GeForce FX 5950 Ultra vs GTX 660M
Aggregate performance score
We've compared GeForce GTX 660M with GeForce FX 5950 Ultra, including specs and performance data.
GTX 660M outperforms FX 5950 Ultra by a whopping 2413% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 716 | 1428 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 5.18 | 0.14 |
| Architecture | Kepler (2012−2018) | Rankine (2003−2005) |
| GPU code name | GK107 | NV38 |
| Market segment | Laptop | Desktop |
| Release date | 22 March 2012 (12 years ago) | 23 October 2003 (21 year ago) |
| Launch price (MSRP) | no data | $499 |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
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 | 384 | no data |
| Core clock speed | 835 MHz | 475 MHz |
| Boost clock speed | 950 MHz | no data |
| Number of transistors | 1,270 million | 135 million |
| Manufacturing process technology | 28 nm | 130 nm |
| Power consumption (TDP) | 50 Watt | 74 Watt |
| Texture fill rate | 30.40 | 3.800 |
| Floating-point processing power | 0.7296 TFLOPS | no data |
| ROPs | 16 | 4 |
| TMUs | 32 | 8 |
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 | no data |
| Bus support | PCI Express 2.0, PCI Express 3.0 | no data |
| Interface | MXM-B (3.0) | AGP 8x |
| Length | no data | 229 mm |
| Width | no data | 2-slot |
| Supplementary power connectors | no data | 1x Molex |
| SLI options | + | - |
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 | DDR |
| Maximum RAM amount | 1 GB | 256 MB |
| Memory bus width | 128bit | 256 Bit |
| Memory clock speed | 2000 MHz | 475 MHz |
| Memory bandwidth | 64.0 GB/s | 30.4 GB/s |
| Shared memory | - | no data |
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 | 1x DVI, 1x VGA, 1x S-Video |
| HDMI | + | - |
| HDCP | + | - |
| Maximum VGA resolution | Up to 2048x1536 | no data |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| Optimus | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 9.0a |
| Shader Model | 5.1 | no data |
| OpenGL | 4.5 | 2.1 |
| OpenCL | 1.1 | N/A |
| Vulkan | 1.1.126 | N/A |
| 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.
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 | 30
+2900%
| 1−2
−2900%
|
| Full HD | 35
+3400%
| 1−2
−3400%
|
| 1200p | 38
+3700%
| 1−2
−3700%
|
Cost per frame, $
| 1080p | no data | 499.00 |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 9−10 | 0−1 |
| Counter-Strike 2 | 10−11 | 0−1 |
| Cyberpunk 2077 | 7−8 | 0−1 |
Full HD
Medium Preset
| Atomic Heart | 9−10 | 0−1 |
| Battlefield 5 | 12−14 | 0−1 |
| Counter-Strike 2 | 10−11 | 0−1 |
| Cyberpunk 2077 | 7−8 | 0−1 |
| Far Cry 5 | 8−9 | 0−1 |
| Fortnite | 20−22 | 0−1 |
| Forza Horizon 4 | 16−18 | 0−1 |
| Forza Horizon 5 | 7−8 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 14−16 | 0−1 |
| Valorant | 50−55
+2450%
|
2−3
−2450%
|
Full HD
High Preset
| Atomic Heart | 9−10 | 0−1 |
| Battlefield 5 | 12−14 | 0−1 |
| Counter-Strike 2 | 10−11 | 0−1 |
| Counter-Strike: Global Offensive | 89
+2867%
|
3−4
−2867%
|
| Cyberpunk 2077 | 7−8 | 0−1 |
| Dota 2 | 30−35
+3200%
|
1−2
−3200%
|
| Far Cry 5 | 8−9 | 0−1 |
| Fortnite | 20−22 | 0−1 |
| Forza Horizon 4 | 16−18 | 0−1 |
| Forza Horizon 5 | 7−8 | 0−1 |
| Grand Theft Auto V | 10−12 | 0−1 |
| Metro Exodus | 6−7 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 14−16 | 0−1 |
| The Witcher 3: Wild Hunt | 10−11 | 0−1 |
| Valorant | 50−55
+2450%
|
2−3
−2450%
|
Full HD
Ultra Preset
| Battlefield 5 | 12−14 | 0−1 |
| Counter-Strike 2 | 10−11 | 0−1 |
| Cyberpunk 2077 | 7−8 | 0−1 |
| Dota 2 | 30−35
+3200%
|
1−2
−3200%
|
| Far Cry 5 | 8−9 | 0−1 |
| Forza Horizon 4 | 16−18 | 0−1 |
| Forza Horizon 5 | 7−8 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 14−16 | 0−1 |
| The Witcher 3: Wild Hunt | 10−11 | 0−1 |
| Valorant | 50−55
+2450%
|
2−3
−2450%
|
Full HD
Epic Preset
| Fortnite | 20−22 | 0−1 |
1440p
High Preset
| Counter-Strike 2 | 5−6 | 0−1 |
| Counter-Strike: Global Offensive | 27−30
+2600%
|
1−2
−2600%
|
| Grand Theft Auto V | 3−4 | 0−1 |
| Metro Exodus | 2−3 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
+2500%
|
1−2
−2500%
|
| Valorant | 35−40
+3600%
|
1−2
−3600%
|
1440p
Ultra Preset
| Cyberpunk 2077 | 3−4 | 0−1 |
| Far Cry 5 | 6−7 | 0−1 |
| Forza Horizon 4 | 8−9 | 0−1 |
| Forza Horizon 5 | 4−5 | 0−1 |
| The Witcher 3: Wild Hunt | 6−7 | 0−1 |
1440p
Epic Preset
| Fortnite | 7−8 | 0−1 |
4K
High Preset
| Atomic Heart | 3−4 | 0−1 |
| Grand Theft Auto V | 16−18 | 0−1 |
| Valorant | 18−20 | 0−1 |
4K
Ultra Preset
| Cyberpunk 2077 | 1−2 | 0−1 |
| Dota 2 | 10−12 | 0−1 |
| Far Cry 5 | 4−5 | 0−1 |
| Forza Horizon 4 | 4−5 | 0−1 |
| Forza Horizon 5 | 1−2 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 4−5 | 0−1 |
4K
Epic Preset
| Fortnite | 4−5 | 0−1 |
This is how GTX 660M and FX 5950 Ultra compete in popular games:
- GTX 660M is 2900% faster in 900p
- GTX 660M is 3400% faster in 1080p
- GTX 660M is 3700% faster in 1200p
Pros & cons summary
| Performance score | 3.77 | 0.15 |
| Recency | 22 March 2012 | 23 October 2003 |
| Maximum RAM amount | 1 GB | 256 MB |
| Chip lithography | 28 nm | 130 nm |
| Power consumption (TDP) | 50 Watt | 74 Watt |
GTX 660M has a 2413.3% higher aggregate performance score, an age advantage of 8 years, a 300% higher maximum VRAM amount, a 364.3% more advanced lithography process, and 48% lower power consumption.
The GeForce GTX 660M is our recommended choice as it beats the GeForce FX 5950 Ultra in performance tests.
Be aware that GeForce GTX 660M is a notebook card while GeForce FX 5950 Ultra is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
