NVIDIA GeForce GTX 660 vs NVIDIA GeForce 9800 GT

Comparative analysis of NVIDIA GeForce GTX 660 and NVIDIA GeForce 9800 GT videocards for all known characteristics in the following categories: Essentials, Technical info, Video outputs and ports, Compatibility, dimensions and requirements, API support, Memory, Technologies. Benchmark videocards performance analysis: PassMark - G3D Mark, PassMark - G2D Mark, Geekbench - OpenCL, CompuBench 1.5 Desktop - Face Detection (mPixels/s), CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s), CompuBench 1.5 Desktop - T-Rex (Frames/s), CompuBench 1.5 Desktop - Video Composition (Frames/s), CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s), GFXBench 4.0 - Car Chase Offscreen (Frames), GFXBench 4.0 - Manhattan (Frames), GFXBench 4.0 - T-Rex (Frames), GFXBench 4.0 - Car Chase Offscreen (Fps), GFXBench 4.0 - Manhattan (Fps), GFXBench 4.0 - T-Rex (Fps), 3DMark Fire Strike - Graphics Score.

NVIDIA GeForce GTX 660

NVIDIA GeForce 9800 GT

Differences

Reasons to consider the NVIDIA GeForce GTX 660

Videocard is newer: launch date 4 year(s) 1 month(s) later
2.3x more texture fill rate: 78.4 billion / sec vs 33.6 billion / sec
8.6x more pipelines: 960 vs 112
5.9x better floating-point performance: 1,981 gflops vs 336.0 gflops
A newer manufacturing process allows for a more powerful, yet cooler running videocard: 28 nm vs 65 nm
4x more maximum memory size: 2 GB vs 512 MB
8.8x better performance in PassMark - G3D Mark: 4017 vs 454
8.7x better performance in PassMark - G2D Mark: 487 vs 56
Around 30% better performance in GFXBench 4.0 - Manhattan (Frames): 3690 vs 2845
Around 2% better performance in GFXBench 4.0 - T-Rex (Frames): 3365 vs 3304
Around 30% better performance in GFXBench 4.0 - Manhattan (Fps): 3690 vs 2845
Around 2% better performance in GFXBench 4.0 - T-Rex (Fps): 3365 vs 3304

Specifications (specs)
Launch date	6 September 2012 vs 21 July 2008
Texture fill rate	78.4 billion / sec vs 33.6 billion / sec
Pipelines	960 vs 112
Floating-point performance	1,981 gflops vs 336.0 gflops
Manufacturing process technology	28 nm vs 65 nm
Maximum memory size	2 GB vs 512 MB
Benchmarks
PassMark - G3D Mark	4017 vs 454
PassMark - G2D Mark	487 vs 56
GFXBench 4.0 - Manhattan (Frames)	3690 vs 2845
GFXBench 4.0 - T-Rex (Frames)	3365 vs 3304
GFXBench 4.0 - Manhattan (Fps)	3690 vs 2845
GFXBench 4.0 - T-Rex (Fps)	3365 vs 3304

Reasons to consider the NVIDIA GeForce 9800 GT

Around 53% higher core clock speed: 1500 MHz vs 980 MHz
Around 33% lower typical power consumption: 105 Watt vs 140 Watt
150x more memory clock speed: 900 MHz vs 6.0 GB/s

Core clock speed	1500 MHz vs 980 MHz
Thermal Design Power (TDP)	105 Watt vs 140 Watt
Memory clock speed	900 MHz vs 6.0 GB/s

Compare benchmarks

GPU 1: NVIDIA GeForce GTX 660
GPU 2: NVIDIA GeForce 9800 GT

PassMark - G3D Mark

GPU 1

GPU 2

4017

454

PassMark - G2D Mark

GPU 1

GPU 2

487

GFXBench 4.0 - Manhattan (Frames)

GPU 1

GPU 2

3690

2845

GFXBench 4.0 - T-Rex (Frames)

GPU 1

GPU 2

3365

3304

GFXBench 4.0 - Manhattan (Fps)

GPU 1

GPU 2

3690

2845

GFXBench 4.0 - T-Rex (Fps)

GPU 1

GPU 2

3365

3304

Name	NVIDIA GeForce GTX 660	NVIDIA GeForce 9800 GT
PassMark - G3D Mark	4017	454
PassMark - G2D Mark	487	56
Geekbench - OpenCL	11364
CompuBench 1.5 Desktop - Face Detection (mPixels/s)	30.505
CompuBench 1.5 Desktop - Ocean Surface Simulation (Frames/s)	705.293
CompuBench 1.5 Desktop - T-Rex (Frames/s)	3.085
CompuBench 1.5 Desktop - Video Composition (Frames/s)	35.416
CompuBench 1.5 Desktop - Bitcoin Mining (mHash/s)	62.69
GFXBench 4.0 - Car Chase Offscreen (Frames)	3581
GFXBench 4.0 - Manhattan (Frames)	3690	2845
GFXBench 4.0 - T-Rex (Frames)	3365	3304
GFXBench 4.0 - Car Chase Offscreen (Fps)	3581
GFXBench 4.0 - Manhattan (Fps)	3690	2845
GFXBench 4.0 - T-Rex (Fps)	3365	3304
3DMark Fire Strike - Graphics Score	1307

Compare specifications (specs)

	NVIDIA GeForce GTX 660	NVIDIA GeForce 9800 GT
Essentials
Architecture	Kepler	Tesla
Code name	GK106	G92
Launch date	6 September 2012	21 July 2008
Launch price (MSRP)	$229	$160
Place in performance rating	740	1063
Price now	$349.99	$103.99
Type	Desktop	Desktop
Value for money (0-100)	14.35	8.86
Technical info
Boost clock speed	1033 MHz
Core clock speed	980 MHz	1500 MHz
CUDA cores	960	112
Floating-point performance	1,981 gflops	336.0 gflops
Manufacturing process technology	28 nm	65 nm
Pipelines	960	112
Texture fill rate	78.4 billion / sec	33.6 billion / sec
Thermal Design Power (TDP)	140 Watt	105 Watt
Transistor count	2,540 million	754 million
Maximum GPU temperature		105 °C
Video outputs and ports
Audio input for HDMI	Internal	S / PDIF
Display Connectors	One Dual Link DVI-I, One Dual Link DVI-D, One HDMI..., 2x DVI, 1x HDMI, 1x DisplayPort	2x DVI, 1x S-Video, HDTVDual Link DVI
G-SYNC support
HDCP
HDMI
Maximum VGA resolution	2048x1536	2048x1536
Multi monitor support
Compatibility, dimensions and requirements
Bus support	PCI Express 3.0
Height	4.376" (11.1 cm)
Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length	9.5" (24.1 cm)	9" (22.9 cm)
Supplementary power connectors	One 6-pin	2x 6-pin
SLI options		2-way
API support
DirectX	12.0 (11_0)	10.0
OpenGL	4.3	2.1
Memory
Maximum RAM amount	2 GB	512 MB
Memory bandwidth	144.2 GB / s	57.6 GB / s
Memory bus width	192-bit GDDR5	256 Bit
Memory clock speed	6.0 GB/s	900 MHz
Memory type	GDDR5	GDDR3
Technologies
3D Blu-Ray
3D Gaming
3D Vision
Adaptive VSync
CUDA
FXAA
GPU Boost
SLI
TXAA