Radeon RX 9070 vs GeForce RTX 3080
Aggregate performance score
We've compared GeForce RTX 3080 and Radeon RX 9070, covering specs and all relevant benchmarks.
RX 9070 outperforms RTX 3080 by a minimal 3% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 34 | 33 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 46.21 | 64.99 |
| Power efficiency | 14.00 | 21.25 |
| Architecture | Ampere (2020−2024) | RDNA 4.0 (2025) |
| GPU code name | GA102 | Navi 48 |
| Market segment | Desktop | Desktop |
| Release date | 1 September 2020 (4 years ago) | 6 March 2025 (recently) |
| Launch price (MSRP) | $699 | $549 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
RX 9070 has 41% better value for money than RTX 3080.
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 | 8704 | 3584 |
| Core clock speed | 1440 MHz | 1330 MHz |
| Boost clock speed | 1710 MHz | 2520 MHz |
| Number of transistors | 28,300 million | 53,900 million |
| Manufacturing process technology | 8 nm | 5 nm |
| Power consumption (TDP) | 320 Watt | 220 Watt |
| Texture fill rate | 465.1 | 564.5 |
| Floating-point processing power | 29.77 TFLOPS | 36.13 TFLOPS |
| ROPs | 96 | 128 |
| TMUs | 272 | 224 |
| Tensor Cores | 272 | 112 |
| Ray Tracing Cores | 68 | 56 |
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 4.0 x16 | PCIe 5.0 x16 |
| Length | 285 mm | 267 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 12-pin | 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 | GDDR6X | GDDR6 |
| Maximum RAM amount | 10 GB | 16 GB |
| Memory bus width | 320 Bit | 256 Bit |
| Memory clock speed | 1188 MHz | 2518 MHz |
| Memory bandwidth | 760.3 GB/s | 644.6 GB/s |
| Shared memory | - | - |
| Resizable BAR | + | + |
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 HDMI, 3x DisplayPort | 1x HDMI 2.1b, 3x DisplayPort 2.1a |
| HDMI | + | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.5 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.2 |
| Vulkan | 1.2 | 1.3 |
| 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.
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 | 163
+1.9%
| 160−170
−1.9%
|
| 1440p | 122
+1.7%
| 120−130
−1.7%
|
| 4K | 85
+0%
| 85−90
+0%
|
Cost per frame, $
| 1080p | 4.29
−25%
| 3.43
+25%
|
| 1440p | 5.73
−25.2%
| 4.58
+25.2%
|
| 4K | 8.22
−27.3%
| 6.46
+27.3%
|
- RX 9070 has 25% lower cost per frame in 1080p
- RX 9070 has 25% lower cost per frame in 1440p
- RX 9070 has 27% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 307
+56.6%
|
190−200
−56.6%
|
| Counter-Strike 2 | 300−350
−2.3%
|
300−350
+2.3%
|
| Cyberpunk 2077 | 150−160
−4.6%
|
150−160
+4.6%
|
Full HD
Medium Preset
| Atomic Heart | 239
+21.9%
|
190−200
−21.9%
|
| Battlefield 5 | 172
+0%
|
170−180
+0%
|
| Counter-Strike 2 | 300−350
−2.3%
|
300−350
+2.3%
|
| Cyberpunk 2077 | 138
−14.5%
|
150−160
+14.5%
|
| Far Cry 5 | 157
−9.6%
|
170−180
+9.6%
|
| Fortnite | 280−290
−5.2%
|
300−350
+5.2%
|
| Forza Horizon 4 | 230−240
−5.1%
|
240−250
+5.1%
|
| Forza Horizon 5 | 152
−21.1%
|
180−190
+21.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 300−350
−5.7%
|
350−400
+5.7%
|
Full HD
High Preset
| Atomic Heart | 147
−33.3%
|
190−200
+33.3%
|
| Battlefield 5 | 156
−10.3%
|
170−180
+10.3%
|
| Counter-Strike 2 | 300−350
−2.3%
|
300−350
+2.3%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 134
−17.9%
|
150−160
+17.9%
|
| Dota 2 | 147
−2%
|
