GeForce RTX 4070 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 4070 (53/100), offering superior measured performance and technical specifications.

Benchmark Performance Comparison

Normalized Lab Scores
Benchmark measurements and scores across compared devices
Benchmark GeForce RTX 4070 GeForce RTX 5090
Efficiency 44.0 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 4070 GeForce RTX 5090
Fire Strike 44067 87569
Night Raid 153385 206648
Port Royal 11156 38202
Solar Bay 82861 236689
Time Spy 17799 46873
Wild Life Extreme 35472 108751

API

API specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
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 4070 GeForce RTX 5090
1080p High 167 299
1080p Ultra 139 254
1440p Ultra 106 207
4K Ultra 62 125
CoD: Modern Warfare III 14914510769 334322260184
Counter-Strike 2 27220514981 36326520299
Cyberpunk 2077 1291197537 26123316077
Far Cry 6 14913311568 237202190121
Forza Horizon 5 17211510279 336247233187
Ghost of Tsushima 106887243 221185175113
Hogwarts Legacy 117977739 24919916697
Margin of Error Low Low
Shadow of the Tomb Raider 21119014580 329302238128
The Witcher 3 19415911461 364327237123

GeekBench 6 ML

GeekBench 6 ML specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Backend DirectML DirectML
Depth Estimation (Q) 50548 85572
Face Detection (HP) 51337 114685
Framework ONNX ONNX
Image Classification (SP) 10246 18948
Image Segmentation (HP) 26153 55109
Image Super Resolution (Q) 32054 58478
Machine Translation (HP) 5484 8184
Object Detection (SP) 13134 27802
Pose Estimation (Q) 124617 344729
Style Transfer (SP) 263477 687080
Text Classification (SP) 3703 4464

GeekBench 6 OpenCL

GeekBench 6 OpenCL specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
API OpenCL OpenCL
Background Blur 233 img/sec 333 img/sec
Edge Detection 9.19 Gpixels/sec 33.7 Gpixels/sec
Face Detection 141.7 img/sec 298.5 img/sec
Feature Matching 1.78 Gpixels/sec 2.53 Gpixels/sec
Gaussian Blur 9.2 Gpixels/sec 34.5 Gpixels/sec
Horizon Detection 6.62 Gpixels/sec 21.7 Gpixels/sec
Particle Physics 25043.9 FPS 59146.9 FPS
Stereo Matching 845.4 Gpixels/sec 2850 Gpixels/sec

General

General specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
AMD Equivalent -Radeon RX 7900 XT
Architecture Ada Lovelace Blackwell 2.0
Build Discrete Discrete
Case Desktop Desktop
GPU Codename AD104 GB202-300
Launch price (MSRP) $599 $1999
Purpose Gaming Gaming
Recommended CPU -Intel Core i7 14700Kor above -Intel Core Ultra 9 285Kor above
Released April 13, 2023 January 7, 2025
Segment Mid-range High-end
Successor -GeForce RTX 5070
Vendor Nvidia Nvidia

Graphics Processing Unit

Graphics Processing Unit specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Base Clock 1920 MHz 2017 MHz
Boost Clock 2475 MHz 2407 MHz
Compute Units (Pipelines) 46 170
Instructions Per Cycle 2 IPC 2 IPC
L1 Cache 128KB per cluster 128KB per cluster
L2 Cache 36MB shared 96MB shared
Ray-tracing Cores 46 170
Render Output Units (ROPs) 64 176
Shading Units 5888 21760
Tensor Cores 184 680
Texture Mapping Units (TMUs) 184 680

Memory

Memory specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Bus 192-bit 512-bit
ECC No No
Effective Memory Speed 21000 Mbps 28000 Mbps
Memory Clock 1313 MHz 1750 MHz
Memory Size 12 GB 32 GB
Memory Type GDDR6X GDDR7

Passmark Graphics

Passmark Graphics specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
DirectX 11 243 FPS 341 FPS
DirectX 12 103 FPS 179 FPS
G2D Mark 1165 1410
GPU Compute 14570 Ops/s 24360 Ops/s

Physical

Physical specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Die Size 294 mm² 750 mm²
Fabrication Process 5 nm 4 nm
Interface PCIe 4.0 x16 PCIe 5.0 x16
Manufacturing TSMC TSMC
TGP 200 W 575 W
Transistor Count 35 billion 92.2 billion
Transistor Density 119.05 MTr/mm² 122.93 MTr/mm²

Raw Performance

Raw Performance specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Pixel Fill Rate 158 GPixel/s 424 GPixel/s
Texture Fill Rate 455 GTexel/s 1637 GTexel/s

Recent User Tests

Recent User Tests specifications comparison
Specification GeForce RTX 4070 GeForce RTX 5090
Date Benchmark
📘 2025-12-14(kashitsu) 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 →