Radeon RX Vega 64 vs GeForce GTX 1070 SLI
Aggregate performance score
We've compared GeForce GTX 1070 SLI and Radeon RX Vega 64, covering specs and all relevant benchmarks.
GTX 1070 SLI outperforms RX Vega 64 by a minimal 3% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 123 | 130 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 21.39 |
| Power efficiency | 8.74 | 8.64 |
| Architecture | Pascal (2016−2021) | GCN 5.0 (2017−2020) |
| GPU code name | Pascal GP104 SLI | Vega 10 |
| Market segment | Desktop | Desktop |
| Release date | 16 August 2016 (8 years ago) | 7 August 2017 (7 years ago) |
| Launch price (MSRP) | no data | $499 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
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 | 3840 | 4096 |
| Core clock speed | 1506 MHz | 1247 MHz |
| Boost clock speed | 1683 MHz | 1546 MHz |
| Number of transistors | 14400 Million | 12,500 million |
| Manufacturing process technology | 16 nm | 14 nm |
| Power consumption (TDP) | 300 Watt | 295 Watt |
| Texture fill rate | no data | 395.8 |
| Floating-point processing power | no data | 12.66 TFLOPS |
| ROPs | no data | 64 |
| TMUs | no data | 256 |
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).
| Interface | no data | PCIe 3.0 x16 |
| Length | no data | 279 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 2x 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 | 2x 8 GB | 8 GB |
| Memory bus width | 256 Bit | 2048 Bit |
| Memory clock speed | 8000 MHz | 945 MHz |
| Memory bandwidth | no data | 483.8 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 | 1x HDMI, 3x DisplayPort |
| HDMI | - | + |
| G-SYNC support | + | - |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| VR Ready | + | no data |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12_1 | 12 (12_1) |
| Shader Model | no data | 6.4 |
| OpenGL | no data | 4.6 |
| OpenCL | no data | 2.0 |
| Vulkan | + | 1.1.125 |
| 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 Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
3DMark Cloud Gate GPU
Cloud Gate is an outdated DirectX 11 feature level 10 benchmark that was used for home PCs and basic notebooks. It displays a few scenes of some weird space teleportation device launching spaceships into unknown, using fixed resolution of 1280x720. Just like Ice Storm benchmark, it has been discontinued in January 2020 and replaced by 3DMark Night Raid.
3DMark Ice Storm GPU
Ice Storm Graphics is an obsolete benchmark, part of 3DMark suite. Ice Storm was used to measure entry level laptops and Windows-based tablets performance. It utilizes DirectX 11 feature level 9 to display a battle between two space fleets near a frozen planet in 1280x720 resolution. Discontinued in January 2020, it is now superseded by 3DMark Night Raid.
SPECviewperf 12 - Showcase
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 | 118
+0%
| 118
+0%
|
| 1440p | 80−85
+0%
| 80
+0%
|
| 4K | 60
+15.4%
| 52
−15.4%
|
Cost per frame, $
| 1080p | no data | 4.23 |
| 1440p | no data | 6.24 |
| 4K | no data | 9.60 |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 75−80
+3.9%
|
75−80
−3.9%
|
| Cyberpunk 2077 | 80−85
+2.5%
|
75−80
−2.5%
|
Full HD
Medium Preset
| Battlefield 5 | 100−110
+25.6%
|
82
−25.6%
|
| Counter-Strike 2 | 75−80
+3.9%
|
75−80
−3.9%
|
| Cyberpunk 2077 | 80−85
+138%
|
34
−138%
|
| Forza Horizon 4 | 180−190
−9.8%
|
202
+9.8%
|
| Forza Horizon 5 | 95−100
+3.2%
|
95−100
−3.2%
|
| Metro Exodus | 90−95
−14.1%
|
105
+14.1%
|
| Red Dead Redemption 2 | 75−80
−54.7%
|
116
+54.7%
|
| Valorant | 150−160
−19.7%
|
182
+19.7%
|
Full HD
High Preset
| Battlefield 5 | 100−110
−68.9%
|
174
+68.9%
|
| Counter-Strike 2 | 75−80
+3.9%
|
75−80
−3.9%
|
| Cyberpunk 2077 | 80−85
+200%
