AMD Radeon 780M vs NVIDIA GeForce RTX 5090 SE Comparison

Where Each One Wins

The benchmark data splits these two GPUs into entirely different performance classes, and the recorded measurements make that division unambiguous. The AMD Radeon 780M, an integrated graphics processor from the Phoenix generation, holds a percentile rank of 61 among all GPUs in the database, placing it just above the midpoint of the field. Its average benchmark score across the three recorded tests stands at 17,588 points. The NVIDIA GeForce RTX 5090 SE, by contrast, has no recorded benchmark scores in the database at this time, and its percentile rank sits at 50 with an average score of zero. This means the RTX 5090 SE cannot currently claim any head-to-head wins in the database, because no direct comparative measurements exist for it.

The AMD Radeon 780M wins in every category where data has been captured. Its 3DMark Steel Nomad DX12 score reaches 480 points, its Geekbench OpenCL result is 18,602 points, and its Geekbench Vulkan result is 33,683 points. These three measurements form the entirety of the comparative record. The RTX 5090 SE has no entries in the benchmark database, so the use-case split is necessarily lopsided: the 780M is the only one of the two with measurable performance data, and it wins by default across every recorded test. The practical interpretation is straightforward. The 780M serves as a low-power integrated solution that can handle lightweight 3D workloads and compute tasks at modest performance levels. The RTX 5090 SE, based on its specifications alone, targets a completely different performance tier, but without benchmark numbers, the database cannot confirm how it performs in practice.

Architecture Differences

The architectural gap between these two parts is enormous, and the specifications in the database quantify that gap precisely. The AMD Radeon 780M uses the Phoenix chip with RDNA 3.0 architecture, manufactured on a 4 nm process at TSMC. It packs 25,390 million transistors into a 178 mm² die, which yields a transistor density of 142.6 million transistors per square millimeter. The NVIDIA GeForce RTX 5090 SE uses the GB202 chip with Blackwell 2.0 architecture, also built at TSMC but on a 5 nm process. It contains 92,200 million transistors across a 750 mm² die, giving a transistor density of 122.9 million per square millimeter. The RTX 5090 SE has more than triple the transistor count of the 780M, and its die is more than four times larger.

The compute resources diverge even more sharply. The 780M has 768 shading units, 48 texture mapping units, 32 raster output units, and 12 ray tracing cores. The RTX 5090 SE has 14,080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. That is roughly 18 times more shading units, 9 times more TMUs, 5 times more ROPs, and over 9 times more ray tracing cores. The RTX 5090 SE also adds a tensor core array that the 780M lacks entirely. Clock behavior differs as well: the 780M runs a base clock of 800 MHz and boosts to 2900 MHz, while the RTX 5090 SE has a higher base of 1740 MHz and a boost of 2377 MHz. The 780M actually boosts higher than the RTX 5090 SE, but the massive difference in execution resources makes the clock advantage irrelevant.

Memory architecture is fundamentally different. The 780M uses system shared memory, with a system-dependent bus width, system-dependent bandwidth, and no dedicated VRAM. The RTX 5090 SE carries 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s of bandwidth, and its memory clock runs at 1750 MHz with 28 Gbps effective transfer rate. The 780M has no dedicated memory clock in the database; its memory bandwidth is listed as system dependent. Power delivery separates the two as well. The 780M has a TDP of 15 W, uses no power connectors, and is an integrated graphics processor with a slot width listed as IGP. The RTX 5090 SE has a TDP of 500 W, requires a single 16-pin power connector, and a suggested power supply of 900 W. It occupies a dual-slot design and measures 267 mm in length, 111 mm in height, and 40 mm in width. The 780M has no listed dimensions because it is integrated onto the motherboard.

The bus interface also differs. The 780M connects through PCIe 4.0 x8, while the RTX 5090 SE uses PCIe 5.0 x16. Display outputs on the 780M are motherboard dependent, whereas the RTX 5090 SE provides one HDMI 2.1b port and three DisplayPort 2.1b outputs. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so the API feature set is identical on paper. The production status for both is listed as active. The 780M released on January 30, 2024, and the RTX 5090 SE has a release date of December 31, 2025. The 780M lists its predecessor as Navi II IGP and successor as Navi III IGP. The RTX 5090 SE lists GeForce 40 as its predecessor and GeForce 60 as its successor.

Head-to-Head Benchmarks

The database contains three benchmark entries for the AMD Radeon 780M and zero for the NVIDIA GeForce RTX 5090 SE. The head-to-head benchmark array is empty, and the win counters show zero wins for both parts. This means there are no direct comparative measurements to walk through. The only way to assess the RTX 5090 SE is through its listed specifications, which cannot be verified against actual test results.

The 780M's recorded scores provide the full picture of what the database knows about either GPU's real-world performance. In 3DMark Steel Nomad DX12, it scores 480 points. In Geekbench OpenCL, it scores 18,602 points. In Geekbench Vulkan, it scores 33,683 points. These results place the 780M near a cluster of comparable GPUs in the database. Its nearest rivals by average score include the AMD Radeon Pro 560 at 17,551 points with a delta of 0.2 percent, the NVIDIA GeForce RTX 4060 at 17,639 points with a delta of negative 0.3 percent, the AMD Radeon HD 7790 at 17,666 points with a delta of negative 0.4 percent, and the AMD Radeon Pro 460 at 17,509 points with a delta of 0.5 percent. The 780M sits within half a percent of all four rivals, which indicates its average score is tightly grouped with that range of GPUs. The 780M's average benchmark score of 17,588 points is slightly below the RTX 4060's average by 0.3 percent, essentially a statistical tie. Against the Radeon Pro 560 and Radeon Pro 460, the 780M is marginally ahead by 0.2 and 0.5 percent respectively. Against the HD 7790, it trails by 0.4 percent.

