GeForce 9800 GTX vs Radeon R7 384 Cores Kaveri

If you are going to buy a new graphics card and are choosing between GeForce 9800 GTX and Radeon R7 384 Cores Kaveri, there are a couple of things to consider. Cards with more VRAM in general perform better and allow you to play on higher graphics settings. Size also makes a difference. A model with a large heatsink can occupy up to three expansion slots on a motherboard. Be sure you have enough room in your PC case. When comparing GPUs with different architectures, more processing cores and even higher TFLOPS will not always translate to better performance. To help you decide which GPU you need, we have measured frame rates in a number of popular games. For more on how the GeForce 9800 GTX stacks up against Radeon R7 384 Cores Kaveri, check out specs charts below.
GeForce 9800 GTX
Radeon R7 384 Cores Kaveri

Main Specs

  GeForce 9800 GTX Radeon R7 384 Cores Kaveri
Power consumption (TDP) 140 Watt
Interface PCIe 2.0 x16
Supplementary power connectors 2x 6-pin
Memory type GDDR3
Maximum RAM amount 512 MB
Display Connectors 2x DVI, 1x S-Video
 
  • Both cards are used in Desktops.
  • GeForce 9800 GTX is build with Tesla architecture, and Radeon R7 384 Cores Kaveri - with GCN.
  • Core clock speed of GeForce 9800 GTX is 968 MHz higher, than Radeon R7 384 Cores Kaveri.
  • GeForce 9800 GTX is manufactured by 65 nm process technology, and Radeon R7 384 Cores Kaveri - by 28 nm process technology.

Game benchmarks

high / 1080p 0−1 7−8
ultra / 1080p 4−5
QHD / 1440p 0−1 0−1
low / 720p 1−2 18−20
medium / 1080p 0−1 9−10
The average gaming FPS of Radeon R7 384 Cores Kaveri in Assassin's Creed Odyssey is 1800% more, than GeForce 9800 GTX.

Full Specs

  GeForce 9800 GTX Radeon R7 384 Cores Kaveri
Architecture Tesla GCN
Code name G92 Kaveri Spectre
Type Desktop Desktop
Release date 28 March 2008 14 January 2014
Pipelines 128 384
Core clock speed 1688 MHz 720 MHz
Transistor count 754 million
Manufacturing process technology 65 nm 28 nm
Texture fill rate 43.2 billion/sec
Floating-point performance 432.1 gflops
Length 10.5" (26.7 cm)
Memory bus width 256 Bit
Memory clock speed 1100 MHz
Memory bandwidth 70.4 GB/s
Shared memory +
DirectX 11.1 (10_0) DirectX 12 (FL 12_0), Shader 5.2
Shader Model 4.0
OpenGL 2.1
OpenCL 1.1
Vulkan N/A
CUDA +
CUDA cores 128
Bus support PCI-E 2.0
Height 4.376" (11.1 cm)
SLI options +
Multi monitor support +
HDMI Via Adapter
Maximum VGA resolution 2048x1536
Audio input for HDMI S/PDIF