Home GPU comparison Nvidia GeForce RTX 5070 and AMD Radeon RX 6900 XT - Which is better?

Nvidia GeForce RTX 5070 vs AMD Radeon RX 6900 XT

61 out 100
Nvidia GeForce RTX 5070
VS
54 out 100
AMD Radeon RX 6900 XT
Nvidia GeForce RTX 5070
AMD Radeon RX 6900 XT

Compared 2 processors: Nvidia GeForce RTX 5070, vs AMD Radeon RX 6900 XT. Below are specs, tests, pros and cons for each device

  1. Differences
  2. Review
  3. General
  4. Benchmarks
  5. Processor
  6. Memory
  7. Comments (0)

Review

Key Specs Nvidia GeForce RTX 5070 and AMD Radeon RX 6900 XT
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
NanoReview Score
Overall score by NanoReview

Tests & specs

Specs & test comparison
Processors:
GeForce RTX 5070
vs
Radeon RX 6900 XT

Games

FPS Table
Game title
1080p (High)
1080p (Ultra)
1440p (Ultra)
4K (Ultra)
Forza Horizon 5
192
140
127
98
213
142
118
87
The Witcher 3
212
180
134
70
208
183
139
72
Counter-Strike 2
284
215
157
82
302
208
149
81
Far Cry 6
161
148
127
82
172
148
133
83
Hogwarts Legacy
137
115
92
50
130
105
83
46
COD Modern Warfare 3
181
172
133
88
183
177
130
84
Ghost of Tsushima
123
107
88
56
131
111
91
55
Cyberpunk 2077
161
141
99
44
148
129
87
42
Shadow of the Tomb Raider
250
241
181
101
225
205
156
82
Avg FPS
1080p High189190
1080p Ultra162156
1440p Ultra126121
4K Ultra7570
DeviationLowLow

Benchmarks

CPU performance comparison across tasks
3DMark
Steel Nomad Lite Score
Nvidia GeForce RTX 5070
22974
AMD Radeon RX 6900 XT
20263
Time Spy2261320781
Solar Bay10376886741
Port Royal1431210519
Fire Strike5779357323
Night Raid172986159759
Sources: 3DMark [Nvidia GeForce RTX 5070], [AMD Radeon RX 6900 XT]
GeekBench v6
GB6 Compute Score
Nvidia GeForce RTX 5070
190967
AMD Radeon RX 6900 XT
124121
Background Blur254.4 frames/s231.6 frames/s
Face Detection180.6 frames/s152.5 frames/s
Horizon Detection7.91 Gpix/sec4.26 Gpix/sec
Edge Detection10.2 Gpix/sec5.75 Gpix/sec
Gaussian Blur10.7 Gpix/sec5.87 Gpix/sec
Feature Matching1.84 Gpix/sec1.12 Gpix/sec
Stereo Matching975.7 Gpix/sec618.7 Gpix/sec
Particle Physics27816.5 fps17973.9 fps
APIOpenCLOpenCL
Sources: GeekBench v6 [Nvidia GeForce RTX 5070], [AMD Radeon RX 6900 XT]
PassMark
PassMark Graphics
Nvidia GeForce RTX 5070
29057
AMD Radeon RX 6900 XT
26727
G2D Mark12971051
DirectX 11277 fps278 fps
DirectX 12108 fps113 fps
GPU Compute15779 Ops/s14962 Ops/s
Sources: PassMark [Nvidia GeForce RTX 5070], [AMD Radeon RX 6900 XT]
GFXBench 5
Aztec Ruins (High 4K)
Nvidia GeForce RTX 5070
n/a
AMD Radeon RX 6900 XT
305.2 fps
Aztec Ruins (Normal)n/a1379.6 fps
Car Chasen/a1317.5 fps
Manhattan 3.1.1 (1440p)n/a1205.3 fps
T-Rexn/a4360 fps
ALU 2n/a6645 fps
Driver Overhead 2n/a325.2 fps
APIn/aOpenGL
OSn/aWindows
Tessellationn/a3954.8
Sources: GFXBench 5 [AMD Radeon RX 6900 XT]
Geekbench 6 ML
GB6 ML Single Precision
Nvidia GeForce RTX 5070
30221
AMD Radeon RX 6900 XT
n/a
GB6 ML Half Precision
Nvidia GeForce RTX 5070
53037
AMD Radeon RX 6900 XT
n/a
GB6 ML Quantized
Nvidia GeForce RTX 5070
23474
AMD Radeon RX 6900 XT
n/a
Image Classification (SP)12270n/a
Image Segmentation (HP)30237n/a
Horizon Detection35585n/a
Face Detection (HP)62662n/a
Pose Estimation (Q)145190n/a
Text Classification (SP)4198n/a
Machine Translation (HP)6233n/a
Object Detection (SP)16709n/a
Depth Estimation (Q)58300n/a
Style Transfer (SP)246598n/a
FrameworkONNXn/a
BackendDirectMLn/a
Sources: GeekBench v6 [Nvidia GeForce RTX 5070]

Blender

Real-world 3D modeling test
Blender GPU
Nvidia GeForce RTX 5070
6148.6
AMD Radeon RX 6900 XT
n/a

Tech Specs

Specs & test comparison

General Info

Manufacturer Nvidia AMD
Build Discrete Discrete
Announced January, 7, 2025 December, 8, 2020
Form Factor PC use PC use
Use case Gaming Gaming
Segment Mid-range High-end
Architecture Blackwell 2.0 RDNA 2.0
Codename GB205-300 Navi 21
Price n/a 999

GPU

GPU Frequency 2325 MHz 1825 MHz
Boost GPU Frequency 2512 MHz 2250 MHz
Shader Units 6144 5120
TMUs 192 320
ROPs 80 128
Execution Units 48 n/a
Ray Tracing Cores 48 80
Tensor Cores 192 n/a
L1 cache 128 KB/core 128 KB/core
L2 cache 48000 KB/core 4000 KB/core
Instructions per Clock 2 IPC 2 IPC

Performance

Pixel Fill Rate 201 Gpix/sec 288 Gpix/sec
Texture Fill Rate 482 GTex/s 720 GTex/s
FLOPS 30.9 TFLOPS 23 TFLOPS

Process

Interface PCIe 5.0 x16 PCIe 4.0 x16
TGP 250 W 300 W
Process TSMC TSMC
Process tech. 4 nm 7 nm
Transistor Size 263 mm² 520 mm²
Transistor count 31.1 billion 26 billion
Transistor density 118.25 MTr/mm² 50 MTr/mm²

Memory

Interface GDDR7 GDDR6
Memory Frequency 1750 MHz 2000 MHz
Bus 192 bit 256 bit
ECC support No No
Effective Memory Speed 28000 MB/s 16000 MB/s
Memory Size 12 GB 16 GB
Max Throughput
Nvidia GeForce RTX 5070
672 GB/s
AMD Radeon RX 6900 XT
512 GB/s

API

DirectX 12.2 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
CUDA 12.0 n/a
DisplayPort 2.1b 1.4a
Ray Tracing Yes Yes
DLSS DLSS 4 No

Results

No clear favorite identified yet; updates may follow as new data arrives.

Survey

Which GPU would you pick?
3 (50%)
3 (50%)
Total Votes: 6

User comments

Share your opinion or ask questions below