Radeon Pro Vega 20 vs GeForce GTX 670MX SLI
Aggregate performance score
We've compared GeForce GTX 670MX SLI with Radeon Pro Vega 20, including specs and performance data.
Pro Vega 20 outperforms GTX 670MX SLI by a substantial 31% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 458 | 392 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 4.56 | 8.99 |
| Architecture | Kepler (2012−2018) | GCN 5.0 (2017−2020) |
| GPU code name | N13E-GR | Vega 12 |
| Market segment | Laptop | Mobile workstation |
| Release date | 1 October 2012 (12 years ago) | 14 November 2018 (6 years ago) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 1920 | 1280 |
| Core clock speed | 600 MHz | 815 MHz |
| Boost clock speed | no data | 1283 MHz |
| Number of transistors | 5080 Million | no data |
| Manufacturing process technology | 28 nm | 14 nm |
| Power consumption (TDP) | 150 Watt | 100 Watt |
| Texture fill rate | no data | 102.6 |
| Floating-point processing power | no data | 3.284 TFLOPS |
| ROPs | no data | 32 |
| TMUs | no data | 80 |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Laptop size | large | large |
| Interface | no data | PCIe 3.0 x16 |
| Supplementary power connectors | no data | 1x 6-pin + 1x 8-pin |
| SLI options | + | - |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR5 | HBM2 |
| Maximum RAM amount | no data | 4 GB |
| Memory bus width | 2x 192 Bit | 1024 Bit |
| Memory clock speed | 2800 MHz | 740 MHz |
| Memory bandwidth | no data | 189.4 GB/s |
| Shared memory | - | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | no data | No outputs |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| Optimus | + | - |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11 | 12 (12_1) |
| Shader Model | no data | 6.3 |
| OpenGL | no data | 4.6 |
| OpenCL | no data | 2.0 |
| Vulkan | - | 1.2.131 |
| CUDA | + | - |
Synthetic benchmark performance
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score. We are regularly improving our combining algorithms, but if you find some perceived inconsistencies, feel free to speak up in comments section, we usually fix problems quickly.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
3DMark Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 68
+4.6%
| 65
−4.6%
|
| 4K | 30−35
−36.7%
| 41
+36.7%
|
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 16−18
−29.4%
|
21−24
+29.4%
|
| Cyberpunk 2077 | 20−22
−30%
|
24−27
+30%
|
Full HD
Medium Preset
| Battlefield 5 | 30−35
−65.6%
|
53
+65.6%
|
| Counter-Strike 2 | 16−18
−29.4%
|
21−24
+29.4%
|
| Cyberpunk 2077 | 20−22
−30%
|
24−27
+30%
|
| Forza Horizon 4 | 40−45
−32.5%
|
50−55
+32.5%
|
| Forza Horizon 5 | 24−27
−36%
|
30−35
+36%
|
| Metro Exodus | 27−30
−33.3%
|
35−40
+33.3%
|
| Red Dead Redemption 2 | 24−27
−26.9%
|
30−35
+26.9%
|
| Valorant | 35−40
−36.8%
|
50−55
+36.8%
|
Full HD
High Preset
| Battlefield 5 | 30−35
−34.4%
|
40−45
+34.4%
|
| Counter-Strike 2 | 16−18
−29.4%
|
21−24
+29.4%
|
| Cyberpunk 2077 | 20−22
−30%
|
24−27
+30%
|
| Dota 2 | 35−40
+28.6%
|
28
−28.6%
|
| Far Cry 5 | 40−45
−22.5%
|
49
+22.5%
|
| Fortnite | 55−60
−27.6%
|
70−75
+27.6%
|
| Forza Horizon 4 | 40−45
−32.5%
|
50−55
+32.5%
|
| Forza Horizon 5 | 24−27
−36%
|
30−35
+36%
|
| Grand Theft Auto V | 35−40
−34.3%
|
45−50
+34.3%
|
| Metro Exodus | 27−30
−33.3%
|
35−40
+33.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 75−80
