GeForce GTX 680 and Radeon HD 6870 - video card comparison
Passmark - benchmark score GeForce GTX 680 vs Radeon HD 6870
GeForce GTX 680
5721
Radeon HD 6870
2285
GeForce GTX 680
Radeon HD 6870
Architecture
Kepler (2012−2018)
Terascale 2 (2009−2015)
GPU code name
GK104
RV940 Barts
Market segment
Desktop
Desktop
Release date
March 2012
October 2010
Bus support
PCI Express 3.0
PCIe 2.0 x16
Interface
PCIe 3.0 x16
PCIe 2.0 x16
Supplementary power connectors
Two 6-pin
2x 6-pin
SLI options
+
-
Boost clock speed
1058 MHz
900 MHz
Core clock speed
1006 MHz
-
CUDA cores
1536
-
Floating-point performance
3,090.4 gflops
2,016.0 gflops
Manufacturing process technology
28 nm
40 nm
Number of transistors
3,540 million
1,700 million
Pipelines / CUDA cores
1536
1120
Power consumption (TDP)
195 Watt
151 Watt
Texture fill rate
128.8 billion/sec
50.40
Memory type
GDDR5
GDDR5
Maximum RAM amount
2048 MB
1 GB
Memory bus width
256-bit GDDR5
256 Bit
Memory clock speed
6000 MHz
1050 MHz
Memory bandwidth
192.2 GB/s
134.4 GB/s
Shared memory
-
-
Display Connectors
One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort
2x DVI, 1x HDMI, 2x mini-DisplayPort
Multi monitor support
4 displays
-
Eyefinity
-
1
HDMI
+
+
HDCP
+
-
Maximum VGA resolution
2048x1536
-
DisplayPort support
-
-
Audio input for HDMI
Internal
-
DirectX
12 (11_0)
DirectX® 11
CUDA
+
-
Mantle
-
-
OpenCL
1.2
1.2
OpenGL
4.2
4.4
Shader Model
5.1
5.0
Vulkan
1.1.126
-
AppAcceleration
-
-
CrossFire
-
1
Enduro
-
-
HD3D
-
-
PowerTune
-
-
TrueAudio
-
-
ZeroCore
-
-