Radeon RX 9070 vs GeForce RTX 4070 Ti
Aggregate performance score
We've compared GeForce RTX 4070 Ti and Radeon RX 9070, covering specs and all relevant benchmarks.
RTX 4070 Ti outperforms RX 9070 by a significant 21% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 9 | 33 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 48.98 | 65.50 |
| Power efficiency | 19.75 | 21.11 |
| Architecture | Ada Lovelace (2022−2024) | RDNA 4.0 (2025) |
| GPU code name | AD104 | Navi 48 |
| Market segment | Desktop | Desktop |
| Release date | 3 January 2023 (2 years ago) | 6 March 2025 (recently) |
| Launch price (MSRP) | $799 | $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 34% better value for money than RTX 4070 Ti.
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 | 7680 | 3584 |
| Core clock speed | 2310 MHz | 1330 MHz |
| Boost clock speed | 2610 MHz | 2520 MHz |
| Number of transistors | 35,800 million | 53,900 million |
| Manufacturing process technology | 4 nm | 5 nm |
| Power consumption (TDP) | 285 Watt | 220 Watt |
| Texture fill rate | 626.4 | 564.5 |
| Floating-point processing power | 40.09 TFLOPS | 36.13 TFLOPS |
| ROPs | 80 | 128 |
| TMUs | 240 | 224 |
| Tensor Cores | 240 | 112 |
| Ray Tracing Cores | 60 | 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 16-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 | 12 GB | 16 GB |
| Memory bus width | 192 Bit | 256 Bit |
| Memory clock speed | 1313 MHz | 2518 MHz |
| Memory bandwidth | 504.2 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 2.1, 3x DisplayPort 1.4a | 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 | 6.7 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.2 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.9 | - |
| 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 | 224
+24.4%
| 180−190
−24.4%
|
| 1440p | 140
+27.3%
| 110−120
−27.3%
|
| 4K | 87
+24.3%
| 70−75
−24.3%
|
Cost per frame, $
| 1080p | 3.57
−16.9%
| 3.05
+16.9%
|
| 1440p | 5.71
−14.4%
| 4.99
+14.4%
|
| 4K | 9.18
−17.1%
| 7.84
+17.1%
|
- RX 9070 has 17% lower cost per frame in 1080p
- RX 9070 has 14% lower cost per frame in 1440p
- RX 9070 has 17% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 316
+61.2%
|
190−200
−61.2%
|
| Counter-Strike 2 | 300−350
+6.5%
|
300−350
−6.5%
|
| Cyberpunk 2077 | 236
+49.4%
|
150−160
−49.4%
|
Full HD
Medium Preset
| Atomic Heart | 253
+29.1%
|
190−200
−29.1%
|
| Battlefield 5 | 190−200
+12.2%
|
170−180
−12.2%
|
| Counter-Strike 2 | 300−350
+6.5%
|
300−350
−6.5%
|
| Cyberpunk 2077 | 218
+38%
|
150−160
−38%
|
| Far Cry 5 | 211
+22.7%
|
170−180
−22.7%
|
| Fortnite | 300−350
+0.3%
|
300−350
−0.3%
|
| Forza Horizon 4 | 300−350
+26.5%
|
240−250
−26.5%
|
| Forza Horizon 5 | 244
+32.6%
|
180−190
−32.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 450−500
+32.4%
|
350−400
−32.4%
|
Full HD
High Preset
| Atomic Heart | 180
−8.9%
|
190−200
+8.9%
|
| Battlefield 5 | 190−200
+12.2%
|
170−180
−12.2%
|
| Counter-Strike 2 | 300−350
+6.5%
|
300−350
−6.5%
|
| Counter-Strike: Global Offensive | 270−280
+0%
|
270−280
+0%
|
| Cyberpunk 2077 | 185
+17.1%
|
150−160
−17.1%
|
| Dota 2 | 259
+23.3%
|
210−220
−23.3%
|
| Far Cry 5 | 203
+18%
|
170−180
−18%
|
| Fortnite | 300−350
+0.3%
|
300−350
−0.3%
|
| Forza Horizon 4 | 300−350
+26.5%
|
240−250
−26.5%
|
| Forza Horizon 5 | 228
+23.9%