−104%
|
157
+104%
|
| Red Dead Redemption 2 | 24−27
−26.9%
|
30−35
+26.9%
|
| The Witcher 3: Wild Hunt | 30−33
−33.3%
|
40−45
+33.3%
|
| Valorant | 35−40
−36.8%
|
50−55
+36.8%
|
| World of Tanks | 168
−4.8%
|
170−180
+4.8%
|
Full HD
Ultra Preset
| Battlefield 5 | 30−35
−40.6%
|
45
+40.6%
|
| Counter-Strike 2 | 16−18
−29.4%
|
21−24
+29.4%
|
| Cyberpunk 2077 | 20−22
−30%
|
24−27
+30%
|
| Dota 2 | 35−40
−117%
|
78
+117%
|
| Far Cry 5 | 40−45
−22.5%
|
45−50
+22.5%
|
| Forza Horizon 4 | 40−45
−32.5%
|
50−55
+32.5%
|
| Forza Horizon 5 | 24−27
−36%
|
30−35
+36%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 75−80
−24.7%
|
95−100
+24.7%
|
| Valorant | 35−40
−36.8%
|
50−55
+36.8%
|
1440p
High Preset
| Dota 2 | 12−14
−38.5%
|
18−20
+38.5%
|
| Grand Theft Auto V | 12−14
−46.2%
|
18−20
+46.2%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 60−65
−58.7%
|
100−105
+58.7%
|
| Red Dead Redemption 2 | 8−9
−37.5%
|
10−12
+37.5%
|
| World of Tanks | 70−75
−29.6%
|
90−95
+29.6%
|
1440p
Ultra Preset
| Battlefield 5 | 18−20
−36.8%
|
24−27
+36.8%
|
| Cyberpunk 2077 | 8−9
−25%
|
10−11
+25%
|
| Far Cry 5 | 21−24
−36.4%
|
30−33
+36.4%
|
| Forza Horizon 4 | 21−24
−40.9%
|
30−35
+40.9%
|
| Forza Horizon 5 | 14−16
−33.3%
|
20−22
+33.3%
|
| Metro Exodus | 18−20
−47.4%
|
27−30
+47.4%
|
| The Witcher 3: Wild Hunt | 12−14
−30.8%
|
16−18
+30.8%
|
| Valorant | 24−27
−28%
|
30−35
+28%
|
4K
High Preset
| Counter-Strike 2 | 10−11
+0%
|
10−11
+0%
|
| Dota 2 | 20−22
−20%
|
24−27
+20%
|
| Grand Theft Auto V | 20−22
−15%
|
21−24
+15%
|
| Metro Exodus | 6−7
−50%
|
9−10
+50%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
−31%
|
35−40
+31%
|
| Red Dead Redemption 2 | 6−7
−33.3%
|
8−9
+33.3%
|
| The Witcher 3: Wild Hunt | 20−22
−15%
|
21−24
+15%
|
4K
Ultra Preset
| Battlefield 5 | 9−10
−33.3%
|
12−14
+33.3%
|
| Counter-Strike 2 | 10−11
+0%
|
10−11
+0%
|
| Cyberpunk 2077 | 3−4
−33.3%
|
4−5
+33.3%
|
| Dota 2 | 20−22
−105%
|
41
+105%
|
| Far Cry 5 | 12−14
−33.3%
|
16−18
+33.3%
|
| Fortnite | 10−11
−40%
|
14−16
+40%
|
| Forza Horizon 4 | 12−14
−38.5%
|
18−20
+38.5%
|
| Forza Horizon 5 | 7−8
−42.9%
|
10−11
+42.9%
|
| Valorant | 10−11
−40%
|
14−16
+40%
|
This is how GTX 670MX SLI and Pro Vega 20 compete in popular games:
- GTX 670MX SLI is 5% faster in 1080p
- Pro Vega 20 is 37% faster in 4K
Here's the range of performance differences observed across popular games:
- in Dota 2, with 1080p resolution and the High Preset, the GTX 670MX SLI is 29% faster.
- in Dota 2, with 1080p resolution and the Ultra Preset, the Pro Vega 20 is 117% faster.
All in all, in popular games:
- GTX 670MX SLI is ahead in 1 test (2%)
- Pro Vega 20 is ahead in 60 tests (95%)
- there's a draw in 2 tests (3%)
Pros & cons summary
| Performance score | 9.49 | 12.46 |
| Recency | 1 October 2012 | 14 November 2018 |
| Chip lithography | 28 nm | 14 nm |
| Power consumption (TDP) | 150 Watt | 100 Watt |
Pro Vega 20 has a 31.3% higher aggregate performance score, an age advantage of 6 years, a 100% more advanced lithography process, and 50% lower power consumption.
The Radeon Pro Vega 20 is our recommended choice as it beats the GeForce GTX 670MX SLI in performance tests.
Be aware that GeForce GTX 670MX SLI is a notebook graphics card while Radeon Pro Vega 20 is a mobile workstation one.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
