Nvidia GeForce RTX 5080 vs Nvidia GeForce RTX 4070 SUPER

Compared 2 processors: Nvidia GeForce RTX 5080, vs Nvidia GeForce RTX 4070 SUPER. Below are specs, tests, pros and cons for each device

Review

Key Specs Nvidia GeForce RTX 5080 and Nvidia GeForce RTX 4070 SUPER
Games
Performance in DirectX, OpenCL, Vulkan
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

Games

FPS Table
Game title
1080p (High)
1080p (Ultra)
1440p (Ultra)
4K (Ultra)
Forza Horizon 5
257
182
175
135
184
128
116
89
The Witcher 3
270
243
168
91
204
175
127
68
Counter-Strike 2
317
236
175
87
283
214
156
83
Far Cry 6
194
173
160
97
157
142
127
76
Hogwarts Legacy
181
154
122
69
132
110
87
48
COD Modern Warfare 3
247
234
192
136
171
165
128
83
Ghost of Tsushima
165
141
129
80
118
99
85
50
Cyberpunk 2077
213
189
135
62
154
136
92
40
Shadow of the Tomb Raider
302
273
213
114
242
224
176
93
Avg FPS
1080p High238183
1080p Ultra203155
1440p Ultra163122
4K Ultra9770
DeviationLowLow

Benchmarks

CPU performance comparison across tasks
3DMark
Steel Nomad Lite Score
Nvidia GeForce RTX 5080
36014
Nvidia GeForce RTX 4070 SUPER
21558
Time Spy3305720901
Solar Bay15490897900
Port Royal2316313112
Fire Strike7499450143
Night Raid200409164308
GeekBench v6
GB6 Compute Score
Nvidia GeForce RTX 5080
297747
Nvidia GeForce RTX 4070 SUPER
206598
Background Blur319.6 frames/s359.5 frames/s
Face Detection225 frames/s210 frames/s
Horizon Detection13.6 Gpix/sec7.61 Gpix/sec
Edge Detection19.5 Gpix/sec10.4 Gpix/sec
Gaussian Blur20.4 Gpix/sec11.3 Gpix/sec
Feature Matching2.33 Gpix/sec1.97 Gpix/sec
Stereo Matching1750 Gpix/sec969.3 Gpix/sec
Particle Physics43676.6 fps29061.4 fps
APIOpenCLOpenCL
PassMark
PassMark Graphics
Nvidia GeForce RTX 5080
35999
Nvidia GeForce RTX 4070 SUPER
29967
G2D Mark13961178
DirectX 11322 fps274 fps
DirectX 12148 fps108 fps
GPU Compute21623 Ops/s17275 Ops/s
GFXBench 5
Aztec Ruins (High 4K)
Nvidia GeForce RTX 5080
410.9 fps
Nvidia GeForce RTX 4070 SUPER
219.6 fps
Aztec Ruins (Normal)1955.9 fps1132.4 fps
Car Chasen/a981.8 fps
Manhattan 3.1.1 (1440p)n/a840.6 fps
T-Rexn/a4325.3 fps
ALU 2n/a6890.2 fps
Driver Overhead 2n/a290.1 fps
APIVulkanOpenGL
OSWindowsWindows
Tessellationn/a7090.8
Geekbench 6 ML
GB6 ML Single Precision
Nvidia GeForce RTX 5080
38994
Nvidia GeForce RTX 4070 SUPER
n/a
GB6 ML Half Precision
Nvidia GeForce RTX 5080
66609
Nvidia GeForce RTX 4070 SUPER
n/a
GB6 ML Quantized
Nvidia GeForce RTX 5080
29206
Nvidia GeForce RTX 4070 SUPER
n/a
Image Classification (SP)15441n/a
Image Segmentation (HP)47173n/a
Horizon Detection43223n/a
Face Detection (HP)92863n/a
Pose Estimation (Q)202202n/a
Text Classification (SP)3701n/a
Machine Translation (HP)7905n/a
Object Detection (SP)20955n/a
Depth Estimation (Q)69068n/a
Style Transfer (SP)349205n/a
FrameworkONNXn/a
BackendDirectMLn/a

Blender

Real-world 3D modeling test
Blender GPU
Nvidia GeForce RTX 5080
9041.36
Nvidia GeForce RTX 4070 SUPER
n/a

Tech Specs

Specs & test comparison

General Info

Manufacturer Nvidia Nvidia
Build Discrete Discrete
Announced January, 7, 2025 January, 17, 2024
Form Factor PC use PC use
Use case Gaming Gaming
Segment High-end Mid-range
Architecture Blackwell 2.0 Ada Lovelace
Codename GB203-400 AD104
Price n/a 599

GPU

GPU Frequency 2295 MHz 1980 MHz
Boost GPU Frequency 2617 MHz 2475 MHz
Shader Units 10752 7168
TMUs 336 224
ROPs 112 80
Execution Units 84 56
Ray Tracing Cores 84 56
Tensor Cores 336 224
L1 cache 128 KB/core 128 KB/core
L2 cache 64 KB/core 48000 KB/core
Instructions per Clock 2 IPC 2 IPC

Performance

Pixel Fill Rate 293 Gpix/sec 198 Gpix/sec
Texture Fill Rate 879 GTex/s 554 GTex/s
FLOPS 56.3 TFLOPS 35.5 TFLOPS

Process

Interface PCIe 5.0 x16 PCIe 4.0 x16
TGP 360 W 220 W
Process TSMC TSMC
Process tech. 4 nm 5 nm
Transistor Size 378 mm² 294 mm²
Transistor count 45.6 billion 35 billion
Transistor density 120.63 MTr/mm² 119.05 MTr/mm²

Memory

Interface GDDR7 GDDR6X
Memory Frequency 1875 MHz 1313 MHz
Bus 256 bit 192 bit
ECC support No No
Effective Memory Speed 30000 MB/s 21000 MB/s
Memory Size 16 GB 12 GB
Max Throughput
Nvidia GeForce RTX 5080
960 GB/s
Nvidia GeForce RTX 4070 SUPER
504.2 GB/s

API

DirectX 12.2 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
CUDA 12.0 8.9
DisplayPort 2.1b 1.4a
Ray Tracing Yes Yes
DLSS DLSS 4 DLSS 3

Results

After analyzing the data, we consider Nvidia GeForce RTX 5080 the clear winner in this comparison.

Survey

Which GPU would you pick?
1 (100%)
0 (0%)
Total Votes: 1

User comments

Share your opinion or ask questions below