NVIDIA GeForce RTX 3090 vs NVIDIA GeForce GTX 680

Compare NVIDIA GeForce RTX 3090 24 GB vs NVIDIA GeForce GTX 680 4 GB, specs and GPU benchmark score. Which is the better graphics card for the money?

Benchmark Score
Other Benchmarks
Specifications
Comments (0)
Popular Comparisons

GPU Comparison

Quickly search and compare graphics cards

NVIDIA GeForce GTX 680

Price

The cheapest price from our partner retailers

$ 1549.99

$ 519.99

$ 1030.00 significantly less expensive

Benchmark Score

Overall Score

General gaming and workstation score

13991 points

1009% significantly better overall score

1261 points

Flux Core frame rate

Volumetric ray casting test, a computationally expensive method of rendering high-quality scenes

333 FPS

304 FPS significantly higher Flux Core frame rate

28 FPS

Electron frame rate

Randomly generated noise sphere test

169 FPS

151 FPS significantly higher Electron frame rate

17 FPS

City frame rate

Procedurally generated city scene with voxel rendering

241 FPS

221 FPS significantly higher City frame rate

19 FPS

Clouds frame rate

Real-time noise calculation and ray marching test

134 FPS

120 FPS significantly higher Clouds frame rate

14 FPS

Free GPU Benchmark

Want to compare your graphics card against the GeForce RTX 3090 and the GeForce GTX 680? Download our free and quick PC Performance Test.

Download GPU Benchmark

Other Benchmarks

3DMark Graphics score

High-end graphics benchmark

19931 points

877% significantly higher 3DMark Graphics score

2038 points

Blender score

Cycles Render (Samples per minute)

5820.93 points

2896% significantly higher Blender score

194.26 points

Geekbench 5 (CUDA) score

CUDA compute benchmark

238123 points

1647% significantly higher Geekbench 5 (CUDA) score

13627 points

Geekbench 5 (OpenCL) score

OpenCL compute benchmark

204921 points

1151% significantly higher Geekbench 5 (OpenCL) score

16368 points

Geekbench 5 (Vulkan) score

Vulkan compute benchmark

138859 points

749% significantly higher Geekbench 5 (Vulkan) score

16340 points

Geekbench 6 (OpenCL) score

OpenCL compute benchmark

194465 points

956% significantly higher Geekbench 6 (OpenCL) score

18409 points

Geekbench 6 (Vulkan) score

Vulkan compute benchmark

179816 points

897% significantly higher Geekbench 6 (Vulkan) score

18023 points

Specifications

Core Clock Speed

Nominal chip frequency

1400 MHz

39% slightly higher core clock speed

1006 MHz

Boost Clock Speed

Higher turbo frequency when power conditions are met

1695 MHz

60% significantly higher boost clock speed

1058 MHz

Memory

Onboard memory size for textures and vertices

24 GiB

499% significantly more memory

4 GiB

Memory Bus Width

Number of parallel lines to the memory chips

384 Bit

49% significantly larger memory bus width

256 Bit

Memory Bandwidth

Data transfer speed between GPU core and memory

936.2 GB/s

386% significantly higher memory bandwidth

192.3 GB/s

TDP

Thermal Design Power: Measure of heat generated by the GPU

350 W

195 W

79% significantly lower TDP

Pixel Rate

Number of pixels that can be rendered per second

189.8 Gigapixels/s

460% significantly higher pixel rate

33.86 Gigapixels/s

Texture Rate

Number of textured pixels that can be rendered per second

556 Gigatexels/s

310% significantly higher texture rate

135.4 Gigatexels/s

Floating Point Performance

Raw number of floating point operations per second

35.58 TFLOPS

994% significantly better floating point performance

3.25 TFLOPS

Shading Units

Number of processors dedicated to shader processing

10496

583% significantly more shading units

1536

Texture Mapping Units

Number of processors dedicated to applying textures

328

156% significantly more texture mapping units

128

Render Output Processors

Number of processors dedicated to final pixel rendering

112

250% significantly more render output processors

Other details

Rank

Ranking in the hardwareDB database

25th of 586

246th of 586

Release date

The official date of release of this chip

2020 September

2012 March

Memory Type

The type of memory used by this chip

GDDR6X

GDDR5

DirectX Support

Maximum version of DirectX supported

12.0

11.0

OpenGL Support

Maximum version of OpenGL supported

4.6

4.5

GeForce RTX 3090 vs GeForce GTX 680 specs and performance

For gaming, the GeForce RTX 3090 graphics card is better than the GeForce GTX 680 in our tests.

The GeForce RTX 3090 has a slightly higher core clock speed. The core clock speed (or base speed) is the frequency at which the GPU core runs. This metric makes sense when comparing GPUs of a similar architecture or generation. In addition, the GeForce RTX 3090 also has a significantly higher boost clock speed: the maximum frequency the chip can reach if power delivery and thermals allow.

Furthermore, the spec sheet for both these GPUs show that the GeForce RTX 3090 has significantly more memory with 24 GiB of memory compared to 4 GiB. Memory size doesn't directly affect performance, but too little memory will certainly degrade gaming performance.

In addition, the GeForce GTX 680 has a significantly lower TDP at 195 W when compared to the GeForce RTX 3090 at 350 W. TDP (Thermal Design Power) measures total heat output from the chip.

In terms of raw gaming performance in our GPU benchmark, the GeForce RTX 3090 is better than the GeForce GTX 680.