GeForce RTX 3070 vs GTX 650 Ti
Aggregate performance score
We've compared GeForce GTX 650 Ti and GeForce RTX 3070, covering specs and all relevant benchmarks.
RTX 3070 outperforms GTX 650 Ti by a whopping 784% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 574 | 42 |
| Place by popularity | not in top-100 | 37 |
| Cost-effectiveness evaluation | 2.10 | 58.01 |
| Power efficiency | 4.12 | 18.20 |
| Architecture | Kepler (2012−2018) | Ampere (2020−2024) |
| GPU code name | GK106 | GA104 |
| Market segment | Desktop | Desktop |
| Release date | 9 October 2012 (12 years ago) | 1 September 2020 (4 years ago) |
| Launch price (MSRP) | $149 | $499 |
Cost-effectiveness evaluation
Performance to price ratio. The higher, the better.
RTX 3070 has 2662% better value for money than GTX 650 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 | 768 | 5888 |
| Core clock speed | 928 MHz | 1500 MHz |
| Boost clock speed | no data | 1725 MHz |
| Number of transistors | 2,540 million | 17,400 million |
| Manufacturing process technology | 28 nm | 8 nm |
| Power consumption (TDP) | 110 Watt | 220 Watt |
| Maximum GPU temperature | 105 °C | no data |
| Texture fill rate | 59.39 | 317.4 |
| Floating-point processing power | 1.425 TFLOPS | 20.31 TFLOPS |
| ROPs | 16 | 96 |
| TMUs | 64 | 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).
| Bus support | PCI Express 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Length | 145 mm | 242 mm |
| Height | 4.376" (11.1 cm) | no data |
| Width | 1-slot | 2-slot |
| Supplementary power connectors | 1x 6-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 | 8 GB |
| Memory bus width | 128 Bit | 256 Bit |
| Memory clock speed | 5.4 GB/s | 1750 MHz |
| Memory bandwidth | 86.4 GB/s | 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 | One Dual Link DVI-I, One Dual Link DVI-D, One Mini HDMI | 1x HDMI, 3x DisplayPort |
| Multi monitor support | 4 Displays | no data |
| HDMI | + | + |
| HDCP | + | - |
| Maximum VGA resolution | 2048x1536 | no data |
| Audio input for HDMI | Internal | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| 3D Blu-Ray | + | - |
| 3D Gaming | + | - |
| 3D Vision | + | - |
API compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.5 |
| OpenGL | 4.3 | 4.6 |
| OpenCL | 1.2 | 2.0 |
| Vulkan | 1.1.126 | 1.2 |
| CUDA | + | 8.5 |
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 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.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 Vulkan
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.
GeekBench 5 CUDA
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses CUDA API by NVIDIA.
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 | 16−18
−838%
| 150
+838%
|
| 1440p | 10−12
−880%
| 98
+880%
|
| 4K | 7−8
−814%
| 64
+814%
|
Cost per frame, $
| 1080p | 9.31
−180%
| 3.33
+180%
|
| 1440p | 14.90
−193%
| 5.09
+193%
|
| 4K | 21.29
−173%
| 7.80
+173%
|
- RTX 3070 has 180% lower cost per frame in 1080p
- RTX 3070 has 193% lower cost per frame in 1440p
- RTX 3070 has 173% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 149
+0%
|
149
+0%
|
| Cyberpunk 2077 | 147
+0%
|
147
+0%
|
Full HD
Medium Preset
| Battlefield 5 | 110−120
+0%
|
110−120
+0%
|
| Counter-Strike 2 | 135
+0%
|
135
+0%
|
| Cyberpunk 2077 | 124
+0%
|
124
+0%
|
| Forza Horizon 4 | 311
