Radeon Pro Vega II Duo vs GeForce RTX 3070
Aggregate performance score
We've compared GeForce RTX 3070 with Radeon Pro Vega II Duo, including specs and performance data.
RTX 3070 outperforms Pro Vega II Duo by an impressive 59% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 43 | 133 |
| Place by popularity | 37 | not in top-100 |
| Cost-effectiveness evaluation | 57.98 | 7.21 |
| Power efficiency | 18.17 | 5.29 |
| Architecture | Ampere (2020−2024) | GCN 5.1 (2018−2022) |
| GPU code name | GA104 | Vega 20 |
| Market segment | Desktop | Workstation |
| Release date | 1 September 2020 (4 years ago) | 3 June 2019 (5 years ago) |
| Launch price (MSRP) | $499 | $4,399 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
RTX 3070 has 704% better value for money than Pro Vega II Duo.
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 | 5888 | 4096 |
| Core clock speed | 1500 MHz | 1400 MHz |
| Boost clock speed | 1725 MHz | 1720 MHz |
| Number of transistors | 17,400 million | 13,230 million |
| Manufacturing process technology | 8 nm | 7 nm |
| Power consumption (TDP) | 220 Watt | 475 Watt |
| Texture fill rate | 317.4 | 440.3 |
| Floating-point processing power | 20.31 TFLOPS | 14.09 TFLOPS |
| ROPs | 96 | 64 |
| TMUs | 184 | 256 |
| Tensor Cores | 184 | no data |
| Ray Tracing Cores | 46 | no data |
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 | PCIe 4.0 x16 | Apple MPX |
| Length | 242 mm | no data |
| Width | 2-slot | Quad-slot |
| Supplementary power connectors | 1x 12-pin | None |
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 | GDDR6 | HBM2 |
| Maximum RAM amount | 8 GB | 32 GB |
| Memory bus width | 256 Bit | 4096 Bit |
| Memory clock speed | 1750 MHz | 1000 MHz |
| Memory bandwidth | 448.0 GB/s | 1.02 TB/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 | 1x HDMI, 3x DisplayPort | 1x HDMI 2.0b, 4x Thunderbolt |
| HDMI | + | + |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
| Shader Model | 6.5 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.1 |
| Vulkan | 1.2 | 1.3 |
| CUDA | 8.5 | - |
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.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
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 | 150
+66.7%
| 90−95
−66.7%
|
| 1440p | 98
+63.3%
| 60−65
−63.3%
|
| 4K | 64
+60%
| 40−45
−60%
|
Cost per frame, $
| 1080p | 3.33
+1369%
| 48.88
−1369%
|
| 1440p | 5.09
+1340%
| 73.32
−1340%
|
| 4K | 7.80
+1311%
| 109.98
−1311%
|
- RTX 3070 has 1369% lower cost per frame in 1080p
- RTX 3070 has 1340% lower cost per frame in 1440p
- RTX 3070 has 1311% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 149
+65.6%
|
90−95
−65.6%
|
| Cyberpunk 2077 | 147
+63.3%
|
90−95
−63.3%
|
Full HD
Medium Preset
| Battlefield 5 | 110−120
+67.1%
|
70−75
−67.1%
|
| Counter-Strike 2 | 135
+68.8%
|
80−85
−68.8%
|
| Cyberpunk 2077 | 124
+65.3%
|
75−80
−65.3%
|
| Forza Horizon 4 | 311
+63.7%
|
190−200
−63.7%
|
| Forza Horizon 5 | 139
+63.5%
|
85−90
−63.5%
|
| Metro Exodus | 124
+65.3%
|
75−80
−65.3%
|
| Red Dead Redemption 2 | 118
+68.6%
|
70−75
−68.6%
|
| Valorant | 246
+64%
|
150−160
−64%
|
Full HD
High Preset
| Battlefield 5 | 110−120
+67.1%
|
70−75
−67.1%
|
| Counter-Strike 2 | 117
+67.1%
|
70−75
−67.1%
|
| Cyberpunk 2077 | 109
+67.7%
|
65−70
−67.7%
|
| Dota 2 | 137
+61.2%
|
85−90
−61.2%
|
| Far Cry 5 | 91
+65.5%
|
55−60
−65.5%
|
| Fortnite | 220−230
