Nvidia GeForce RTX 5070 Ti vs Nvidia GeForce RTX 3080 Ti

Compared 2 processors: Nvidia GeForce RTX 5070 Ti, vs Nvidia GeForce RTX 3080 Ti. Below are specs, tests, pros and cons for each device

Review

Key Specs Nvidia GeForce RTX 5070 Ti and Nvidia GeForce RTX 3080 Ti
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
223
170
153
119
186
129
117
86
The Witcher 3
235
215
152
83
202
173
123
67
Counter-Strike 2
302
224
170
85
272
215
154
85
Far Cry 6
179
161
143
89
152
144
126
77
Hogwarts Legacy
157
130
107
60
132
106
85
47
COD Modern Warfare 3
219
207
163
111
166
158
123
80
Ghost of Tsushima
144
123
110
66
116
99
81
51
Cyberpunk 2077
192
176
117
57
146
130
89
42
Shadow of the Tomb Raider
280
268
198
107
236
220
169
92
Avg FPS
1080p High215179
1080p Ultra186153
1440p Ultra146119
4K Ultra8670
DeviationLowLow

Benchmarks

CPU performance comparison across tasks
3DMark
Steel Nomad Lite Score
Nvidia GeForce RTX 5070 Ti
29778
Nvidia GeForce RTX 3080 Ti
21408
Time Spy2768519630
Solar Bay13326396489
Port Royal1932113261
Fire Strike6655047892
Night Raid187880143788
GeekBench v6
GB6 Compute Score
Nvidia GeForce RTX 5070 Ti
240508
Nvidia GeForce RTX 3080 Ti
196756
Background Blur297.9 frames/s239.8 frames/s
Face Detection218.6 frames/s156.8 frames/s
Horizon Detection10.1 Gpix/sec10.8 Gpix/sec
Edge Detection13.9 Gpix/sec14.8 Gpix/sec
Gaussian Blur14.8 Gpix/sec11.9 Gpix/sec
Feature Matching2.03 Gpix/sec1.53 Gpix/sec
Stereo Matching1290 Gpix/sec889.6 Gpix/sec
Particle Physics35438.3 fps26054.6 fps
APIOpenCLOpenCL
PassMark
PassMark Graphics
Nvidia GeForce RTX 5070 Ti
32819
Nvidia GeForce RTX 3080 Ti
26944
G2D Mark13351088
DirectX 11300 fps223 fps
DirectX 12127 fps111 fps
GPU Compute20169 Ops/s15428 Ops/s
GFXBench 5
Aztec Ruins (High 4K)
Nvidia GeForce RTX 5070 Ti
296.6 fps
Nvidia GeForce RTX 3080 Ti
227.3 fps
Aztec Ruins (Normal)1021.4 fps1039 fps
Car Chase973.1 fps860.8 fps
Manhattan 3.1.1 (1440p)885.2 fps743.2 fps
T-Rex3379.4 fps3834.2 fps
ALU 2n/a6702 fps
Driver Overhead 2n/a296.1 fps
APIOpenGLOpenGL
OSWindowsWindows
Tessellationn/a6622.8
Geekbench 6 ML
GB6 ML Single Precision
Nvidia GeForce RTX 5070 Ti
36504
Nvidia GeForce RTX 3080 Ti
n/a
GB6 ML Half Precision
Nvidia GeForce RTX 5070 Ti
64459
Nvidia GeForce RTX 3080 Ti
n/a
GB6 ML Quantized
Nvidia GeForce RTX 5070 Ti
27312
Nvidia GeForce RTX 3080 Ti
n/a
Image Classification (SP)14913n/a
Image Segmentation (HP)45199n/a
Horizon Detection39360n/a
Face Detection (HP)84188n/a
Pose Estimation (Q)161400n/a
Text Classification (SP)4010n/a
Machine Translation (HP)7973n/a
Object Detection (SP)18934n/a
Depth Estimation (Q)67761n/a
Style Transfer (SP)335879n/a
FrameworkONNXn/a
BackendDirectMLn/a

Blender

Real-world 3D modeling test
Blender GPU
Nvidia GeForce RTX 5070 Ti
7461.05
Nvidia GeForce RTX 3080 Ti
n/a

Tech Specs

Specs & test comparison

General Info

Manufacturer Nvidia Nvidia
Build Discrete Discrete
Announced January, 7, 2025 January, 3, 2021
Form Factor PC use PC use
Use case Gaming Gaming
Segment Mid-range High-end
Architecture Blackwell 2.0 Ampere
Codename GB203-200 GA102
Price n/a 1199

GPU

GPU Frequency 2295 MHz 1365 MHz
Boost GPU Frequency 2452 MHz 1665 MHz
Shader Units 8960 10240
TMUs 280 320
ROPs 96 112
Execution Units 70 80
Ray Tracing Cores 70 80
Tensor Cores 280 320
L1 cache 128 KB/core 128 KB/core
L2 cache 48000 KB/core 6000 KB/core
Instructions per Clock 2 IPC 2 IPC

Performance

Pixel Fill Rate 235 Gpix/sec 186 Gpix/sec
Texture Fill Rate 687 GTex/s 533 GTex/s
FLOPS 43.9 TFLOPS 34.1 TFLOPS

Process

Interface PCIe 5.0 x16 PCIe 4.0 x16
TGP 300 W 350 W
Process TSMC Samsung
Process tech. 4 nm 8 nm
Transistor Size 378 mm² 628 mm²
Transistor count 45.6 billion 28 billion
Transistor density 120.63 MTr/mm² 44.59 MTr/mm²

Memory

Interface GDDR7 GDDR6X
Memory Frequency 1750 MHz 1188 MHz
Bus 256 bit 384 bit
ECC support No No
Effective Memory Speed 28000 MB/s 19000 MB/s
Memory Size 16 GB 12 GB
Max Throughput
Nvidia GeForce RTX 5070 Ti
896 GB/s
Nvidia GeForce RTX 3080 Ti
912 GB/s

API

DirectX 12.2 12
Vulkan 1.4 1.3
OpenGL 4.6 4.6
CUDA 12.0 8.6
DisplayPort 2.1b 1.4a
Ray Tracing Yes Yes
DLSS DLSS 4 DLSS 2

Results

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

Survey

Which GPU would you pick?
7 (50%)
7 (50%)
Total Votes: 14

User comments

Share your opinion or ask questions below