AMD Radeon RX 7800 XT vs NVIDIA GeForce RTX 5090 SE Comparison
AMD Radeon RX 7800 XT
GeForce RTX 5090 SE
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 7800 XT vs NVIDIA GeForce RTX 5090 SE
AMD Radeon RX 7800 XT vs NVIDIA GeForce RTX 5090 SE
The AMD Radeon RX 7800 XT and the NVIDIA GeForce RTX 5090 SE occupy very different positions in the current graphics card landscape. The RX 7800 XT is an established product from the Radeon RX 7000 series, built on the RDNA 3.0 architecture, while the RTX 5090 SE is a newly released entry from the GeForce 50-series, utilizing the Blackwell 2.0 architecture. The database shows that the RX 7800 XT has an average benchmark score of 11627, placing it in the 51st percentile among all GPUs. The RTX 5090 SE currently has no recorded benchmark scores in the database, with an average of zero and a 50th percentile ranking. This difference in available data makes a direct comparison of measured performance impossible, but the specification sheets and architectural details provide a clear picture of what each card delivers.
Where Each One Wins
The RX 7800 XT wins in the category of established, measurable performance. The database contains ten benchmark results for this card, covering a range of tests from 3DMark Steel Nomad DX12 to PassMark’s DirectX 9, 10, 11, and 12 suites, along with Geekbench OpenCL and Vulkan tests. Its strongest recorded result is in Geekbench Vulkan with a score of 54228, while its PassMark G3D score reaches 24176. The card also delivers a PassMark GPU Compute score of 13473 and a Geekbench OpenCL score of 18290. These numbers indicate that the RX 7800 XT has a broad, tested performance profile across both gaming and compute workloads.
The RTX 5090 SE, by contrast, has no recorded benchmark entries. The database lists no scores for any test, meaning its performance cannot be quantified from direct measurements. However, the card’s specifications suggest it wins in raw hardware capacity. It features 14080 shading units compared to the RX 7800 XT’s 3840, 440 texture mapping units versus 240, and 160 render output units versus 96. The RTX 5090 SE also includes 440 tensor cores and 110 ray tracing cores, while the RX 7800 XT has 60 ray tracing cores and no tensor cores listed. In terms of compute throughput, the RTX 5090 SE reaches 66.94 TFLOPS for FP32 and FP16, nearly double the RX 7800 XT’s 37.32 TFLOPS for both precision formats. These figures indicate that the RTX 5090 SE is built for significantly higher peak workloads, even without confirmed benchmark data.
FAQ
Q: Which card has a higher average benchmark score?
A: The AMD Radeon RX 7800 XT has an average benchmark score of 11627, while the NVIDIA GeForce RTX 5090 SE has an average benchmark score of 0 because no benchmarks have been recorded for it.
Q: How do the memory configurations differ?
A: The RX 7800 XT has 16 GB of GDDR6 memory on a 256-bit bus with 624.1 GB/s bandwidth. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth.
Q: What is the difference in power consumption?
A: The RX 7800 XT has a TDP of 263 W and requires a 600 W suggested power supply. The RTX 5090 SE has a TDP of 500 W and requires a 900 W suggested power supply.
Q: Which card uses more advanced ray tracing hardware?
A: The RTX 5090 SE has 110 ray tracing cores, while the RX 7800 XT has 60. The RTX 5090 SE also includes 440 tensor cores, which the RX 7800 XT does not list.
Q: What is the difference in release timing?
A: The RX 7800 XT was released on 2023-09-05, while the RTX 5090 SE has a release date of 2025-12-31.
Q: Which card has a smaller physical footprint?
A: Both cards share the same length of 267 mm and height of 111 mm, but the RX 7800 XT is 50 mm wide while the RTX 5090 SE is 40 mm wide.
Head-to-Head Benchmarks
The database shows no head-to-head benchmark results between these two cards, and the RTX 5090 SE has zero recorded scores in any test. This means there are no direct numerical comparisons available for 3DMark, Geekbench, or PassMark runs. The only benchmark-related data for the RX 7800 XT comes from its individual test scores: 4157 in 3DMark Steel Nomad DX12, 18290 in Geekbench OpenCL, 54228 in Geekbench Vulkan, and 24176 in PassMark G3D. These results establish a baseline for the RX 7800 XT’s measured performance.
