Radeon Pro Vega 20 vs GeForce 9800M GS
Aggregate performance score
We've compared GeForce 9800M GS with Radeon Pro Vega 20, including specs and performance data.
Pro Vega 20 outperforms 9800M GS by a whopping 809% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 1006 | 399 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 1.65 | 8.97 |
| Architecture | Tesla (2006−2010) | GCN 5.0 (2017−2020) |
| GPU code name | G94 | Vega 12 |
| Market segment | Laptop | Mobile workstation |
| Release date | 1 November 2008 (16 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 | 64 | 1280 |
| Core clock speed | 530 MHz | 815 MHz |
| Boost clock speed | no data | 1283 MHz |
| Number of transistors | 505 million | no data |
| Manufacturing process technology | 65 nm | 14 nm |
| Power consumption (TDP) | 60 Watt | 100 Watt |
| Texture fill rate | 16.96 | 102.6 |
| Floating-point processing power | 0.1696 TFLOPS | 3.284 TFLOPS |
| Gigaflops | 254 | no data |
| ROPs | 16 | 32 |
| TMUs | 32 | 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 |
| Bus support | PCI-E 2.0 | no data |
| Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Supplementary power connectors | None | 1x 6-pin + 1x 8-pin |
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 | GDDR3 | HBM2 |
| Maximum RAM amount | 512 MB | 4 GB |
| Memory bus width | 256 Bit | 1024 Bit |
| Memory clock speed | 800 MHz | 740 MHz |
| Memory bandwidth | 51.2 GB/s | 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 outputs | No outputs |
| Multi monitor support | + | no data |
| Maximum VGA resolution | 2048x1536 | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| Power management | 8.0 | no data |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.1 (10_0) | 12 (12_1) |
| Shader Model | 4.0 | 6.3 |
| OpenGL | 2.1 | 4.6 |
| OpenCL | 1.1 | 2.0 |
| Vulkan | N/A | 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.
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.
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 | 6−7
−917%
| 61
+917%
|
| 4K | 4−5
−925%
| 41
+925%
|
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 4−5
−675%
|
30−35
+675%
|
| Cyberpunk 2077 | 3−4
−733%
|
24−27
+733%
|
Full HD
Medium Preset
| Atomic Heart | 4−5
−675%
|
30−35
+675%
|
| Battlefield 5 | 2−3
−3600%
|
74
+3600%
|
| Cyberpunk 2077 | 3−4
−733%
|
24−27
+733%
|
| Fortnite | 4−5
−1675%
|
70−75
+1675%
|
| Forza Horizon 4 | 7−8
−643%
|
50−55
+643%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 9−10
−389%
|
40−45
+389%
|
| Valorant | 30−35
−215%
|
100−110
+215%
|
Full HD
High Preset
| Atomic Heart | 4−5
−675%
|
30−35
+675%
|
| Battlefield 5 | 2−3
−3050%
|
63
+3050%
|
| Counter-Strike: Global Offensive | 30−33
−480%
|
170−180
+480%
|
| Cyberpunk 2077 | 3−4
−733%
|
24−27
+733%
|
| Dota 2 | 16−18
−400%
|
85
+400%
|
| Fortnite | 4−5
−1675%
|
70−75
+1675%
|
| Forza Horizon 4 | 7−8
−643%
|
50−55
+643%
|
| Grand Theft Auto V | 1−2
−4600%
|
45−50
+4600%
|
| Metro Exodus | 2−3
−1150%
|
24−27
+1150%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 9−10
−389%
|
40−45
+389%
|
| The Witcher 3: Wild Hunt | 6−7
−733%
|
50
+733%
|
| Valorant | 30−35
−215%
|
100−110
+215%
|
Full HD
Ultra Preset
| Battlefield 5 | 2−3
−2900%
|
60
+2900%
|
| Cyberpunk 2077 | 3−4
−733%
|
24−27
