Radeon RX 6950 XT vs HD 8670D
Aggregate performance score
We've compared Radeon HD 8670D and Radeon RX 6950 XT, covering specs and all relevant benchmarks.
RX 6950 XT outperforms HD 8670D by a whopping 5188% 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 | 15 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 27.09 |
| Power efficiency | 0.96 | 15.13 |
| Architecture | TeraScale 3 (2010−2013) | RDNA 2.0 (2020−2024) |
| GPU code name | Devastator | Navi 21 |
| Market segment | Desktop | Desktop |
| Release date | 12 March 2013 (11 years ago) | 10 May 2022 (2 years ago) |
| Launch price (MSRP) | no data | $1,099 |
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 | 384 | 5120 |
| Core clock speed | 844 MHz | 1925 MHz |
| Boost clock speed | 950 MHz | 2324 MHz |
| Number of transistors | 1,303 million | 26,800 million |
| Manufacturing process technology | 32 nm | 7 nm |
| Power consumption (TDP) | 100 Watt | 335 Watt |
| Texture fill rate | 22.80 | 743.7 |
| Floating-point processing power | 0.7296 TFLOPS | 23.8 TFLOPS |
| ROPs | 8 | 128 |
| TMUs | 24 | 320 |
| Ray Tracing Cores | no data | 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).
| Interface | IGP | PCIe 4.0 x16 |
| Length | no data | 267 mm |
| Width | IGP | 3-slot |
| Supplementary power connectors | no data | 2x 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 | System Shared | GDDR6 |
| Maximum RAM amount | System Shared | 16 GB |
| Memory bus width | System Shared | 256 Bit |
| Memory clock speed | System Shared | 2250 MHz |
| Memory bandwidth | no data | 576.0 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 | 1x HDMI 2.1, 2x DisplayPort 1.4a |
| HDMI | - | + |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 11.2 (11_0) | 12 Ultimate (12_2) |
| Shader Model | 5.0 | 6.5 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 2.1 |
| Vulkan | N/A | 1.3 |
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.
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 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.
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.
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 | 16
−1313%
| 226
+1313%
|
| 1440p | 2−3
−6900%
| 140
+6900%
|
| 4K | 1−2
−8400%
| 85
+8400%
|
Cost per frame, $
| 1080p | no data | 4.86 |
| 1440p | no data | 7.85 |
| 4K | no data | 12.93 |
FPS performance in popular games
Full HD
Low Preset
| Cyberpunk 2077 | 4−5
−3925%
|
161
+3925%
|
Full HD
Medium Preset
| Assassin's Creed Odyssey | 6−7
−2417%
|
150−160
+2417%
|
| Call of Duty: Modern Warfare | 4−5
−2900%
|
120−130
+2900%
|
| Cyberpunk 2077 | 4−5
−3475%
|
143
+3475%
|
| Far Cry 5 | 2−3
−5750%
|
110−120
+5750%
|
| Far Cry New Dawn | 3−4
−5933%
|
180−190
+5933%
|
| Forza Horizon 4 | 3−4
−7967%
|
240−250
+7967%
|
| Hitman 3 | 6−7
−2050%
|
120−130
+2050%
|
| Horizon Zero Dawn | 14−16
−1660%
|
260−270
+1660%
|
| Red Dead Redemption 2 | 2−3
−6050%
|
120−130
+6050%
|
| Shadow of the Tomb Raider | 8−9
−3813%
|
300−350
+3813%
|
| Watch Dogs: Legion | 30−35
−364%
|
150−160
+364%
|
Full HD
High Preset
| Assassin's Creed Odyssey | 6−7
−2417%
|
150−160
+2417%
|
| Call of Duty: Modern Warfare | 4−5
−2900%
|
120−130
+2900%
|
| Cyberpunk 2077 | 4−5
−3100%
|
128
+3100%
|
| Far Cry 5 | 2−3
−5750%
|
110−120
+5750%
|
| Far Cry New Dawn | 3−4
−5933%
|
180−190
+5933%
|
| Forza Horizon 4 | 3−4
−7967%
|
240−250
+7967%
|
| Hitman 3 | 6−7
−2050%
|
120−130
+2050%
|
| Horizon Zero Dawn | 14−16
−1660%
|
260−270
+1660%
|
| Red Dead Redemption 2 | 2−3
−6050%
|
120−130
+6050%
|
| Shadow of the Tomb Raider | 8−9
−5425%
|
442
+5425%
|
| The Witcher 3: Wild Hunt | 10−12
−1345%
|
150−160
+1345%
|
| Watch Dogs: Legion | 30−35
−364%
|
150−160
+364%
|