+63.6%
|
140−150
−63.6%
|
| Forza Horizon 4 | 256
+60%
|
160−170
−60%
|
| Forza Horizon 5 | 144
+60%
|
90−95
−60%
|
| Grand Theft Auto V | 134
+67.5%
|
80−85
−67.5%
|
| Metro Exodus | 107
+64.6%
|
65−70
−64.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+65.4%
|
130−140
−65.4%
|
| Red Dead Redemption 2 | 98
+63.3%
|
60−65
−63.3%
|
| The Witcher 3: Wild Hunt | 170−180
+74%
|
100−105
−74%
|
| Valorant | 159
+67.4%
|
95−100
−67.4%
|
| World of Tanks | 270−280
+64.1%
|
170−180
−64.1%
|
Full HD
Ultra Preset
| Battlefield 5 | 110−120
+67.1%
|
70−75
−67.1%
|
| Counter-Strike 2 | 105
+61.5%
|
65−70
−61.5%
|
| Cyberpunk 2077 | 91
+65.5%
|
55−60
−65.5%
|
| Dota 2 | 125
+66.7%
|
75−80
−66.7%
|
| Far Cry 5 | 110−120
+67.1%
|
70−75
−67.1%
|
| Forza Horizon 4 | 223
+59.3%
|
140−150
−59.3%
|
| Forza Horizon 5 | 118
+68.6%
|
70−75
−68.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+65.4%
|
130−140
−65.4%
|
| Valorant | 237
+69.3%
|
140−150
−69.3%
|
1440p
High Preset
| Counter-Strike 2 | 30−35
+77.8%
|
18−20
−77.8%
|
| Dota 2 | 98
+63.3%
|
60−65
−63.3%
|
| Grand Theft Auto V | 95
+72.7%
|
55−60
−72.7%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+75%
|
100−105
−75%
|
| Red Dead Redemption 2 | 63
+80%
|
35−40
−80%
|
| World of Tanks | 350−400
+65.7%
|
230−240
−65.7%
|
1440p
Ultra Preset
| Battlefield 5 | 85−90
+74%
|
50−55
−74%
|
| Cyberpunk 2077 | 58
+65.7%
|
35−40
−65.7%
|
| Far Cry 5 | 160−170
+60%
|
100−105
−60%
|
| Forza Horizon 4 | 166
+66%
|
100−105
−66%
|
| Forza Horizon 5 | 98
+63.3%
|
60−65
−63.3%
|
| Metro Exodus | 101
+68.3%
|
60−65
−68.3%
|
| The Witcher 3: Wild Hunt | 110−120
+70%
|
70−75
−70%
|
| Valorant | 208
+60%
|
130−140
−60%
|
4K
High Preset
| Counter-Strike 2 | 30−35
+83.3%
|
18−20
−83.3%
|
| Dota 2 | 117
+67.1%
|
70−75
−67.1%
|
| Grand Theft Auto V | 115
+64.3%
|
70−75
−64.3%
|
| Metro Exodus | 49
+63.3%
|
30−33
−63.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 200−210
+71.7%
|
120−130
−71.7%
|
| Red Dead Redemption 2 | 43
+59.3%
|
27−30
−59.3%
|
| The Witcher 3: Wild Hunt | 117
+67.1%
|
70−75
−67.1%
|
4K
Ultra Preset
| Battlefield 5 | 70−75
+64.4%
|
45−50
−64.4%
|
| Counter-Strike 2 | 16
+60%
|
10−11
−60%
|
| Cyberpunk 2077 | 28
+75%
|
16−18
−75%
|
| Dota 2 | 125
+66.7%
|
75−80
−66.7%
|
| Far Cry 5 | 100−110
+61.5%
|
65−70
−61.5%
|
| Fortnite | 95−100
+60%
|
60−65
−60%
|
| Forza Horizon 4 | 98
+63.3%
|
60−65
−63.3%
|
| Forza Horizon 5 | 57
+62.9%
|
35−40
−62.9%
|
| Valorant | 116
+65.7%
|
70−75
−65.7%
|
This is how RTX 3070 and Pro Vega II Duo compete in popular games:
- RTX 3070 is 67% faster in 1080p
- RTX 3070 is 63% faster in 1440p
- RTX 3070 is 60% faster in 4K
Pros & cons summary
| Performance score | 55.85 | 35.08 |
| Recency | 1 September 2020 | 3 June 2019 |
| Maximum RAM amount | 8 GB | 32 GB |
| Chip lithography | 8 nm | 7 nm |
| Power consumption (TDP) | 220 Watt | 475 Watt |
RTX 3070 has a 59.2% higher aggregate performance score, an age advantage of 1 year, and 115.9% lower power consumption.
Pro Vega II Duo, on the other hand, has a 300% higher maximum VRAM amount, and a 14.3% more advanced lithography process.
The GeForce RTX 3070 is our recommended choice as it beats the Radeon Pro Vega II Duo in performance tests.
Be aware that GeForce RTX 3070 is a desktop card while Radeon Pro Vega II Duo is a 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.