+733%
|
| Dota 2 | 16−18
−359%
|
78
+359%
|
| Forza Horizon 4 | 7−8
−643%
|
50−55
+643%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 9−10
−389%
|
40−45
+389%
|
| The Witcher 3: Wild Hunt | 6−7
−417%
|
31
+417%
|
| Valorant | 30−35
−215%
|
100−110
+215%
|
Full HD
Epic Preset
| Fortnite | 4−5
−1675%
|
70−75
+1675%
|
1440p
High Preset
| Counter-Strike 2 | 0−1 | 21−24 |
| Counter-Strike: Global Offensive | 8−9
−1050%
|
90−95
+1050%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−646%
|
95−100
+646%
|
| Valorant | 6−7
−2083%
|
130−140
+2083%
|
1440p
Ultra Preset
| Cyberpunk 2077 | 1−2
−1000%
|
10−12
+1000%
|
| Far Cry 5 | 1−2
−2600%
|
27−30
+2600%
|
| Forza Horizon 4 | 3−4
−900%
|
30−33
+900%
|
| The Witcher 3: Wild Hunt | 2−3
−850%
|
18−20
+850%
|
1440p
Epic Preset
| Fortnite | 2−3
−1250%
|
27−30
+1250%
|
4K
High Preset
| Atomic Heart | 1−2
−900%
|
10−11
+900%
|
| Grand Theft Auto V | 14−16
−60%
|
24−27
+60%
|
| Valorant | 7−8
−843%
|
65−70
+843%
|
4K
Ultra Preset
| Cyberpunk 2077 | 0−1 | 4−5 |
| Dota 2 | 1−2
−4000%
|
41
+4000%
|
| Far Cry 5 | 2−3
−550%
|
12−14
+550%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 2−3
−500%
|
12−14
+500%
|
4K
Epic Preset
| Fortnite | 2−3
−500%
|
12−14
+500%
|
Full HD
Low Preset
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
Full HD
Medium Preset
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
| Far Cry 5 | 40
+0%
|
40
+0%
|
| Forza Horizon 5 | 35−40
+0%
|
35−40
+0%
|
Full HD
High Preset
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
| Far Cry 5 | 37
+0%
|
37
+0%
|
| Forza Horizon 5 | 35−40
+0%
|
35−40
+0%
|
Full HD
Ultra Preset
| Far Cry 5 | 37
+0%
|
37
+0%
|
1440p
High Preset
| Grand Theft Auto V | 18−20
+0%
|
18−20
+0%
|
| Metro Exodus | 14−16
+0%
|
14−16
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 30−35
+0%
|
30−35
+0%
|
4K
High Preset
| Counter-Strike 2 | 7−8
+0%
|
7−8
+0%
|
| Metro Exodus | 8−9
+0%
|
8−9
+0%
|
| The Witcher 3: Wild Hunt | 16−18
+0%
|
16−18
+0%
|
4K
Ultra Preset
| Battlefield 5 | 16−18
+0%
|
16−18
+0%
|
| Counter-Strike 2 | 7−8
+0%
|
7−8
+0%
|
| Forza Horizon 4 | 21−24
+0%
|
21−24
+0%
|
This is how 9800M GS and Pro Vega 20 compete in popular games:
- Pro Vega 20 is 917% faster in 1080p
- Pro Vega 20 is 925% faster in 4K
Here's the range of performance differences observed across popular games:
- in Grand Theft Auto V, with 1080p resolution and the High Preset, the Pro Vega 20 is 4600% faster.
All in all, in popular games:
- Pro Vega 20 is ahead in 44 tests (72%)
- there's a draw in 17 tests (28%)
Pros & cons summary
| Performance score | 1.24 | 11.27 |
| Recency | 1 November 2008 | 14 November 2018 |
| Maximum RAM amount | 512 MB | 4 GB |
| Chip lithography | 65 nm | 14 nm |
| Power consumption (TDP) | 60 Watt | 100 Watt |
9800M GS has 66.7% lower power consumption.
Pro Vega 20, on the other hand, has a 808.9% higher aggregate performance score, an age advantage of 10 years, a 700% higher maximum VRAM amount, and a 364.3% more advanced lithography process.
The Radeon Pro Vega 20 is our recommended choice as it beats the GeForce 9800M GS in performance tests.
Be aware that GeForce 9800M GS is a notebook graphics card while Radeon Pro Vega 20 is a mobile workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