Full HD
Ultra Preset
| Assassin's Creed Odyssey | 6−7
−2417%
|
150−160
+2417%
|
| Call of Duty: Modern Warfare | 4−5
−2900%
|
120−130
+2900%
|
| Cyberpunk 2077 | 4−5
−2950%
|
122
+2950%
|
| Far Cry 5 | 2−3
−5750%
|
110−120
+5750%
|
| Forza Horizon 4 | 3−4
−7967%
|
240−250
+7967%
|
| Hitman 3 | 6−7
−2050%
|
120−130
+2050%
|
| Horizon Zero Dawn | 14−16
−2020%
|
318
+2020%
|
| Shadow of the Tomb Raider | 8−9
−4850%
|
396
+4850%
|
| The Witcher 3: Wild Hunt | 10−12
−1864%
|
216
+1864%
|
| Watch Dogs: Legion | 30−35
−224%
|
107
+224%
|
Full HD
Epic Preset
| Red Dead Redemption 2 | 2−3
−6050%
|
120−130
+6050%
|
1440p
High Preset
| Battlefield 5 | 1−2
−16500%
|
160−170
+16500%
|
| Far Cry New Dawn | 2−3
−5500%
|
110−120
+5500%
|
1440p
Ultra Preset
| Assassin's Creed Odyssey | 1−2
−8600%
|
85−90
+8600%
|
| Call of Duty: Modern Warfare | 0−1 | 80−85 |
| Cyberpunk 2077 | 1−2
−9200%
|
93
+9200%
|
| Far Cry 5 | 1−2
−8300%
|
80−85
+8300%
|
| Hitman 3 | 7−8
−1429%
|
100−110
+1429%
|
| Horizon Zero Dawn | 5−6
−5000%
|
255
+5000%
|
| The Witcher 3: Wild Hunt | 1−2
−13400%
|
130−140
+13400%
|
| Watch Dogs: Legion | 7−8
−3329%
|
240−250
+3329%
|
1440p
Epic Preset
| Red Dead Redemption 2 | 4−5
−2850%
|
110−120
+2850%
|
4K
High Preset
| Far Cry New Dawn | 1−2
−6800%
|
65−70
+6800%
|
4K
Ultra Preset
| Assassin's Creed Odyssey | 1−2
−6000%
|
60−65
+6000%
|
| Assassin's Creed Valhalla | 1−2
−5800%
|
55−60
+5800%
|
| Call of Duty: Modern Warfare | 0−1 | 50−55 |
| Far Cry 5 | 0−1 | 50−55 |
4K
Epic Preset
| Red Dead Redemption 2 | 3−4
−2633%
|
80−85
+2633%
|
Full HD
Medium Preset
| Assassin's Creed Valhalla | 130−140
+0%
|
130−140
+0%
|
| Battlefield 5 | 230−240
+0%
|
230−240
+0%
|
| Metro Exodus | 150−160
+0%
|
150−160
+0%
|
Full HD
High Preset
| Assassin's Creed Valhalla | 130−140
+0%
|
130−140
+0%
|
| Battlefield 5 | 230−240
+0%
|
230−240
+0%
|
| Metro Exodus | 150−160
+0%
|
150−160
+0%
|
Full HD
Ultra Preset
| Assassin's Creed Valhalla | 130−140
+0%
|
130−140
+0%
|
1440p
Ultra Preset
| Assassin's Creed Valhalla | 90−95
+0%
|
90−95
+0%
|
| Forza Horizon 4 | 270−280
+0%
|
270−280
+0%
|
| Metro Exodus | 132
+0%
|
132
+0%
|
| Shadow of the Tomb Raider | 294
+0%
|
294
+0%
|
4K
High Preset
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Hitman 3 | 65−70
+0%
|
65−70
+0%
|
| Horizon Zero Dawn | 220−230
+0%
|
220−230
+0%
|
| Metro Exodus | 110−120
+0%
|
110−120
+0%
|
| The Witcher 3: Wild Hunt | 144
+0%
|
144
+0%
|
4K
Ultra Preset
| Cyberpunk 2077 | 46
+0%
|
46
+0%
|
| Forza Horizon 4 | 130−140
+0%
|
130−140
+0%
|
| Shadow of the Tomb Raider | 172
+0%
|
172
+0%
|
| Watch Dogs: Legion | 65
+0%
|
65
+0%
|
This is how HD 8670D and RX 6950 XT compete in popular games:
- RX 6950 XT is 1313% faster in 1080p
- RX 6950 XT is 6900% faster in 1440p
- RX 6950 XT is 8400% faster in 4K
Here's the range of performance differences observed across popular games:
- in Battlefield 5, with 1440p resolution and the High Preset, the RX 6950 XT is 16500% faster.
All in all, in popular games:
- RX 6950 XT is ahead in 49 tests (71%)
- there's a draw in 20 tests (29%)
Pros & cons summary
| Performance score | 1.38 | 72.97 |
| Recency | 12 March 2013 | 10 May 2022 |
| Chip lithography | 32 nm | 7 nm |
| Power consumption (TDP) | 100 Watt | 335 Watt |
HD 8670D has 235% lower power consumption.
RX 6950 XT, on the other hand, has a 5187.7% higher aggregate performance score, an age advantage of 9 years, and a 357.1% more advanced lithography process.
The Radeon RX 6950 XT is our recommended choice as it beats the Radeon HD 8670D in performance tests.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Comparisons with similar GPUs
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
