GeForce GT 650M vs Radeon Pro 450
Aggregate performance score
We've compared Radeon Pro 450 with GeForce GT 650M, including specs and performance data.
Pro 450 outperforms GT 650M by a whopping 125% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 561 | 766 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 13.87 | 4.78 |
| Architecture | GCN 4.0 (2016−2020) | Kepler (2012−2018) |
| GPU code name | Baffin | GK107 |
| Market segment | Mobile workstation | Laptop |
| Release date | 30 October 2016 (8 years ago) | 22 March 2012 (12 years ago) |
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 | 640 | 384 |
| Core clock speed | 800 MHz | Up to 900 MHz |
| Boost clock speed | no data | 950 MHz |
| Number of transistors | 3,000 million | 1,270 million |
| Manufacturing process technology | 14 nm | 28 nm |
| Power consumption (TDP) | 35 Watt | 45 Watt |
| Texture fill rate | 32.00 | 30.40 |
| Floating-point processing power | 1.024 TFLOPS | 0.7296 TFLOPS |
| ROPs | 16 | 16 |
| TMUs | 40 | 32 |
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).
| Laptop size | large | medium sized |
| Bus support | no data | PCI Express 2.0, PCI Express 3.0 |
| Interface | PCIe 3.0 x8 | PCIe 3.0 x16 |
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 | DDR3\GDDR5 |
| Maximum RAM amount | 2 GB | 2 GB |
| Memory bus width | 128 Bit | 128bit |
| Memory clock speed | 1270 MHz | 900 MHz |
| Memory bandwidth | 81.28 GB/s | Up to 80.0 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 | No outputs |
| HDMI | - | + |
| HDCP | - | + |
| Maximum VGA resolution | no data | Up to 2048x1536 |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| FreeSync | + | - |
| 3D Blu-Ray | - | + |
| Optimus | - | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_0) | 12 API |
| Shader Model | 6.4 | 5.1 |
| OpenGL | 4.6 | 4.5 |
| OpenCL | 2.0 | 1.1 |
| Vulkan | 1.2.131 | 1.1.126 |
| CUDA | - | + |
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 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:
| 900p | 65−70
+110%
| 31
−110%
|
| Full HD | 28
−14.3%
| 32
+14.3%
|
| 4K | 19
+138%
| 8−9
−138%
|
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 16−18
+129%
|
7−8
−129%
|
| Counter-Strike 2 | 12−14
+44.4%
|
9−10
−44.4%
|
| Cyberpunk 2077 | 12−14
+117%
|
6−7
−117%
|
Full HD
Medium Preset
| Atomic Heart | 16−18
+129%
|
7−8
−129%
|
| Battlefield 5 | 27−30
+190%
|
10−11
−190%
|
| Counter-Strike 2 | 12−14
+44.4%
|
9−10
−44.4%
|
| Cyberpunk 2077 | 12−14
+117%
|
6−7
−117%
|
| Far Cry 5 | 21−24
+250%
|
6−7
−250%
|
| Fortnite | 40−45
+167%
|
14−16
−167%
|
| Forza Horizon 4 | 30−33
+114%
|
14−16
−114%
|
| Forza Horizon 5 | 16−18
+220%
|
5−6
−220%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
+84.6%
|
12−14
−84.6%
|
| Valorant | 70−75
+58.7%
|
45−50
−58.7%
|
Full HD
High Preset
| Atomic Heart | 16−18
+129%
|
7−8
−129%
|
| Battlefield 5 | 27−30
+190%
|
10−11
−190%
|
| Counter-Strike 2 | 12−14
+44.4%
|
9−10
−44.4%
|
| Counter-Strike: Global Offensive | 100−110
+50%
|
72
−50%
|
| Cyberpunk 2077 | 12−14
+117%
|
6−7
−117%
|
| Dota 2 | 50−55
+79.3%
|
27−30
−79.3%
|
| Far Cry 5 | 21−24
+250%
|
6−7
−250%
|
| Fortnite | 40−45
+167%
|
14−16
−167%
|
| Forza Horizon 4 | 30−33
+114%
|
14−16
−114%
|
| Forza Horizon 5 | 16−18
+220%
|
5−6
−220%
|
