Radeon 680M vs GeForce GTX 470M
Aggregate performance score
We've compared GeForce GTX 470M and Radeon 680M, covering specs and all relevant benchmarks.
680M outperforms 470M by an impressive 90% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 694 | 529 |
| Place by popularity | not in top-100 | 74 |
| Power efficiency | 4.79 | 13.69 |
| Architecture | Fermi (2010−2014) | RDNA 2.0 (2020−2025) |
| GPU code name | GF104 | Rembrandt+ |
| Market segment | Laptop | Laptop |
| Release date | 3 September 2010 (15 years ago) | 3 January 2023 (3 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 | 288 | 768 |
| Core clock speed | 535 MHz | 2000 MHz |
| Boost clock speed | no data | 2200 MHz |
| Number of transistors | 1,950 million | 13,100 million |
| Manufacturing process technology | 40 nm | 6 nm |
| Power consumption (TDP) | 75 Watt | 50 Watt |
| Texture fill rate | 25.68 | 105.6 |
| Floating-point processing power | 0.6163 TFLOPS | 3.379 TFLOPS |
| ROPs | 24 | 32 |
| TMUs | 48 | 48 |
| Ray Tracing Cores | no data | 12 |
| L0 Cache | no data | 192 KB |
| L1 Cache | 384 KB | 256 KB |
| L2 Cache | 384 KB | 2 MB |
| L3 Cache | no data | 8 MB |
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 |
| Interface | MXM-B (3.0) | PCIe 4.0 x8 |
| Supplementary power connectors | None | None |
| 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 | System Shared |
| Maximum RAM amount | 1536 MB | System Shared |
| Memory bus width | 192 Bit | System Shared |
| Memory clock speed | 1250 MHz | System Shared |
| Memory bandwidth | 60.0 GB/s | no data |
| Shared memory | - | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | No outputs | Portable Device Dependent |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 API | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.7 |
| OpenGL | 4.5 | 4.6 |
| OpenCL | 1.1 | 2.0 |
| Vulkan | N/A | 1.3 |
| CUDA | + | - |
Synthetic benchmarks
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.
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 | 34
−76.5%
| 60−65
+76.5%
|
| Full HD | 50
+35.1%
| 37
−35.1%
|
| 1440p | 8−9
−113%
| 17
+113%
|
| 4K | 5−6
−100%
| 10
+100%
|
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 21−24
−129%
|
45−50
+129%
|
| Cyberpunk 2077 | 10−11
−280%
|
38
+280%
|
| Resident Evil 4 Remake | 7−8
−357%
|
32
+357%
|
Full HD
Medium
| Battlefield 5 | 18−20
−111%
|
40−45
+111%
|
| Counter-Strike 2 | 21−24
−129%
|
45−50
+129%
|
| Cyberpunk 2077 | 10−11
−180%
|
28
+180%
|
| Far Cry 5 | 14−16
−171%
|
38
+171%
|
| Fortnite | 27−30
−92.9%
|
50−55
+92.9%
|
| Forza Horizon 4 | 21−24
−77.3%
|
35−40
+77.3%
|
| Forza Horizon 5 | 12−14
−300%
|
52
+300%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−68.4%
|
30−35
+68.4%
|
| Valorant | 60−65
−48.3%
|
85−90
+48.3%
|
Full HD
High
| Battlefield 5 | 18−20
−111%
|
40−45
+111%
|
| Counter-Strike 2 | 21−24
−129%
|
45−50
+129%
|
| Counter-Strike: Global Offensive | 80−85
−68.3%
|
130−140
+68.3%
|
| Cyberpunk 2077 | 10−11
−110%
|
21
+110%
|
| Dota 2 | 40−45
−73.2%
|
71
+73.2%
|
| Far Cry 5 | 14−16
−150%
|
35
+150%
|
