GeForce RTX 3080 vs GeForce RTX 5090

[ VERDICT ] Winner: GeForce RTX 5090 (96/100)

GeForce RTX 5090 leads overall with a score of 96/100 compared to GeForce RTX 3080 (53/100), offering superior measured performance and technical specifications.

GeForce RTX 3080
GeForce

GeForce RTX 3080

53/100
View Full Specs →
[ WINNER ]
GeForce RTX 5090
GeForce

GeForce RTX 5090

96/100
View Full Specs →

Benchmark Performance Comparison

Normalized Lab Scores
Benchmark measurements and scores across compared devices
Benchmark GeForce RTX 3080 GeForce RTX 5090
Efficiency 35.0 Poor 48.0 Poor WINNER
Gaming 54.0 Below Average 100.0 Excellent WINNER

Detailed Technical Specifications

3D Mark

3D Mark specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Fire Strike 42472 87569
Night Raid 133004 206648
Port Royal 11597 38202
Solar Bay 85898 236689
Time Spy 17664 46873
Wild Life Extreme 37900 108751

API

API specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
CUDA 8.6 12.0
DLSS DLSS 2 DLSS 4
DirectX 12 12.2
DisplayPort 1.4a 2.1b
OpenCL 3.0 3.0
OpenGL 4.6 4.6
Ray Tracing Yes Yes
Vulkan 1.3 1.4

Games

Games specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
1080p High 167 299
1080p Ultra 141 254
1440p Ultra 108 207
4K Ultra 64 125
CoD: Modern Warfare III 15214511073 334322260184
Counter-Strike 2 27420614982 36326520299
Cyberpunk 2077 1351177936 26123316077
Far Cry 6 14513811472 237202190121
Forza Horizon 5 17011410480 336247233187
Ghost of Tsushima 109897444 221185175113
Hogwarts Legacy 119987843 24919916697
Margin of Error Low Low
Shadow of the Tomb Raider 21019515182 329302238128
The Witcher 3 18916511663 364327237123

GeekBench 6 ML

GeekBench 6 ML specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Backend DirectML DirectML
Depth Estimation (Q) 36822 85572
Face Detection (HP) 46956 114685
Framework ONNX ONNX
Image Classification (SP) 9439 18948
Image Segmentation (HP) 25471 55109
Image Super Resolution (Q) 19892 58478
Machine Translation (HP) 4828 8184
Object Detection (SP) 12153 27802
Pose Estimation (Q) 104704 344729
Style Transfer (SP) 246005 687080
Text Classification (SP) 2712 4464

GeekBench 6 OpenCL

GeekBench 6 OpenCL specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
API OpenCL OpenCL
Background Blur 217.3 img/sec 333 img/sec
Edge Detection 11 Gpixels/sec 33.7 Gpixels/sec
Face Detection 141.9 img/sec 298.5 img/sec
Feature Matching 1.29 Gpixels/sec 2.53 Gpixels/sec
Gaussian Blur 8.43 Gpixels/sec 34.5 Gpixels/sec
Horizon Detection 8.19 Gpixels/sec 21.7 Gpixels/sec
Particle Physics 22538.5 FPS 59146.9 FPS
Stereo Matching 780.7 Gpixels/sec 2850 Gpixels/sec

General

General specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
AMD Equivalent -Radeon RX 6800 XT —
Architecture Ampere Blackwell 2.0
Build Discrete Discrete
Case Desktop Desktop
GPU Codename GA102 GB202-300
Launch price (MSRP) $699 $1999
Purpose Gaming Gaming
Recommended CPU -Intel Core i7 12700Kor above -Intel Core Ultra 9 285Kor above
Released September 1, 2020 January 7, 2025
Segment High-end High-end
Successor -GeForce RTX 5080 —
Vendor Nvidia Nvidia

Graphics Processing Unit

Graphics Processing Unit specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Base Clock 1440 MHz 2017 MHz
Boost Clock 1710 MHz 2407 MHz
Compute Units (Pipelines) 68 170
Instructions Per Cycle 2 IPC 2 IPC
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 5MB shared 96MB shared
Ray-tracing Cores 68 170
Render Output Units (ROPs) 96 176
Shading Units 8704 21760
Tensor Cores 272 680
Texture Mapping Units (TMUs) 272 680

Memory

Memory specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Bus 320-bit 512-bit
ECC No No
Effective Memory Speed 19000 Mbps 28000 Mbps
Memory Clock 1188 MHz 1750 MHz
Memory Size 10 GB 32 GB
Memory Type GDDR6X GDDR7

Passmark Graphics

Passmark Graphics specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
DirectX 11 207 FPS 341 FPS
DirectX 12 99 FPS 179 FPS
G2D Mark 1062 1410
GPU Compute 14058 Ops/s 24360 Ops/s

Physical

Physical specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Die Size 628 mm² 750 mm²
Fabrication Process 8 nm 4 nm
Interface PCIe 4.0 x16 PCIe 5.0 x16
Manufacturing Samsung TSMC
TGP 320 W 575 W
Transistor Count 28 billion 92.2 billion
Transistor Density 44.59 MTr/mm² 122.93 MTr/mm²

Raw Performance

Raw Performance specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Pixel Fill Rate 164 GPixel/s 424 GPixel/s
Texture Fill Rate 465 GTexel/s 1637 GTexel/s

Recent User Tests

Recent User Tests specifications comparison
Specification GeForce RTX 3080 GeForce RTX 5090
Date Benchmark —
📘 2026-08-06(Henry) Cinebench 2024 —

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 →