|
27
−200%
|
| Dota 2 | 58
+16%
|
50
−16%
|
| Far Cry 5 | 95−100
+54.8%
|
62
−54.8%
|
| Fortnite | 160−170
+36.6%
|
123
−36.6%
|
| Forza Horizon 4 | 180−190
+12.2%
|
164
−12.2%
|
| Forza Horizon 5 | 95−100
+3.2%
|
95−100
−3.2%
|
| Grand Theft Auto V | 87
−34.5%
|
110−120
+34.5%
|
| Metro Exodus | 90−95
+16.5%
|
79
−16.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 190−200
+1%
|
190−200
−1%
|
| Red Dead Redemption 2 | 75−80
+31.6%
|
57
−31.6%
|
| The Witcher 3: Wild Hunt | 130−140
+3.1%
|
130−140
−3.1%
|
| Valorant | 150−160
+65.2%
|
92
−65.2%
|
| World of Tanks | 270−280
+0%
|
270−280
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 100−110
+43.1%
|
72
−43.1%
|
| Counter-Strike 2 | 75−80
+3.9%
|
75−80
−3.9%
|
| Cyberpunk 2077 | 80−85
+238%
|
24
−238%
|
| Dota 2 | 120−130
−15%
|
138
+15%
|
| Far Cry 5 | 95−100
+1.1%
|
95−100
−1.1%
|
| Forza Horizon 4 | 180−190
+28.7%
|
143
−28.7%
|
| Forza Horizon 5 | 95−100
+3.2%
|
95−100
−3.2%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 190−200
+1%
|
190−200
−1%
|
| Valorant | 150−160
+8.6%
|
140
−8.6%
|
1440p
High Preset
| Counter-Strike 2 | 30−35
+3.3%
|
30−33
−3.3%
|
| Dota 2 | 70−75
+2.9%
|
65−70
−2.9%
|
| Grand Theft Auto V | 70−75
+2.9%
|
65−70
−2.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Red Dead Redemption 2 | 35−40
+2.7%
|
37
−2.7%
|
| World of Tanks | 240−250
+2.5%
|
230−240
−2.5%
|
1440p
Ultra Preset
| Battlefield 5 | 70−75
+1.4%
|
70−75
−1.4%
|
| Cyberpunk 2077 | 35−40
+153%
|
15
−153%
|
| Far Cry 5 | 120−130
+3.4%
|
110−120
−3.4%
|
| Forza Horizon 4 | 100−110
+9%
|
100
−9%
|
| Forza Horizon 5 | 60−65
+3.3%
|
60−65
−3.3%
|
| Metro Exodus | 80−85
+5.1%
|
79
−5.1%
|
| The Witcher 3: Wild Hunt | 65−70
+3.2%
|
60−65
−3.2%
|
| Valorant | 110−120
+24.2%
|
95
−24.2%
|
4K
High Preset
| Counter-Strike 2 | 24−27
+4.3%
|
21−24
−4.3%
|
| Dota 2 | 81
+14.1%
|
70−75
−14.1%
|
| Grand Theft Auto V | 81
+14.1%
|
70−75
−14.1%
|
| Metro Exodus | 30−35
−43.8%
|
46
+43.8%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 120−130
+3.4%
|
110−120
−3.4%
|
| Red Dead Redemption 2 | 24−27
+4.2%
|
24
−4.2%
|
| The Witcher 3: Wild Hunt | 81
+14.1%
|
70−75
−14.1%
|
4K
Ultra Preset
| Battlefield 5 | 40−45
−6.8%
|
47
+6.8%
|
| Counter-Strike 2 | 24−27
+4.3%
|
21−24
−4.3%
|
| Cyberpunk 2077 | 16−18
+129%
|
7
−129%
|
| Dota 2 | 70−75
−29.7%
|
96
+29.7%
|
| Far Cry 5 | 55−60
+3.7%
|
50−55
−3.7%
|
| Fortnite | 41
−22%
|
50
+22%
|
| Forza Horizon 4 | 60−65
+6.8%
|
59
−6.8%
|
| Forza Horizon 5 | 35−40
+2.9%
|
30−35
−2.9%
|
| Valorant | 60−65
+26.5%
|
49
−26.5%
|
1440p
Ultra Preset
| Counter-Strike 2 | 30−33
+0%
|
30−33
+0%
|
This is how GTX 1070 SLI and RX Vega 64 compete in popular games:
- A tie in 1080p
- A tie in 1440p
- GTX 1070 SLI is 15% faster in 4K
Here's the range of performance differences observed across popular games:
- in Cyberpunk 2077, with 1080p resolution and the Ultra Preset, the GTX 1070 SLI is 238% faster.
- in Battlefield 5, with 1080p resolution and the High Preset, the RX Vega 64 is 69% faster.
All in all, in popular games:
- GTX 1070 SLI is ahead in 50 tests (78%)
- RX Vega 64 is ahead in 11 tests (17%)
- there's a draw in 3 tests (5%)
Pros & cons summary
| Performance score | 36.64 | 35.62 |
| Recency | 16 August 2016 | 7 August 2017 |
| Chip lithography | 16 nm | 14 nm |
| Power consumption (TDP) | 300 Watt | 295 Watt |
GTX 1070 SLI has a 2.9% higher aggregate performance score.
RX Vega 64, on the other hand, has an age advantage of 11 months, a 14.3% more advanced lithography process, and 1.7% lower power consumption.
Given the minimal performance differences, no clear winner can be declared between GeForce GTX 1070 SLI and Radeon RX Vega 64.
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.
