Radeon Pro W6800 vs GeForce 9800M GTX SLI
Aggregate performance score
We've compared GeForce 9800M GTX SLI with Radeon Pro W6800, including specs and performance data.
Pro W6800 outperforms 9800M SLI by a whopping 1585% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 831 | 77 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 10.66 |
| Power efficiency | 1.47 | 14.85 |
| Architecture | G9x (2007−2010) | RDNA 2.0 (2020−2025) |
| GPU code name | NB9E-GTX | Navi 21 |
| Market segment | Laptop | Workstation |
| Release date | 15 July 2008 (17 years ago) | 8 June 2021 (4 years ago) |
| Launch price (MSRP) | no data | $2,249 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 224 | 3840 |
| Core clock speed | 500 MHz | 2075 MHz |
| Boost clock speed | no data | 2320 MHz |
| Number of transistors | 3016 Million | 26,800 million |
| Manufacturing process technology | 65 nm | 7 nm |
| Power consumption (TDP) | 150 Watt | 250 Watt |
| Texture fill rate | no data | 556.8 |
| Floating-point processing power | no data | 17.82 TFLOPS |
| ROPs | no data | 96 |
| TMUs | no data | 240 |
| Ray Tracing Cores | no data | 60 |
| L0 Cache | no data | 960 KB |
| L1 Cache | no data | 768 KB |
| L2 Cache | no data | 4 MB |
| L3 Cache | no data | 128 MB |
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 | no data |
| Interface | no data | PCIe 4.0 x16 |
| Length | no data | 267 mm |
| Width | no data | 2-slot |
| 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 | GDDR3 | GDDR6 |
| Maximum RAM amount | 1 GB | 32 GB |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 800 MHz | 2000 MHz |
| Memory bandwidth | no data | 512.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | - | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | no data | 6x mini-DisplayPort |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 10 | 12 Ultimate (12_2) |
| Shader Model | no data | 6.5 |
| OpenGL | no data | 4.6 |
| OpenCL | no data | 2.1 |
| Vulkan | - | 1.2 |
| CUDA | + | - |
Synthetic benchmarks
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.
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 | 8−9
−1613%
| 137
+1613%
|
| 1440p | 6−7
−1833%
| 116
+1833%
|
| 4K | 4−5
−2000%
| 84
+2000%
|
Cost per frame, $
| 1080p | no data | 16.42 |
| 1440p | no data | 19.39 |
| 4K | no data | 26.77 |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 9−10
−2756%
|
250−260
+2756%
|
| Cyberpunk 2077 | 6−7
−1850%
|
110−120
+1850%
|
| Resident Evil 4 Remake | 3−4
−4533%
|
130−140
+4533%
|
Full HD
Medium
| Battlefield 5 | 10−11
−1400%
|
150−160
+1400%
|
| Counter-Strike 2 | 9−10
−2756%
|
250−260
+2756%
|
| Cyberpunk 2077 | 6−7
−1850%
|
110−120
+1850%
|
| Far Cry 5 | 8−9
−775%
|
70
+775%
|
| Fortnite | 14−16
−1300%
|
210−220
+1300%
|
| Forza Horizon 4 | 14−16
−1236%
|
180−190
+1236%
|
| Forza Horizon 5 | 7−8
−2057%
|
150−160
+2057%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1223%
|
170−180
+1223%
|
| Valorant | 45−50
−485%
|
260−270
+485%
|
Full HD
High
| Battlefield 5 | 10−11
−1400%
|
150−160
+1400%
|
| Counter-Strike 2 | 9−10
−2756%
|
250−260
+2756%
|
| Counter-Strike: Global Offensive | 55−60
−407%
|
270−280
+407%
|
| Cyberpunk 2077 | 6−7
−1850%
|
110−120
+1850%
|
| Dota 2 | 27−30
−254%
|
99
+254%
|
| Far Cry 5 | 8−9
−713%
|
65
+713%
|
| Fortnite | 14−16
−1300%
|
210−220