| Fortnite | 27−30
−92.9%
|
50−55
+92.9%
|
| Forza Horizon 4 | 21−24
−77.3%
|
35−40
+77.3%
|
| Forza Horizon 5 | 12−14
−254%
|
46
+254%
|
| Grand Theft Auto V | 14−16
−140%
|
36
+140%
|
| Metro Exodus | 9−10
−156%
|
23
+156%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−68.4%
|
30−35
+68.4%
|
| The Witcher 3: Wild Hunt | 12−14
−208%
|
40
+208%
|
| Valorant | 60−65
−48.3%
|
85−90
+48.3%
|
Full HD
Ultra
| Battlefield 5 | 18−20
−111%
|
40−45
+111%
|
| Cyberpunk 2077 | 10−11
−80%
|
18
+80%
|
| Dota 2 | 40−45
−48.8%
|
61
+48.8%
|
| Far Cry 5 | 14−16
−136%
|
33
+136%
|
| Forza Horizon 4 | 21−24
−77.3%
|
35−40
+77.3%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
−68.4%
|
30−35
+68.4%
|
| The Witcher 3: Wild Hunt | 12−14
−84.6%
|
24
+84.6%
|
| Valorant | 60−65
−143%
|
146
+143%
|
Full HD
Epic
| Fortnite | 27−30
−92.9%
|
50−55
+92.9%
|
1440p
High
| Counter-Strike 2 | 9−10
−88.9%
|
16−18
+88.9%
|
| Counter-Strike: Global Offensive | 35−40
−91.7%
|
65−70
+91.7%
|
| Grand Theft Auto V | 3−4
−467%
|
17
+467%
|
| Metro Exodus | 3−4
−233%
|
10−11
+233%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
−34.3%
|
45−50
+34.3%
|
| Valorant | 50−55
−96.1%
|
100−105
+96.1%
|
1440p
Ultra
| Battlefield 5 | 4−5
−425%
|
21−24
+425%
|
| Cyberpunk 2077 | 3−4
−233%
|
10
+233%
|
| Far Cry 5 | 9−10
−133%
|
21
+133%
|
| Forza Horizon 4 | 10−12
−90.9%
|
21−24
+90.9%
|
| The Witcher 3: Wild Hunt | 7−8
−143%
|
17
+143%
|
1440p
Epic
| Fortnite | 9−10
−111%
|
18−20
+111%
|
4K
High
| Grand Theft Auto V | 16−18
−25%
|
20−22
+25%
|
| The Witcher 3: Wild Hunt | 1−2
−1200%
|
13
+1200%
|
| Valorant | 21−24
−104%
|
45−50
+104%
|
4K
Ultra
| Battlefield 5 | 1−2
−900%
|
10−11
+900%
|
| Cyberpunk 2077 | 1−2
−300%
|
4
+300%
|
| Dota 2 | 16−18
−12.5%
|
18
+12.5%
|
| Far Cry 5 | 4−5
−125%
|
9−10
+125%
|
| Forza Horizon 4 | 6−7
−150%
|
14−16
+150%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 5−6
−80%
|
9−10
+80%
|
4K
Epic
| Fortnite | 5−6
−80%
|
9−10
+80%
|
4K
High
| Counter-Strike 2 | 3−4
+0%
|
3−4
+0%
|
| Metro Exodus | 4−5
+0%
|
4−5
+0%
|
4K
Ultra
| Counter-Strike 2 | 3−4
+0%
|
3−4
+0%
|
This is how GTX 470M and Radeon 680M compete in popular games:
- Radeon 680M is 76% faster in 900p
- GTX 470M is 35% faster in 1080p
- Radeon 680M is 113% faster in 1440p
- Radeon 680M is 100% faster in 4K
Here's the range of performance differences observed across popular games:
- in The Witcher 3: Wild Hunt, with 4K resolution and the High Preset, the Radeon 680M is 1200% faster.
All in all, in popular games:
- Radeon 680M performs better in 57 tests (95%)
- there's a draw in 3 tests (5%)
Pros & cons summary
| Performance score | 4.67 | 8.89 |
| Recency | 3 September 2010 | 3 January 2023 |
| Chip lithography | 40 nm | 6 nm |
| Power consumption (TDP) | 75 Watt | 50 Watt |
Radeon 680M has a 90% higher aggregate performance score, an age advantage of 12 years, a 567% more advanced lithography process, and 50% lower power consumption.
The Radeon 680M is our recommended choice as it beats the GeForce GTX 470M 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.
