NVIDIA GeForce GT 720M vs NVIDIA GeForce RTX 5080 SUPER Comparison

# NVIDIA GeForce RTX 5080 SUPER vs NVIDIA GeForce GT 720M

The NVIDIA GeForce RTX 5080 SUPER and the NVIDIA GeForce GT 720M occupy opposite extremes of the GPU spectrum, separated by over a decade of architectural evolution and a massive gulf in performance. The RTX 5080 SUPER is a current-generation Blackwell 2.0 flagship-class part, while the GT 720M is an end-of-life Kepler 2.0 mobile chip from the GeForce 700M generation. Direct head-to-head benchmark comparisons are unavailable, but the data from their respective benchmark suites and performance percentiles tells a clear story of generational dominance.

Head-to-Head Benchmarks

The two GPUs were tested under different benchmark methodologies, making a direct apples-to-apples comparison impossible from the available data. The RTX 5080 SUPER was evaluated using 3DMark Steel Nomad DX12, scoring 3075 points, while the GT 720M was tested with Geekbench OpenCL, scoring 2605 points. These are distinct workloads with different scoring scales, so the raw numbers cannot be directly compared as if they were equivalent measurements.

What the data does reveal is the relative standing of each GPU within the broader GPU landscape. The RTX 5080 SUPER sits in the 19th percentile of all GPUs, meaning approximately 81% of all GPUs in the database rank below it. Its nearest rivals include the NVIDIA Quadro P1000, which scores 3163 (2.8% higher), and the Intel Arc Pro B60, which scores 3182 (3.4% higher). On the other side, the NVIDIA GeForce 820A scores 2983 (3.1% lower) and the NVIDIA GeForce GTX 860M scores 2967 (3.6% lower). This clustering suggests the RTX 5080 SUPER is positioned in a competitive mid-to-high performance tier, with its closest competitors trading blows within a narrow band of roughly ±3.6%.

The GT 720M, by contrast, sits in the 17th percentile of all GPUs, placing it even lower in the overall distribution. Its nearest rivals show a similar pattern of tight clustering: the NVIDIA GeForce GT 440 scores 2645 (1.5% higher), the Intel Arc Pro B50 scores 2660 (2.1% higher), and the NVIDIA GeForce GT 1030 scores 2662 (2.1% higher). The NVIDIA Quadro K2000M scores 2555, which is 2% lower than the GT 720M. This places the GT 720M in a very low-performance tier, consistent with its role as an entry-level mobile graphics solution from 2013.

Interpreting the percentiles is instructive. A 2-percentile-point gap between the two GPUs may seem modest, but the underlying performance difference is enormous when considering the architectural and specification gaps. The RTX 5080 SUPER delivers 56.28 TFLOPS of FP32 compute, while the GT 720M delivers 291.1 GFLOPS—a difference of roughly 193 times. Similarly, the pixel rate of the RTX 5080 SUPER is 293.1 GPixel/s versus 3.032 GPixel/s for the GT 720M, a factor of nearly 97. These are the real head-to-head numbers, even if no single benchmark directly compares them.

Architecture Differences

The architectural divide between these two GPUs spans four generations of NVIDIA design. The RTX 5080 SUPER is built on the Blackwell 2.0 architecture using the GB203 chip, fabricated on a 5 nm process at TSMC. The GT 720M uses the Kepler 2.0 architecture with the GK208 chip, manufactured on a 28 nm process, also at TSMC. The process node difference alone represents a massive reduction in feature size, enabling far greater transistor density.

The transistor counts tell the story of integration scale. The RTX 5080 SUPER contains 45,600 million transistors on a 378 mm² die, yielding a transistor density of 120.6 million per square millimeter. The GT 720M contains 1,020 million transistors on an 87 mm² die, with a density of 11.7 million per square millimeter. The RTX 5080 SUPER packs roughly 45 times more transistors and does so at more than 10 times the density.

The memory subsystems are equally divergent. The RTX 5080 SUPER features 24 GB of GDDR7 memory on a 256-bit bus, delivering 1.02 TB/s of bandwidth. The GT 720M has 2 GB of DDR3 memory on a 64-bit bus, with 12.80 GB/s of bandwidth. The bandwidth difference is approximately 80-fold, which has profound implications for texture-heavy workloads and high-resolution rendering.

Compute resources differ by orders of magnitude. The RTX 5080 SUPER has 10,752 shading units, 336 texture mapping units, and 112 raster output units. The GT 720M has 192 shading units, 16 TMUs, and 8 ROPs. The RTX 5080 SUPER also includes 84 ray tracing cores and 336 tensor cores, features entirely absent from the GT 720M, which has no RT or tensor core support. This reflects the fundamental architectural shift toward ray tracing and AI-accelerated workloads in modern GPUs.

The clock speeds also reflect the process advantage. The RTX 5080 SUPER runs at a base clock of 2295 MHz with a boost clock of 2617 MHz, while the GT 720M runs at 719 MHz base and 758 MHz boost. The RTX 5080 SUPER's memory runs at 2000 MHz with 32 Gbps effective data rate, versus the GT 720M's 800 MHz with 1600 Mbps effective. The power envelopes are correspondingly different: the RTX 5080 SUPER has a TDP of 415 W and requires a 16-pin power connector, while the GT 720M has a 33 W TDP and draws power from the MXM module without any external connector.

