GeForce RTX 3070 vs Radeon HD 6990
Aggregate performance score
We've compared Radeon HD 6990 and GeForce RTX 3070, covering specs and all relevant benchmarks.
RTX 3070 outperforms HD 6990 by a whopping 640% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 531 | 45 |
| Place by popularity | not in top-100 | 40 |
| Cost-effectiveness evaluation | 0.62 | 57.71 |
| Power efficiency | 1.43 | 18.09 |
| Architecture | TeraScale 3 (2010−2013) | Ampere (2020−2024) |
| GPU code name | Antilles | GA104 |
| Market segment | Desktop | Desktop |
| Release date | 8 March 2011 (13 years ago) | 1 September 2020 (4 years ago) |
| Launch price (MSRP) | $699 | $499 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
RTX 3070 has 9208% better value for money than HD 6990.
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 | 1536 ×2 | 5888 |
| Core clock speed | 830 MHz | 1500 MHz |
| Boost clock speed | no data | 1725 MHz |
| Number of transistors | 2,640 million | 17,400 million |
| Manufacturing process technology | 40 nm | 8 nm |
| Power consumption (TDP) | 375 Watt | 220 Watt |
| Texture fill rate | 79.68 ×2 | 317.4 |
| Floating-point processing power | 2.55 TFLOPS ×2 | 20.31 TFLOPS |
| ROPs | 32 ×2 | 96 |
| TMUs | 96 ×2 | 184 |
| Tensor Cores | no data | 184 |
| Ray Tracing Cores | no data | 46 |
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 | 295 mm | 242 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 2x 8-pin | 1x 12-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 | GDDR5 | GDDR6 |
| Maximum RAM amount | 2 GB ×2 | 8 GB |
| Memory bus width | 256 Bit ×2 | 256 Bit |
| Memory clock speed | 1250 MHz | 1750 MHz |
| Memory bandwidth | 160.0 GB/s ×2 | 448.0 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 | 1x DVI, 4x mini-DisplayPort | 1x HDMI, 3x DisplayPort |
| HDMI | - | + |
API and SDK 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 | 2.0 |
| Vulkan | N/A | 1.2 |
| CUDA | - | 8.5 |
| DLSS | - | + |
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 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.
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 | 18−21
−733%
| 150
+733%
|
| 1440p | 12−14
−717%
| 98
+717%
|
| 4K | 8−9
−700%
| 64
+700%
|
Cost per frame, $
| 1080p | 38.83
−1067%
| 3.33
+1067%
|
| 1440p | 58.25
−1044%
| 5.09
+1044%
|
| 4K | 87.38
−1021%
| 7.80
+1021%
|
- RTX 3070 has 1067% lower cost per frame in 1080p
- RTX 3070 has 1044% lower cost per frame in 1440p
- RTX 3070 has 1021% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 263
+0%
|
263
+0%
|
| Counter-Strike 2 | 149
+0%
|
149
+0%
|
| Cyberpunk 2077 | 147
+0%
|
147
+0%
|
Full HD
Medium Preset
| Atomic Heart | 196
+0%
|
196
+0%
|
| Battlefield 5 | 149
+0%
|
149
+0%
|
| Counter-Strike 2 | 135
+0%
|
135
+0%
|
| Cyberpunk 2077 | 139
+0%
|
139
+0%
|
| Far Cry 5 | 154
+0%
|
154
+0%
|
| Fortnite | 230−240
+0%
|
230−240
+0%
|
| Forza Horizon 4 | 200−210
+0%
|
200−210
+0%
|
| Forza Horizon 5 | 159
+0%
|
159
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 290−300
+0%
|
290−300
+0%
|
Full HD
High Preset
| Atomic Heart | 113
+0%
|
113
+0%
|
| Battlefield 5 | 132
+0%
|
132
+0%
|
| Counter-Strike 2 | 117
+0%
|
117
+0%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 126
+0%
|
126
+0%
|
| Dota 2 | 133
+0%
|
133
+0%
|
| Far Cry 5 | 148
+0%
|
148
+0%
|
| Fortnite | 230−240
+0%
|
230−240
+0%
|
| Forza Horizon 4 | 200−210
+0%
|
200−210
+0%
|
| Forza Horizon 5 | 148
+0%
|
148
+0%
|
| Grand Theft Auto V | 139
+0%
|
139
+0%
|
| Metro Exodus | 120
+0%
|
120
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 230
+0%
|
230
+0%
|
| Valorant | 290−300
+0%
|
290−300
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 119
+0%
|
119
+0%
|
| Counter-Strike 2 | 105
+0%
|
105
+0%
|
| Cyberpunk 2077 | 102
+0%
|
102
+0%
|
| Dota 2 | 125
+0%
|
125
+0%
|
| Far Cry 5 | 141
+0%
|
141
+0%
|
| Forza Horizon 4 | 200−210
+0%
|
200−210
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 121
+0%
|
121
+0%
|
| Valorant | 237
+0%
|
237
+0%
|
Full HD
Epic Preset
| Fortnite | 230−240
+0%
|
230−240
+0%
|
1440p
High Preset
| Counter-Strike 2 | 40−45
+0%
|
40−45
+0%
|
| Counter-Strike: Global Offensive | 350−400
+0%
|
350−400
+0%
|
| Grand Theft Auto V | 98
+0%
|
98
+0%
|
| Metro Exodus | 75
+0%
|
75
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 103
+0%
|
103
+0%
|
| Cyberpunk 2077 | 62
+0%
|
62
+0%
|
| Far Cry 5 | 125
+0%
|
125
+0%
|
| Forza Horizon 4 | 160−170
+0%
|
160−170
+0%
|
| The Witcher 3: Wild Hunt | 110−120
+0%
|
110−120
+0%
|
1440p
Epic Preset
| Fortnite | 150−160
+0%
|
150−160
+0%
|
4K
High Preset
| Atomic Heart | 45−50
+0%
|
45−50
+0%
|
| Counter-Strike 2 | 30−35
+0%
|
30−35
+0%
|
| Grand Theft Auto V | 117
+0%
|
117
+0%
|
| Metro Exodus | 49
+0%
|
49
+0%
|
| The Witcher 3: Wild Hunt | 90
+0%
|
90
+0%
|
| Valorant | 300−350
+0%
|
300−350
+0%
|
4K
Ultra Preset
| Battlefield 5 | 70
+0%
|
70
+0%
|
| Counter-Strike 2 | 16
+0%
|
16
+0%
|
| Cyberpunk 2077 | 30
+0%
|
30
+0%
|
| Dota 2 | 125
+0%
|
125
+0%
|
| Far Cry 5 | 70
+0%
|
70
+0%
|
| Forza Horizon 4 | 120−130
+0%
|
120−130
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 90−95
+0%
|
90−95
+0%
|
4K
Epic Preset
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how HD 6990 and RTX 3070 compete in popular games:
- RTX 3070 is 733% faster in 1080p
- RTX 3070 is 717% faster in 1440p
- RTX 3070 is 700% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 7.66 | 56.67 |
| Recency | 8 March 2011 | 1 September 2020 |
| Maximum RAM amount | 2 GB | 8 GB |
| Chip lithography | 40 nm | 8 nm |
| Power consumption (TDP) | 375 Watt | 220 Watt |
RTX 3070 has a 639.8% higher aggregate performance score, an age advantage of 9 years, a 300% higher maximum VRAM amount, a 400% more advanced lithography process, and 70.5% lower power consumption.
The GeForce RTX 3070 is our recommended choice as it beats the Radeon HD 6990 in performance tests.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
