GeForce RTX 4090 vs GeForce RTX 5070

[ VERDICT ] Winner: GeForce RTX 4090 (89/100)

GeForce RTX 4090 leads overall with a score of 89/100 compared to GeForce RTX 5070 (61/100), offering superior measured performance and technical specifications.

Benchmark Performance Comparison

Normalized Lab Scores
Benchmark measurements and scores across compared devices
Benchmark GeForce RTX 4090 GeForce RTX 5070
Efficiency 43.0 Poor 48.0 Poor WINNER
Gaming 93.0 Excellent WINNER 64.0 Average

Detailed Technical Specifications

3D Mark

3D Mark specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Fire Strike 72432 58324
Night Raid 195813 172064
Port Royal 26127 14498
Solar Bay 187525 107004
Time Spy 36299 22708
Wild Life Extreme 85218 43879

API

API specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
CUDA 8.9 12.0
DLSS DLSS 3 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 4090 GeForce RTX 5070
1080p High 255 192
1080p Ultra 217 162
1440p Ultra 177 128
4K Ultra 106 74
CoD: Modern Warfare III 266263219151 17817113689
Counter-Strike 2 33923818890 29321016081
Cyberpunk 2077 22620814366 1641449943
Far Cry 6 203179170104 16414512882
Forza Horizon 5 275199193155 19714013097
Ghost of Tsushima 18815213791 1231078958
Hogwarts Legacy 20016313274 1401179251
Margin of Error Low Low
Shadow of the Tomb Raider 302284222118 25323818998
The Witcher 3 292268191101 21618313171

GeekBench 6 ML

GeekBench 6 ML specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Backend DirectML DirectML
Depth Estimation (Q) 75599 58300
Face Detection (HP) 78111 62662
Framework ONNX ONNX
Image Classification (SP) 15600 12270
Image Segmentation (HP) 36657 30237
Image Super Resolution (Q) 48114 35585
Machine Translation (HP) 6349 6233
Object Detection (SP) 21186 16709
Pose Estimation (Q) 289639 145190
Style Transfer (SP) 601428 246598
Text Classification (SP) 4074 4198

GeekBench 6 OpenCL

GeekBench 6 OpenCL specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
API OpenCL OpenCL
Background Blur 318.9 img/sec 254.4 img/sec
Edge Detection 21 Gpixels/sec 10.2 Gpixels/sec
Face Detection 222.8 img/sec 180.6 img/sec
Feature Matching 2.38 Gpixels/sec 1.84 Gpixels/sec
Gaussian Blur 23.9 Gpixels/sec 10.7 Gpixels/sec
Horizon Detection 14.2 Gpixels/sec 7.91 Gpixels/sec
Particle Physics 48090.4 FPS 27816.5 FPS
Stereo Matching 1950 Gpixels/sec 975.7 Gpixels/sec

General

General specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Architecture Ada Lovelace Blackwell 2.0
Build Discrete Discrete
Case Desktop Desktop
GPU Codename AD102 GB205-300
Launch price (MSRP) $1599 $549
Purpose Gaming Gaming
Recommended CPU -Intel Core i9 14900Kor above -Intel Core Ultra 5 245Kor above
Released September 20, 2022 January 7, 2025
Segment High-end Mid-range
Successor -GeForce RTX 5090
Vendor Nvidia Nvidia
AMD Equivalent -Radeon RX 9070

Graphics Processing Unit

Graphics Processing Unit specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Base Clock 2235 MHz 2160 MHz
Boost Clock 2520 MHz 2512 MHz
Compute Units (Pipelines) 128 48
Instructions Per Cycle 2 IPC 2 IPC
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 72MB shared 48MB shared
Ray-tracing Cores 128 48
Render Output Units (ROPs) 176 80
Shading Units 16384 6144
Tensor Cores 512 192
Texture Mapping Units (TMUs) 512 192

Memory

Memory specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Bus 384-bit 192-bit
ECC No No
Effective Memory Speed 21000 Mbps 28000 Mbps
Memory Clock 2625 MHz 1750 MHz
Memory Size 24 GB 12 GB
Memory Type GDDR6X GDDR7

Passmark Graphics

Passmark Graphics specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
DirectX 11 323 FPS 280 FPS
DirectX 12 151 FPS 106 FPS
G2D Mark 1303 1291
GPU Compute 26022 Ops/s 14310 Ops/s

Physical

Physical specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Die Size 609 mm² 263 mm²
Fabrication Process 5 nm 4 nm
Interface PCIe 4.0 x16 PCIe 5.0 x16
Manufacturing TSMC TSMC
TGP 450 W 250 W
Transistor Count 76.3 billion 31.1 billion
Transistor Density 125.29 MTr/mm² 118.25 MTr/mm²

Raw Performance

Raw Performance specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Pixel Fill Rate 444 GPixel/s 201 GPixel/s
Texture Fill Rate 1290 GTexel/s 482 GTexel/s

Recent User Tests

Recent User Tests specifications comparison
Specification GeForce RTX 4090 GeForce RTX 5070
Date Benchmark
📘 2026-04-03(afroman420IU) 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 →