+1300%
|
| Forza Horizon 4 | 14−16
−1236%
|
180−190
+1236%
|
| Forza Horizon 5 | 7−8
−2057%
|
150−160
+2057%
|
| Grand Theft Auto V | 7−8
−1629%
|
121
+1629%
|
| Metro Exodus | 5−6
−3100%
|
160
+3100%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1223%
|
170−180
+1223%
|
| The Witcher 3: Wild Hunt | 10−11
−1890%
|
199
+1890%
|
| Valorant | 45−50
−485%
|
260−270
+485%
|
Full HD
Ultra
| Battlefield 5 | 10−11
−1400%
|
150−160
+1400%
|
| Cyberpunk 2077 | 6−7
−1850%
|
110−120
+1850%
|
| Dota 2 | 27−30
−207%
|
86
+207%
|
| Far Cry 5 | 8−9
−675%
|
62
+675%
|
| Forza Horizon 4 | 14−16
−1236%
|
180−190
+1236%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 12−14
−1223%
|
170−180
+1223%
|
| The Witcher 3: Wild Hunt | 10−11
−1470%
|
157
+1470%
|
| Valorant | 45−50
−485%
|
260−270
+485%
|
Full HD
Epic
| Fortnite | 14−16
−1300%
|
210−220
+1300%
|
1440p
High
| Counter-Strike 2 | 6−7
−2133%
|
130−140
+2133%
|
| Counter-Strike: Global Offensive | 21−24
−1562%
|
300−350
+1562%
|
| Metro Exodus | 1−2
−17000%
|
171
+17000%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
−573%
|
170−180
+573%
|
| Valorant | 27−30
−1019%
|
300−350
+1019%
|
1440p
Ultra
| Cyberpunk 2077 | 2−3
−3000%
|
60−65
+3000%
|
| Far Cry 5 | 5−6
−1180%
|
64
+1180%
|
| Forza Horizon 4 | 7−8
−2014%
|
140−150
+2014%
|
| The Witcher 3: Wild Hunt | 4−5
−2425%
|
100−110
+2425%
|
1440p
Epic
| Fortnite | 5−6
−2580%
|
130−140
+2580%
|
4K
High
| Grand Theft Auto V | 14−16
−733%
|
125
+733%
|
| Valorant | 14−16
−1957%
|
280−290
+1957%
|
4K
Ultra
| Cyberpunk 2077 | 0−1 | 27−30 |
| Dota 2 | 8−9
−1075%
|
94
+1075%
|
| Far Cry 5 | 1−2
−5900%
|
60
+5900%
|
| Forza Horizon 4 | 2−3
−5000%
|
100−110
+5000%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 3−4
−2500%
|
75−80
+2500%
|
4K
Epic
| Fortnite | 3−4
−2233%
|
70−75
+2233%
|
1440p
High
| Grand Theft Auto V | 88
+0%
|
88
+0%
|
1440p
Ultra
| Battlefield 5 | 120−130
+0%
|
120−130
+0%
|
4K
High
| Counter-Strike 2 | 60−65
+0%
|
60−65
+0%
|
| Metro Exodus | 55
+0%
|
55
+0%
|
| The Witcher 3: Wild Hunt | 99
+0%
|
99
+0%
|
4K
Ultra
| Battlefield 5 | 80−85
+0%
|
80−85
+0%
|
| Counter-Strike 2 | 60−65
+0%
|
60−65
+0%
|
This is how 9800M GTX SLI and Pro W6800 compete in popular games:
- Pro W6800 is 1613% faster in 1080p
- Pro W6800 is 1833% faster in 1440p
- Pro W6800 is 2000% faster in 4K
Here's the range of performance differences observed across popular games:
- in Metro Exodus, with 1440p resolution and the High Preset, the Pro W6800 is 17000% faster.
All in all, in popular games:
- Pro W6800 performs better in 52 tests (88%)
- there's a draw in 7 tests (12%)
Pros & cons summary
| Performance score | 2.86 | 48.20 |
| Recency | 15 July 2008 | 8 June 2021 |
| Maximum RAM amount | 1 GB | 32 GB |
| Chip lithography | 65 nm | 7 nm |
| Power consumption (TDP) | 150 Watt | 250 Watt |
9800M GTX SLI has 67% lower power consumption.
Pro W6800, on the other hand, has a 1585% higher aggregate performance score, an age advantage of 12 years, a 3100% higher maximum VRAM amount, and a 829% more advanced lithography process.
The Radeon Pro W6800 is our recommended choice as it beats the GeForce 9800M GTX SLI in performance tests.
Be aware that GeForce 9800M GTX SLI is a notebook graphics card while Radeon Pro W6800 is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