The RTX 5090 SE has no such comparative data. Its nearest rivals list is empty, its benchmark array is empty, and its average score is zero. The database cannot confirm any performance claims for this GPU. The specification sheet suggests extremely high throughput, with 66.94 TFLOPS of FP32 performance and 66.94 TFLOPS of FP16 performance, both at a 1:1 ratio. The 780M delivers 8.909 TFLOPS in both FP32 and FP16, also at a 1:1 ratio. The RTX 5090 SE's listed FP32 figure is roughly 7.5 times higher than the 780M's. Pixel rate for the RTX 5090 SE is listed at 380.3 GPixel/s versus 92.80 GPixel/s for the 780M, a ratio of about 4.1. Texture rate is 1,045.9 GTexel/s versus 139.2 GTexel/s, a ratio of about 7.5. These specification gaps are large, but they are not benchmark results, and the database treats them as unverified.

The Verdict

The data in the database supports one clear conclusion: the AMD Radeon 780M is the only one of these two GPUs with measurable performance records, and every recorded benchmark belongs to it. The NVIDIA GeForce RTX 5090 SE has no benchmark scores, no nearest rivals, and no head-to-head results, so the database cannot assign it any verified wins. Any selection between these two parts must therefore rely on what each one is designed to do, based on the recorded specifications.

The 780M is an integrated graphics processor with a 15 W TDP, no power connectors, and system shared memory. It is built for low-power systems where discrete graphics is not an option. Its benchmark results confirm that it can run lightweight 3D workloads and general compute tasks at a level comparable to the AMD Radeon Pro 560, the NVIDIA GeForce RTX 4060, the AMD Radeon HD 7790, and the AMD Radeon Pro 460, all within a half percent of its average score. The RTX 5090 SE is a dual-slot discrete card with a 500 W TDP, a 900 W suggested power supply, 24 GB of GDDR7 memory, and a 384-bit memory bus. It requires a 16-pin power connector and a PCIe 5.0 x16 slot. Its specification sheet indicates an entirely different performance class, but the database has no measurements to confirm it. The verdict from the recorded data is that the 780M is the verified performer, while the RTX 5090 SE remains an unverified specification sheet. For systems that need an integrated solution with confirmed benchmark results, the 780M is the choice. For systems that require a high-end discrete card with dedicated memory and a massive compute array, the RTX 5090 SE is the only option that matches those requirements, but its performance is not yet recorded.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 780M has an average benchmark score of 17,588 points. The NVIDIA GeForce RTX 5090 SE has an average benchmark score of zero because no benchmark results are recorded for it.

Q: How does the 780M compare to its nearest rivals?

A: The 780M is within 0.5 percent of all four nearest rivals. It is 0.2 percent ahead of the AMD Radeon Pro 560, 0.5 percent ahead of the AMD Radeon Pro 460, 0.3 percent behind the NVIDIA GeForce RTX 4060, and 0.4 percent behind the AMD Radeon HD 7790.

Q: What memory configurations do the two GPUs use?

A: The 780M uses system shared memory with system-dependent bus width and bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth.

Q: What are the power requirements for each GPU?

A: The 780M has a TDP of 15 W and uses no power connectors. The RTX 5090 SE has a TDP of 500 W, uses one 16-pin power connector, and has a suggested power supply of 900 W.

Q: What is the transistor count difference between the two?

A: The 780M contains 25,390 million transistors on a 178 mm² die. The RTX 5090 SE contains 92,200 million transistors on a 750 mm² die.

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Specification Differences

| Specification | AMD Radeon 780M | NVIDIA GeForce RTX 5090 SE |

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

| Architecture | RDNA 3.0 | Blackwell 2.0 |

| Process node | 4 nm | 5 nm |

| Transistors | 25,390 million | 92,200 million |

| Die size | 178 mm² | 750 mm² |

| Transistor density | 142.6M / mm² | 122.9M / mm² |

| Base clock | 800 MHz | 1740 MHz |

| Boost clock | 2900 MHz | 2377 MHz |

| Memory size | System Shared | 24 GB |

| Memory type | System Shared | GDDR7 |

| Memory bus width | System Shared | 384 bit |

| Memory bandwidth | System Dependent | 1.34 TB/s |

| Shading units | 768 | 14,080 |

| TMUs | 48 | 440 |

| ROPs | 32 | 160 |

| Ray tracing cores | 12 | 110 |

| Tensor cores | None | 440 |

| Pixel rate | 92.80 GPixel/s | 380.3 GPixel/s |

| Texture rate | 139.2 GTexel/s | 1,045.9 GTexel/s |

| FP32 performance | 8.909 TFLOPS | 66.94 TFLOPS |

| FP16 performance | 8.909 TFLOPS | 66.94 TFLOPS |

| TDP | 15 W | 500 W |

| Slot width | IGP | Dual-slot |

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

| Suggested PSU | None | 900 W |

| Bus interface | PCIe 4.0 x8 | PCIe 5.0 x16 |

| Display outputs | Motherboard Dependent | 1x HDMI 2.1b, 3x DisplayPort 2.1b |

| Launch MSRP | None | 1,499 USD |

| Release date | 2024-01-30 | 2025-12-31 |