150−160
+2%
|
| Far Cry 5 | 150
−14.7%
|
170−180
+14.7%
|
| Fortnite | 280−290
−5.2%
|
300−350
+5.2%
|
| Forza Horizon 4 | 230−240
−5.1%
|
240−250
+5.1%
|
| Forza Horizon 5 | 140
−31.4%
|
180−190
+31.4%
|
| Grand Theft Auto V | 147
−12.9%
|
160−170
+12.9%
|
| Metro Exodus | 128
−25%
|
160−170
+25%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 303
+15.6%
|
260−270
−15.6%
|
| Valorant | 300−350
−5.7%
|
350−400
+5.7%
|
Full HD
Ultra Preset
| Battlefield 5 | 145
−18.6%
|
170−180
+18.6%
|
| Cyberpunk 2077 | 131
−20.6%
|
150−160
+20.6%
|
| Dota 2 | 135
+3.8%
|
130−140
−3.8%
|
| Far Cry 5 | 140
−22.9%
|
170−180
+22.9%
|
| Forza Horizon 4 | 230−240
−5.1%
|
240−250
+5.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 149
−75.8%
|
260−270
+75.8%
|
| Valorant | 268
−32.1%
|
350−400
+32.1%
|
Full HD
Epic Preset
| Fortnite | 280−290
−5.2%
|
300−350
+5.2%
|
1440p
High Preset
| Counter-Strike 2 | 180−190
−5.5%
|
190−200
+5.5%
|
| Counter-Strike: Global Offensive | 450−500
−6.4%
|
450−500
+6.4%
|
| Grand Theft Auto V | 112
−18.8%
|
130−140
+18.8%
|
| Metro Exodus | 95
−11.6%
|
100−110
+11.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 350−400
−7.8%
|
400−450
+7.8%
|
1440p
Ultra Preset
| Battlefield 5 | 124
−27.4%
|
150−160
+27.4%
|
| Cyberpunk 2077 | 86
−3.5%
|
85−90
+3.5%
|
| Far Cry 5 | 135
−12.6%
|
150−160
+12.6%
|
| Forza Horizon 4 | 200−210
−6%
|
210−220
+6%
|
| The Witcher 3: Wild Hunt | 130−140
−6.6%
|
140−150
+6.6%
|
1440p
Epic Preset
| Fortnite | 150−160
+0%
|
150−160
+0%
|
4K
High Preset
| Atomic Heart | 50−55
−7.4%
|
55−60
+7.4%
|
| Counter-Strike 2 | 80−85
−6.2%
|
85−90
+6.2%
|
| Grand Theft Auto V | 143
−7.7%
|
150−160
+7.7%
|
| Metro Exodus | 65
−4.6%
|
65−70
+4.6%
|
| The Witcher 3: Wild Hunt | 115
−10.4%
|
120−130
+10.4%
|
| Valorant | 300−350
−1.2%
|
300−350
+1.2%
|
4K
Ultra Preset
| Battlefield 5 | 91
−26.4%
|
110−120
+26.4%
|
| Counter-Strike 2 | 80−85
−6.2%
|
85−90
+6.2%
|
| Cyberpunk 2077 | 43
+0%
|
40−45
+0%
|
| Dota 2 | 129
−0.8%
|
130−140
+0.8%
|
| Far Cry 5 | 94
−5.3%
|
95−100
+5.3%
|
| Forza Horizon 4 | 150−160
−9.3%
|
160−170
+9.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+0%
|
95−100
+0%
|
4K
Epic Preset
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how RTX 3080 and RX 9070 compete in popular games:
- RTX 3080 is 2% faster in 1080p
- RTX 3080 is 2% faster in 1440p
- A tie in 4K
Here's the range of performance differences observed across popular games:
- in Atomic Heart, with 1080p resolution and the Low Preset, the RTX 3080 is 57% faster.
- in The Witcher 3: Wild Hunt, with 1080p resolution and the Ultra Preset, the RX 9070 is 76% faster.
All in all, in popular games:
- RTX 3080 is ahead in 3 tests (5%)
- RX 9070 is ahead in 47 tests (78%)
- there's a draw in 10 tests (17%)
Pros & cons summary
| Performance score | 56.32 | 58.09 |
| Recency | 1 September 2020 | 6 March 2025 |
| Maximum RAM amount | 10 GB | 16 GB |
| Chip lithography | 8 nm | 5 nm |
| Power consumption (TDP) | 320 Watt | 220 Watt |
RX 9070 has a 3.1% higher aggregate performance score, an age advantage of 4 years, a 60% higher maximum VRAM amount, a 60% more advanced lithography process, and 45.5% lower power consumption.
Given the minimal performance differences, no clear winner can be declared between GeForce RTX 3080 and Radeon RX 9070.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