+0%
|
311
+0%
|
| Forza Horizon 5 | 139
+0%
|
139
+0%
|
| Metro Exodus | 124
+0%
|
124
+0%
|
| Red Dead Redemption 2 | 118
+0%
|
118
+0%
|
| Valorant | 246
+0%
|
246
+0%
|
Full HD
High Preset
| Battlefield 5 | 110−120
+0%
|
110−120
+0%
|
| Counter-Strike 2 | 117
+0%
|
117
+0%
|
| Cyberpunk 2077 | 109
+0%
|
109
+0%
|
| Dota 2 | 137
+0%
|
137
+0%
|
| Far Cry 5 | 91
+0%
|
91
+0%
|
| Fortnite | 220−230
+0%
|
220−230
+0%
|
| Forza Horizon 4 | 256
+0%
|
256
+0%
|
| Forza Horizon 5 | 144
+0%
|
144
+0%
|
| Grand Theft Auto V | 134
+0%
|
134
+0%
|
| Metro Exodus | 107
+0%
|
107
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+0%
|
210−220
+0%
|
| Red Dead Redemption 2 | 98
+0%
|
98
+0%
|
| The Witcher 3: Wild Hunt | 170−180
+0%
|
170−180
+0%
|
| Valorant | 159
+0%
|
159
+0%
|
| World of Tanks | 270−280
+0%
|
270−280
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 110−120
+0%
|
110−120
+0%
|
| Counter-Strike 2 | 105
+0%
|
105
+0%
|
| Cyberpunk 2077 | 91
+0%
|
91
+0%
|
| Dota 2 | 125
+0%
|
125
+0%
|
| Far Cry 5 | 110−120
+0%
|
110−120
+0%
|
| Forza Horizon 4 | 223
+0%
|
223
+0%
|
| Forza Horizon 5 | 118
+0%
|
118
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+0%
|
210−220
+0%
|
| Valorant | 237
+0%
|
237
+0%
|
1440p
High Preset
| Dota 2 | 98
+0%
|
98
+0%
|
| Grand Theft Auto V | 95
+0%
|
95
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Red Dead Redemption 2 | 63
+0%
|
63
+0%
|
| World of Tanks | 350−400
+0%
|
350−400
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 85−90
+0%
|
85−90
+0%
|
| Counter-Strike 2 | 68
+0%
|
68
+0%
|
| Cyberpunk 2077 | 58
+0%
|
58
+0%
|
| Far Cry 5 | 160−170
+0%
|
160−170
+0%
|
| Forza Horizon 4 | 166
+0%
|
166
+0%
|
| Forza Horizon 5 | 98
+0%
|
98
+0%
|
| Metro Exodus | 101
+0%
|
101
+0%
|
| The Witcher 3: Wild Hunt | 110−120
+0%
|
110−120
+0%
|
| Valorant | 208
+0%
|
208
+0%
|
4K
High Preset
| Counter-Strike 2 | 43
+0%
|
43
+0%
|
| Dota 2 | 117
+0%
|
117
+0%
|
| Grand Theft Auto V | 115
+0%
|
115
+0%
|
| Metro Exodus | 49
+0%
|
49
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 200−210
+0%
|
200−210
+0%
|
| Red Dead Redemption 2 | 43
+0%
|
43
+0%
|
| The Witcher 3: Wild Hunt | 117
+0%
|
117
+0%
|
4K
Ultra Preset
| Battlefield 5 | 70−75
+0%
|
70−75
+0%
|
| Counter-Strike 2 | 65−70
+0%
|
65−70
+0%
|
| Cyberpunk 2077 | 28
+0%
|
28
+0%
|
| Dota 2 | 125
+0%
|
125
+0%
|
| Far Cry 5 | 100−110
+0%
|
100−110
+0%
|
| Fortnite | 95−100
+0%
|
95−100
+0%
|
| Forza Horizon 4 | 98
+0%
|
98
+0%
|
| Forza Horizon 5 | 57
+0%
|
57
+0%
|
| Valorant | 116
+0%
|
116
+0%
|
This is how GTX 650 Ti and RTX 3070 compete in popular games:
- RTX 3070 is 838% faster in 1080p
- RTX 3070 is 880% faster in 1440p
- RTX 3070 is 814% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 6.57 | 58.07 |
| Recency | 9 October 2012 | 1 September 2020 |
| Maximum RAM amount | 2 GB | 8 GB |
| Chip lithography | 28 nm | 8 nm |
| Power consumption (TDP) | 110 Watt | 220 Watt |
GTX 650 Ti has 100% lower power consumption.
RTX 3070, on the other hand, has a 783.9% higher aggregate performance score, an age advantage of 7 years, a 300% higher maximum VRAM amount, and a 250% more advanced lithography process.
The GeForce RTX 3070 is our recommended choice as it beats the GeForce GTX 650 Ti in performance tests.
Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