For the RTX 5090 SE, the lack of benchmark scores means the database cannot provide any wins or losses in direct tests. The wins counter shows 0 for both cards, reflecting the absence of head-to-head data. The closest comparison comes from the RX 7800 XT’s nearest rivals in the database, which include the NVIDIA GeForce GTX 1660 with an average score of 11680 (0.5% ahead), the AMD Radeon Pro 5500M at 11528 (0.9% behind), the NVIDIA Tesla K20c at 11479 (1.3% behind), and the AMD Radeon RX 6500 XT at 11842 (1.8% ahead). These rivals are all lower-tier cards, and the RX 7800 XT sits near the 51st percentile overall. The RTX 5090 SE has no rival data to compare against.
Specification Differences
The two cards differ across nearly every major specification. The RX 7800 XT uses a Navi 32 chip with 28,100 million transistors on a 346 mm² die, while the RTX 5090 SE uses a GB202 chip with 92,200 million transistors on a 750 mm² die. Transistor density also differs, with the RX 7800 XT at 81.2 million transistors per square millimeter and the RTX 5090 SE at 122.9 million per square millimeter. Clock speeds show the RTX 5090 SE with a higher base clock of 1740 MHz versus 1295 MHz, but a slightly lower boost clock of 2377 MHz versus 2430 MHz. The RX 7800 XT has a game clock of 2124 MHz, which the RTX 5090 SE does not list.
Memory specifications diverge sharply. The RX 7800 XT has 16 GB of GDDR6 at 2438 MHz with 19.5 Gbps effective speed, while the RTX 5090 SE has 24 GB of GDDR7 at 1750 MHz with 28 Gbps effective speed. Bandwidth jumps from 624.1 GB/s on the RX 7800 XT to 1.34 TB/s on the RTX 5090 SE. Bus width increases from 256 bits to 384 bits. The power connectors differ as well, with the RX 7800 XT using two 8-pin connectors and the RTX 5090 SE using a single 16-pin connector. The bus interface changes from PCIe 4.0 x16 to PCIe 5.0 x16. Display outputs are similar but not identical, with the RX 7800 XT offering 1x HDMI 2.1a and 3x DisplayPort 2.1, while the RTX 5090 SE offers 1x HDMI 2.1b and 3x DisplayPort 2.1b. Dimensions are shared in length and height, but the RX 7800 XT is 50 mm wide versus 40 mm for the RTX 5090 SE.
Architecture Differences
The RX 7800 XT is built on RDNA 3.0 with a codename of Wheat Nas, part of the Navi III generation. The RTX 5090 SE uses Blackwell 2.0 with no codename listed, part of the GeForce 50 generation. The process node is the same at 5 nm from TSMC, but the chip designs are entirely different. The RX 7800 XT has 3840 shading units, 240 TMUs, 96 ROPs, and 60 ray tracing cores. The RTX 5090 SE has 14080 shading units, 440 TMUs, 160 ROPs, 110 ray tracing cores, and 440 tensor cores. The tensor core count is a notable addition, indicating the RTX 5090 SE supports AI-accelerated features that the RX 7800 XT does not list.
Pixel and texture rates reflect the raw throughput differences. The RX 7800 XT achieves 233.3 GPixel/s and 583.2 GTexel/s, while the RTX 5090 SE achieves 380.3 GPixel/s and 1,045.9 GTexel/s. FP32 and FP16 compute are both listed as 1:1 ratios for each card, but the absolute values differ: 37.32 TFLOPS for the RX 7800 XT versus 66.94 TFLOPS for the RTX 5090 SE. The API support is identical, with both cards supporting DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The production status for both is Active, and the RTX 5090 SE lists its predecessor as GeForce 40 and successor as GeForce 60, while the RX 7800 XT lists its predecessor as Navi II and successor as Navi IV.
The Verdict
The data shows that the RX 7800 XT is a fully measured product with a concrete performance profile, while the RTX 5090 SE is a specification-heavy card without any recorded benchmark results. For users who rely on tested performance, the RX 7800 XT offers verified scores across multiple test suites, with its Geekbench Vulkan score of 54228 and PassMark G3D score of 24176 being the standout results. The card’s 51st percentile ranking among all GPUs, combined with its nearest rivals being lower-tier models like the GTX 1660 and RX 6500 XT, suggests it delivers solid mid-range performance.
For users who prioritize raw hardware capacity, the RTX 5090 SE presents a larger feature set on paper. Its 24 GB of GDDR7 memory, 1.34 TB/s bandwidth, 14080 shading units, and 440 tensor cores indicate a card designed for high-end workloads, but the absence of benchmark scores means its real-world performance remains unverified. The RTX 5090 SE’s higher TDP of 500 W and larger transistor count of 92,200 million point to a more power-hungry and complex design, but without measured data, the card cannot be ranked against any competitor in the database. The choice between these two cards depends on whether the user values confirmed results or untested specifications, as the database currently provides no direct comparison to settle the question.