1 Navi 48
Launch price (MSRP) $8559 $549
Purpose Professional Gaming
Recommended CPU -AMD Ryzen 9 9955HX3Dor above -Intel Core Ultra 5 245Kor above
Released March 18, 2026 January 7, 2025
Segment High-end High-end
Vendor Nvidia Amd
Nvidia Equivalent -GeForce RTX 5070

Graphics Processing Unit

Graphics Processing Unit specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Base Clock 1590 MHz 1330 MHz
Boost Clock 2617 MHz 2520 MHz
Compute Units (Pipelines) 188 56
Instructions Per Cycle 2 IPC 4 IPC
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 128MB shared 4MB shared
Ray-tracing Cores 188 56
Render Output Units (ROPs) 190 128
Shading Units 24064 3584
Tensor Cores 752 112
Texture Mapping Units (TMUs) 752 224

Memory

Memory specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Bus 512-bit 256-bit
ECC Yes No
Effective Memory Speed 28000 Mbps 20100 Mbps
Memory Clock 1750 MHz 2518 MHz
Memory Size 96 GB 16 GB
Memory Type GDDR7 GDDR6

Passmark Graphics

Passmark Graphics specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
DirectX 11 339 FPS 280 FPS
DirectX 12 154 FPS 73 FPS
G2D Mark 1391 1263
GPU Compute 26607 Ops/s 14791 Ops/s

Physical

Physical specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Die Size 750 mm² 356.5 mm²
Fabrication Process 5 nm 4 nm
Interface PCIe 5.0 x16 PCIe 5.0 x16
Manufacturing TSMC TSMC
TGP 600 W 220 W
Transistor Count 92.2 billion 53.9 billion
Transistor Density 122.93 MTr/mm² 151.19 MTr/mm²

Raw Performance

Raw Performance specifications comparison
Specification Nvidia RTX Pro 6000 Blackwell Radeon RX 9070
Pixel Fill Rate 497 GPixel/s 323 GPixel/s
Texture Fill Rate 1968 GTexel/s 564 GTexel/s

Looking for More Comparisons?

Browse all available head-to-head comparisons or select new devices in the comparison hub.

Browse Graphics Cards Comparisons → Launch Full Comparison Hub →