Radeon Pro W6800 vs GeForce 9800 GX2
Aggregate performance score
We've compared GeForce 9800 GX2 with Radeon Pro W6800, including specs and performance data.
Pro W6800 outperforms 9800 GX2 by a whopping 3201% 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 | 1034 | 77 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 0.03 | 10.66 |
| Power efficiency | 0.57 | 14.85 |
| Architecture | Tesla (2006−2010) | RDNA 2.0 (2020−2025) |
| GPU code name | G92 | Navi 21 |
| Market segment | Desktop | Workstation |
| Release date | 18 March 2008 (17 years ago) | 8 June 2021 (4 years ago) |
| Launch price (MSRP) | $599 | $2,249 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Pro W6800 has 35433% better value for money than 9800 GX2.
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 | 256 (128 per GPU) ×2 | 3840 |
| Core clock speed | 600 MHz | 2075 MHz |
| Boost clock speed | no data | 2320 MHz |
| Number of transistors | 754 million | 26,800 million |
| Manufacturing process technology | 65 nm | 7 nm |
| Power consumption (TDP) | 197 Watt | 250 Watt |
| Maximum GPU temperature | 105 °C | no data |
| Texture fill rate | 38.40 ×2 | 556.8 |
| Floating-point processing power | 0.384 TFLOPS ×2 | 17.82 TFLOPS |
| ROPs | 16 ×2 | 96 |
| TMUs | 64 ×2 | 240 |
| Ray Tracing Cores | no data | 60 |
| L0 Cache | no data | 960 KB |
| L1 Cache | no data | 768 KB |
| L2 Cache | 64 KB | 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).
| Interface | PCIe 2.0 x16 | PCIe 4.0 x16 |
| Length | 267 mm | 267 mm |
| Height | 2-slot | no data |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 6-pin + 1x 8-pin | 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 | 512 MB ×2 | 32 GB |
| Memory bus width | 512 Bit ×2 | 256 Bit |
| Memory clock speed | 1000 MHz | 2000 MHz |
| Memory bandwidth | 128 (64 per GPU) ×2 | 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 | HDMIDual Link DVI | 6x mini-DisplayPort |
| Multi monitor support | + | no data |
| HDMI | + | - |
| Maximum VGA resolution | 2048x1536 | no data |
| Audio input for HDMI | S/PDIF | no data |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.1 (10_0) | 12 Ultimate (12_2) |
| Shader Model | 4.0 | 6.5 |
| OpenGL | 2.1 | 4.6 |
| OpenCL | 1.1 | 2.1 |
| Vulkan | N/A | 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.
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 | 4−5
−3325%
| 137
+3325%
|
| 1440p | 3−4
−3767%
| 116
+3767%
|
| 4K | 2−3
−4100%
| 84
+4100%
|
Cost per frame, $
| 1080p | 149.75
−812%
| 16.42
+812%
|
| 1440p | 199.67
−930%
| 19.39
+930%
|
| 4K | 299.50
−1019%
| 26.77
+1019%
|
- Pro W6800 has 812% lower cost per frame in 1080p
- Pro W6800 has 930% lower cost per frame in 1440p
- Pro W6800 has 1019% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 250−260
+0%
|
250−260
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Resident Evil 4 Remake | 130−140
+0%
|
130−140
+0%
|
Full HD
Medium
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Counter-Strike 2 | 250−260
+0%
|
250−260
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Far Cry 5 | 70
+0%
|
70
+0%
|
| Fortnite | 210−220
+0%
|
210−220
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| Forza Horizon 5 | 150−160
+0%
|
150−160
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 260−270
+0%
|
260−270
+0%
|
Full HD
High
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Counter-Strike 2 | 250−260
+0%
|
250−260
+0%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Dota 2 | 99
+0%
|
99
+0%
|
| Far Cry 5 | 65
+0%
|
65
+0%
|
| Fortnite | 210−220
+0%
|
210−220
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| Forza Horizon 5 | 150−160
+0%
|
150−160
+0%
|
| Grand Theft Auto V | 121
+0%
|
121
+0%
|
| Metro Exodus | 160
+0%
|
160
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 199
+0%
|
199
+0%
|
| Valorant | 260−270
+0%
|
260−270
+0%
|
Full HD
Ultra
| Battlefield 5 | 150−160
+0%
|
150−160
+0%
|
| Cyberpunk 2077 | 110−120
+0%
|
110−120
+0%
|
| Dota 2 | 86
+0%
|
86
+0%
|
| Far Cry 5 | 62
+0%
|
62
+0%
|
| Forza Horizon 4 | 180−190
+0%
|
180−190
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 157
+0%
|
157
+0%
|
| Valorant | 260−270
+0%
|
260−270
+0%
|
Full HD
Epic
| Fortnite | 210−220
+0%
|
210−220
+0%
|
1440p
High
| Counter-Strike 2 | 130−140
+0%
|
130−140
+0%
|
| Counter-Strike: Global Offensive | 300−350
+0%
|
300−350
+0%
|
| Grand Theft Auto V | 88
+0%
|
88
+0%
|
| Metro Exodus | 171
+0%
|
171
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
1440p
Ultra
| Battlefield 5 | 120−130
+0%
|
120−130
+0%
|
| Cyberpunk 2077 | 60−65
+0%
|
60−65
+0%
|
| Far Cry 5 | 64
+0%
|
64
+0%
|
| Forza Horizon 4 | 140−150
+0%
|
140−150
+0%
|
| The Witcher 3: Wild Hunt | 100−110
+0%
|
100−110
+0%
|
1440p
Epic
| Fortnite | 130−140
+0%
|
130−140
+0%
|
4K
High
| Counter-Strike 2 | 60−65
+0%
|
60−65
+0%
|
| Grand Theft Auto V | 125
+0%
|
125
+0%
|
| Metro Exodus | 55
+0%
|
55
+0%
|
| The Witcher 3: Wild Hunt | 99
+0%
|
99
+0%
|
| Valorant | 280−290
+0%
|
280−290
+0%
|
4K
Ultra
| Battlefield 5 | 80−85
+0%
|
80−85
+0%
|
| Counter-Strike 2 | 60−65
+0%
|
60−65
+0%
|
| Cyberpunk 2077 | 27−30
+0%
|
27−30
+0%
|
| Dota 2 | 94
+0%
|
94
+0%
|
| Far Cry 5 | 60
+0%
|
60
+0%
|
| Forza Horizon 4 | 100−110
+0%
|
100−110
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 75−80
+0%
|
75−80
+0%
|
4K
Epic
| Fortnite | 70−75
+0%
|
70−75
+0%
|
This is how 9800 GX2 and Pro W6800 compete in popular games:
- Pro W6800 is 3325% faster in 1080p
- Pro W6800 is 3767% faster in 1440p
- Pro W6800 is 4100% faster in 4K
All in all, in popular games:
- there's a draw in 60 tests (100%)
Pros & cons summary
| Performance score | 1.46 | 48.20 |
| Recency | 18 March 2008 | 8 June 2021 |
| Maximum RAM amount | 512 MB | 32 GB |
| Chip lithography | 65 nm | 7 nm |
| Power consumption (TDP) | 197 Watt | 250 Watt |
9800 GX2 has 26.9% lower power consumption.
Pro W6800, on the other hand, has a 3201.4% higher aggregate performance score, an age advantage of 13 years, a 6300% higher maximum VRAM amount, and a 828.6% more advanced lithography process.
The Radeon Pro W6800 is our recommended choice as it beats the GeForce 9800 GX2 in performance tests.
Be aware that GeForce 9800 GX2 is a desktop 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.