|
180−190
−23.9%
|
| Grand Theft Auto V | 178
+7.2%
|
160−170
−7.2%
|
| Metro Exodus | 197
+23.1%
|
160−170
−23.1%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 453
+72.2%
|
260−270
−72.2%
|
| Valorant | 450−500
+32.4%
|
350−400
−32.4%
|
Full HD
Ultra Preset
| Battlefield 5 | 190−200
+12.2%
|
170−180
−12.2%
|
| Cyberpunk 2077 | 167
+5.7%
|
150−160
−5.7%
|
| Dota 2 | 243
+21.5%
|
200−210
−21.5%
|
| Far Cry 5 | 189
+9.9%
|
170−180
−9.9%
|
| Forza Horizon 4 | 300−350
+26.5%
|
240−250
−26.5%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| The Witcher 3: Wild Hunt | 221
−19%
|
260−270
+19%
|
| Valorant | 450−500
+32.4%
|
350−400
−32.4%
|
Full HD
Epic Preset
| Fortnite | 300−350
+0.3%
|
300−350
−0.3%
|
1440p
High Preset
| Counter-Strike 2 | 240−250
+27.6%
|
190−200
−27.6%
|
| Counter-Strike: Global Offensive | 500−550
+6.6%
|
450−500
−6.6%
|
| Grand Theft Auto V | 156
+17.3%
|
130−140
−17.3%
|
| Metro Exodus | 131
+23.6%
|
100−110
−23.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Valorant | 450−500
+13.3%
|
400−450
−13.3%
|
1440p
Ultra Preset
| Battlefield 5 | 190−200
+24.1%
|
150−160
−24.1%
|
| Cyberpunk 2077 | 105
+16.7%
|
90−95
−16.7%
|
| Far Cry 5 | 182
+19.7%
|
150−160
−19.7%
|
| Forza Horizon 4 | 280−290
+31.9%
|
210−220
−31.9%
|
| The Witcher 3: Wild Hunt | 190−200
+34.5%
|
140−150
−34.5%
|
1440p
Epic Preset
| Fortnite | 150−160
+0%
|
150−160
+0%
|
4K
High Preset
| Atomic Heart | 75−80
+32.8%
|
55−60
−32.8%
|
| Counter-Strike 2 | 110−120
+30.2%
|
85−90
−30.2%
|
| Grand Theft Auto V | 172
+11.7%
|
150−160
−11.7%
|
| Metro Exodus | 84
+23.5%
|
65−70
−23.5%
|
| The Witcher 3: Wild Hunt | 149
+15.5%
|
120−130
−15.5%
|
| Valorant | 300−350
+0.6%
|
300−350
−0.6%
|
4K
Ultra Preset
| Battlefield 5 | 130−140
+18.3%
|
110−120
−18.3%
|
| Counter-Strike 2 | 110−120
+30.2%
|
85−90
−30.2%
|
| Cyberpunk 2077 | 48
+11.6%
|
40−45
−11.6%
|
| Dota 2 | 226
+25.6%
|
180−190
−25.6%
|
| Far Cry 5 | 111
+11%
|
100−105
−11%
|
| Forza Horizon 4 | 240−250
+50.6%
|
160−170
−50.6%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+0%
|
95−100
+0%
|
4K
Epic Preset
| Fortnite | 75−80
+0%
|
75−80
+0%
|
This is how RTX 4070 Ti and RX 9070 compete in popular games:
- RTX 4070 Ti is 24% faster in 1080p
- RTX 4070 Ti is 27% faster in 1440p
- RTX 4070 Ti is 24% faster in 4K
Here's the range of performance differences observed across popular games:
- in The Witcher 3: Wild Hunt, with 1080p resolution and the High Preset, the RTX 4070 Ti is 72% faster.
- in The Witcher 3: Wild Hunt, with 1080p resolution and the Ultra Preset, the RX 9070 is 19% faster.
All in all, in popular games:
- RTX 4070 Ti is ahead in 50 tests (83%)
- RX 9070 is ahead in 2 tests (3%)
- there's a draw in 8 tests (13%)
Pros & cons summary
| Performance score | 70.96 | 58.55 |
| Recency | 3 January 2023 | 6 March 2025 |
| Maximum RAM amount | 12 GB | 16 GB |
| Chip lithography | 4 nm | 5 nm |
| Power consumption (TDP) | 285 Watt | 220 Watt |
RTX 4070 Ti has a 21.2% higher aggregate performance score, and a 25% more advanced lithography process.
RX 9070, on the other hand, has an age advantage of 2 years, a 33.3% higher maximum VRAM amount, and 29.5% lower power consumption.
The GeForce RTX 4070 Ti is our recommended choice as it beats the Radeon RX 9070 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.