FAQ

Q: Which GPU has a higher benchmark percentile rank?

A: The RTX 5080 SUPER ranks in the 19th percentile of all GPUs, while the GT 720M ranks in the 17th percentile. The RTX 5080 SUPER is positioned higher in the overall performance distribution.

Q: What is the difference in FP32 compute performance?

A: The RTX 5080 SUPER delivers 56.28 TFLOPS of FP32 compute, whereas the GT 720M delivers 291.1 GFLOPS. The RTX 5080 SUPER is approximately 193 times faster in raw floating-point throughput.

Q: Does the GT 720M support ray tracing or tensor cores?

A: No. The GT 720M has no ray tracing cores and no tensor cores. The RTX 5080 SUPER includes 84 ray tracing cores and 336 tensor cores, enabling hardware-accelerated ray tracing and AI workloads.

Q: How do the memory bandwidths compare?

A: The RTX 5080 SUPER provides 1.02 TB/s of memory bandwidth from 24 GB of GDDR7 on a 256-bit bus. The GT 720M provides 12.80 GB/s from 2 GB of DDR3 on a 64-bit bus, a bandwidth difference of roughly 80 times.

Q: What are the production statuses of these GPUs?

A: The RTX 5080 SUPER is listed as "Active" in production, while the GT 720M is "End-of-life." The GT 720M also has a predecessor (GeForce 600M) and successor (GeForce 800M), whereas the RTX 5080 SUPER has no listed predecessor or successor.

Q: What is the process node difference?

A: The RTX 5080 SUPER is fabricated on a 5 nm process, while the GT 720M uses a 28 nm process. Both are manufactured at TSMC, but the 5 nm node enables significantly higher transistor density and efficiency.

Specification Differences

| Specification | NVIDIA GeForce RTX 5080 SUPER | NVIDIA GeForce GT 720M |

|---|---|---|

| Architecture | Blackwell 2.0 | Kepler 2.0 |

| Chip | GB203 | GK208 |

| Process Node | 5 nm | 28 nm |

| Transistors | 45,600 million | 1,020 million |

| Die Size | 378 mm² | 87 mm² |

| Transistor Density | 120.6M / mm² | 11.7M / mm² |

| Base Clock | 2295 MHz | 719 MHz |

| Boost Clock | 2617 MHz | 758 MHz |

| Memory Clock | 2000 MHz / 32 Gbps effective | 800 MHz / 1600 Mbps effective |

| Memory Size | 24 GB | 2 GB |

| Memory Type | GDDR7 | DDR3 |

| Memory Bus Width | 256 bit | 64 bit |

| Memory Bandwidth | 1.02 TB/s | 12.80 GB/s |

| Shading Units | 10752 | 192 |

| TMUs | 336 | 16 |

| ROPs | 112 | 8 |

| RT Cores | 84 | None |

| Tensor Cores | 336 | None |

| Pixel Rate | 293.1 GPixel/s | 3.032 GPixel/s |

| Texture Rate | 879.3 GTexel/s | 12.13 GTexel/s |

| FP32 Performance | 56.28 TFLOPS | 291.1 GFLOPS |

| FP16 Performance | 56.28 TFLOPS (1:1) | None |

| TDP | 415 W | 33 W |

| Slot Width | Dual-slot | MXM Module |

| Power Connectors | 1x 16-pin | None |

| Bus Interface | PCIe 5.0 x16 | PCIe 2.0 x8 |

| Display Outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b | Portable Device Dependent |

| DirectX Support | 12 Ultimate (12_2) | 12 (11_0) |

| Vulkan Support | 1.4 | 1.2.175 |

| Production Status | Active | End-of-life |

| Release Date | 2025-12-31 | 2013-12-24 |

| Launch MSRP | 999 USD | None |

The Verdict

The RTX 5080 SUPER is the clear choice for any modern workload requiring high-performance rendering, ray tracing, or AI acceleration. Its 24 GB of GDDR7 memory and 1.02 TB/s bandwidth make it suitable for large datasets and high-resolution textures. The inclusion of 84 ray tracing cores and 336 tensor cores positions it for current-generation gaming and compute applications that leverage these features. Its 19th percentile ranking, while not top-tier, indicates strong performance relative to the broader GPU landscape, with nearest rivals within a narrow 3.6% band.

The GT 720M is a legacy part, end-of-life since its 2013 release. Its 2 GB of DDR3 memory and 12.80 GB/s bandwidth are severely limiting by modern standards. The lack of RT and tensor cores means it cannot handle ray-traced or AI-accelerated workloads. Its 17th percentile ranking places it near the bottom of the performance distribution, with nearest rivals clustered within a 2.1% band. The GT 720M is only relevant for legacy systems or basic display output tasks.

From the data, the RTX 5080 SUPER is the only viable option for any serious computational or gaming use case. The GT 720M should be considered only for historical reference or extremely low-power, low-performance embedded applications. The generational leap in every measurable specification—from transistor count to memory bandwidth to compute throughput—makes this comparison a foregone conclusion. The RTX 5080 SUPER is a modern powerhouse; the GT 720M is a relic of a bygone era.