| Grand Theft Auto V | 24−27
+200%
|
8−9
−200%
|
| Metro Exodus | 12−14
+160%
|
5−6
−160%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
+84.6%
|
12−14
−84.6%
|
| The Witcher 3: Wild Hunt | 20
+122%
|
9−10
−122%
|
| Valorant | 70−75
+58.7%
|
45−50
−58.7%
|
Full HD
Ultra Preset
| Battlefield 5 | 27−30
+190%
|
10−11
−190%
|
| Counter-Strike 2 | 12−14
+44.4%
|
9−10
−44.4%
|
| Cyberpunk 2077 | 12−14
+117%
|
6−7
−117%
|
| Dota 2 | 67
+131%
|
27−30
−131%
|
| Far Cry 5 | 21−24
+250%
|
6−7
−250%
|
| Forza Horizon 4 | 30−33
+114%
|
14−16
−114%
|
| Forza Horizon 5 | 16−18
+220%
|
5−6
−220%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
+84.6%
|
12−14
−84.6%
|
| The Witcher 3: Wild Hunt | 18−20
+100%
|
9−10
−100%
|
| Valorant | 70−75
+58.7%
|
45−50
−58.7%
|
Full HD
Epic Preset
| Fortnite | 40−45
+167%
|
14−16
−167%
|
1440p
High Preset
| Counter-Strike: Global Offensive | 50−55
+132%
|
21−24
−132%
|
| Grand Theft Auto V | 8−9
+300%
|
2−3
−300%
|
| Metro Exodus | 6−7
+500%
|
1−2
−500%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
+77.3%
|
21−24
−77.3%
|
| Valorant | 75−80
+159%
|
27−30
−159%
|
1440p
Ultra Preset
| Battlefield 5 | 12−14
+140%
|
5−6
−140%
|
| Counter-Strike 2 | 8−9
+167%
|
3−4
−167%
|
| Cyberpunk 2077 | 5−6
+150%
|
2−3
−150%
|
| Far Cry 5 | 12−14
+160%
|
5−6
−160%
|
| Forza Horizon 4 | 16−18
+129%
|
7−8
−129%
|
| Forza Horizon 5 | 10−12
+267%
|
3−4
−267%
|
| The Witcher 3: Wild Hunt | 10−11
+100%
|
5−6
−100%
|
1440p
Epic Preset
| Fortnite | 12−14
+160%
|
5−6
−160%
|
4K
High Preset
| Atomic Heart | 5−6
+150%
|
2−3
−150%
|
| Counter-Strike 2 | 1−2 | 0−1 |
| Grand Theft Auto V | 18−20
+12.5%
|
16−18
−12.5%
|
| Metro Exodus | 1−2 | 0−1 |
| The Witcher 3: Wild Hunt | 5−6
+150%
|
2−3
−150%
|
| Valorant | 30−35
+127%
|
14−16
−127%
|
4K
Ultra Preset
| Battlefield 5 | 6−7
+200%
|
2−3
−200%
|
| Counter-Strike 2 | 1−2 | 0−1 |
| Cyberpunk 2077 | 2−3
+100%
|
1−2
−100%
|
| Dota 2 | 24−27
+200%
|
8−9
−200%
|
| Far Cry 5 | 7−8
+133%
|
3−4
−133%
|
| Forza Horizon 4 | 10−11
+400%
|
2−3
−400%
|
| Forza Horizon 5 | 4−5
+300%
|
1−2
−300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 6−7
+50%
|
4−5
−50%
|
4K
Epic Preset
| Fortnite | 6−7
+50%
|
4−5
−50%
|
1440p
High Preset
| Counter-Strike 2 | 4−5
+0%
|
4−5
+0%
|
This is how Pro 450 and GT 650M compete in popular games:
- Pro 450 is 110% faster in 900p
- GT 650M is 14% faster in 1080p
- Pro 450 is 138% faster in 4K
Here's the range of performance differences observed across popular games:
- in Metro Exodus, with 1440p resolution and the High Preset, the Pro 450 is 500% faster.
All in all, in popular games:
- Pro 450 is ahead in 60 tests (98%)
- there's a draw in 1 test (2%)
Pros & cons summary
| Performance score | 7.08 | 3.14 |
| Recency | 30 October 2016 | 22 March 2012 |
| Chip lithography | 14 nm | 28 nm |
| Power consumption (TDP) | 35 Watt | 45 Watt |
Pro 450 has a 125.5% higher aggregate performance score, an age advantage of 4 years, a 100% more advanced lithography process, and 28.6% lower power consumption.
The Radeon Pro 450 is our recommended choice as it beats the GeForce GT 650M in performance tests.
Be aware that Radeon Pro 450 is a mobile workstation card while GeForce GT 650M is a mobile workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
