AMD Radeon RX 9070 XT vs GeForce RTX 3070

We compared two discrete desktop gaming GPUs: the Radeon RX 9070 XT 16 GB with 64 pipelines and 4096 shaders against the 4 years and 3 months older GeForce RTX 3070 8 GB that utilizes 46 pipelines and 5888 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
DeviceFacts Final Score
Overall video card score

Value for money (Beta)

We use average GPU prices from all manufacturers by default. Enter the current price of a specific card for better accuracy.
Currency
16 GB GDDR6
VS
8 GB GDDR6
98.8
(Very good)
Value Index
96.5
(Very good)

Key differences

Key distinctions and advantages of RTX 3070 over RX 9070 XT
Reasons to consider the Radeon RX 9070 XT
  • Performs significantly better (up to 85%) in 3DMark Steel Nomad Lite
  • 2.4x higher maximum theoretical performance (48.7 vs 20.3 TFLOPS)
  • Manufactured using a more efficient 4 nm process technology
  • Shows 73% higher average frame rate in modern games at QHD resolution – 152 vs 88 FPS
  • Includes 8 GB more video memory
  • Has 44% higher memory bandwidth: 644.6 vs 448 GB/s
  • Achieves 45% more points in the GeekBench 6 Compute test (182K vs 126K)
Reasons to consider the GeForce RTX 3070
  • Supports Nvidia DLSS 2 technology
  • Features 56 more tensor cores for effective ML and AI workloads
  • Has 44% more shading units (5888 vs 4096)

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions

Games

FPS Table
Forza Horizon 5
242
169
149
109
147
99
86
61
The Witcher 3
267
237
167
89
168
143
100
54
Counter-Strike 2
325
224
163
82
244
194
137
77
Far Cry 6
198
176
163
104
132
121
96
54
Hogwarts Legacy
162
133
107
58
97
80
62
35
CoD: Modern Warfare III
240
232
174
118
121
113
85
52
Ghost of Tsushima
158
137
116
73
89
74
56
31
Cyberpunk 2077
190
171
119
53
106
94
59
28
Shadow of the Tomb Raider
280
265
207
107
165
153
113
60
Average FPS by Resolution
1080p High 229 141
1080p Ultra 194 119
1440p Ultra 152 88
4K Ultra 88 50
Margin of Error Low Low

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
RX 9070 XT +85%
26251
14152
Time Spy 29556 13644
Solar Bay 122220 64452
Port Royal 18363 8312
Fire Strike 66319 34056
Wild Life Extreme 54672 28488
Night Raid 194947 122159
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
RX 9070 XT +45%
182816
126195
Background Blur 427.4 img/sec 161.6 img/sec
Face Detection 251 img/sec 117.2 img/sec
Horizon Detection 6.77 Gpixels/sec 5.89 Gpixels/sec
Edge Detection 9.42 Gpixels/sec 8.05 Gpixels/sec
Gaussian Blur 9.35 Gpixels/sec 6.65 Gpixels/sec
Feature Matching 1.42 Gpixels/sec 1.25 Gpixels/sec
Stereo Matching 651.4 Gpixels/sec 550.6 Gpixels/sec
Particle Physics 23630 FPS 17613.1 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Cinebench 2024 GPU

Hardware benchmark using Maxon's Cinema 4D rendering engine
Cinebench 2024 GPU
RX 9070 XT +419%
50113
9652

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
RX 9070 XT +22%
26913
22079
G2D Mark 1310 1005
DirectX 11 295 FPS 183 FPS
DirectX 12 77 FPS 84 FPS
GPU Compute 16100 Ops/s 11007 Ops/s
Sources: PassMark [5], [6] – 17863 & 38662 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
3287.07
RTX 3070 +2%
3356.03
Sources: Blender [9], [10] – 1724 & 4796 samples

Recent User Tests

The latest benchmark tests that have been submitted by users
Radeon RX 9070 XT
DateBenchmarkResult
📘 2026-07-12 (luizmdd)Cinebench 202450113
📘 2026-07-04 -> StevenSGeekbench 6 OpenCL179283
📘 2026-07-04 -> StevenSSteel Nomad Light27505
📘 2025-10-15 (adv)Geekbench 6 OpenCL175418
GeForce RTX 3070
DateBenchmarkResult
📘 2025-11-15 (mit)Cinebench 20249652

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
RX 9070 XT +98%
39190
19789
GB6 ML Half Precision
RX 9070 XT +69%
55727
33013
GB6 ML Quantized
RX 9070 XT +170%
33599
12443
Image Classification (SP) 18001 7624
Image Segmentation (HP) 25174 23420
Image Super Resolution (Q) 45714 17898
Face Detection (HP) 74776 40535
Pose Estimation (Q) 196137 83624
Text Classification (SP) 5163 2724
Machine Translation (HP) 8677 4481
Object Detection (SP) 19602 10304
Depth Estimation (Q) 74879 30418
Style Transfer (SP) 411302 180089
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon RX 9070 XT and GeForce RTX 3070

General

Vendor Amd Nvidia
Build Discrete Discrete
Released January 7, 2025 October 22, 2020
Launch price (MSRP) $599 $499
Case Desktop Desktop
Purpose Gaming Gaming
Segment High-end Mid-range
Architecture RDNA 4.0 Ampere
GPU Codename Navi 48 GA104
Rival Equivalent - GeForce RTX 5070 Ti - Radeon RX 7800 XT
Successor - - GeForce RTX 5070
Recommended CPU - Intel Core Ultra 5 245K or above - Intel Core i7 12700K or above
Desktop GPU rating (12th and 44th place)

Graphics Processing Unit

Base Clock 1660 MHz 1500 MHz
Boost Clock 2970 MHz 1725 MHz
Shading Units 4096 5888
Texture Mapping Units (TMUs) 256 184
Render Output Units (ROPs) 128 96
Compute Units (Pipelines) 64 46
Tensor Cores 128 184
Ray-tracing Cores 64 46
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 8MB shared 4MB shared
Instructions Per Cycle 4 IPC 2 IPC

Raw Performance

Pixel Fill Rate 380 GPixel/s 166 GPixel/s
Texture Fill Rate 760 GTexel/s 317 GTexel/s
FLOPS (FP32)
RX 9070 XT +140%
48.7 TFLOPS
20.3 TFLOPS
Differences in GPUs' instructions per clock make TFLOPS values not directly comparable.

Physical

Interface PCIe 5.0 x16 PCIe 4.0 x16
TGP 304 W 220 W
Manufacturing TSMC Samsung
Fabrication Process 4 nm 8 nm
Die Size 357 mm² 392 mm²
Transistor Count 53.9 billion 17 billion
Transistor Density 150.98 MTr/mm² 43.37 MTr/mm²

Memory

Memory Type GDDR6 GDDR6
Memory Size 16 GB 8 GB
Memory Clock 2518 MHz 1750 MHz
Effective Memory Speed 20100 Mbps 14000 Mbps
Bus 256-bit 256-bit
ECC No No
Memory Bandwidth
RX 9070 XT +44%
644.6 GB/s
448 GB/s

API

DirectX 12.2 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
OpenCL 2.2 3.0
CUDA No 8.6
Ray Tracing Yes Yes
DLSS No DLSS 2
DisplayPort 2.1a 1.4a

Cast your vote

Choose between two graphics cards
45 (97.8%)
1 (2.2%)
Total votes: 46

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of DeviceFacts community!