AMD Radeon RX 7600 XT vs NVIDIA GeForce RTX 5090 D V2 Comparison

The AMD Radeon RX 7600 XT and the NVIDIA GeForce RTX 5090 D V2 occupy opposite ends of the performance spectrum, but the benchmark data reveals a far more nuanced picture than the raw specs suggest. The RTX 5090 D V2 leads in the single shared DirectX 12 test by a massive margin, yet the RX 7600 XT holds a higher percentile ranking among all GPUs and a significantly higher average benchmark score across multiple tests. This means the choice hinges entirely on what you are measuring: the RX 7600 XT offers consistent, well-rounded performance across a broad suite of legacy and compute workloads, while the RTX 5090 D V2 is a specialized powerhouse for modern, high-fidelity DirectX 12 scenarios. The data does not support a universal winner; it supports two distinct buyers with different priorities.

The Verdict

For the builder targeting current-generation AAA gaming at high resolutions with ray tracing enabled, the NVIDIA GeForce RTX 5090 D V2 is the clear pick. Its 3DMark Steel Nomad DX12 score of 16,504 crushes the AMD’s 2,348, a delta of -85.8% in NVIDIA’s favor. This is not a marginal lead; it is a generational gap that suggests the NVIDIA card is in a different performance class for modern DirectX 12 workloads. The RTX 5090 D V2’s 24 GB of GDDR7 memory on a 384-bit bus, delivering 1.34 TB/s bandwidth, provides the headroom needed for 4K texture packs and future titles.

Conversely, the AMD Radeon RX 7600 XT is the pick for the builder who needs a versatile card that performs admirably across older APIs, compute tasks, and general 3D acceleration. Its average benchmark score of 17,083 across ten different tests—including PassMark DirectX 9, 10, 11, and OpenCL—demonstrates broad compatibility and consistent output. Its percentile ranking of 60 places it ahead of the RTX 5090 D V2’s 59th percentile, meaning that in the aggregate of all GPU performance data, the AMD card sits in a better overall position relative to the entire market. The RTX 5090 D V2’s score is based on a single test, making its 59th percentile a less reliable indicator of general capability.

Where Each One Wins

The data shows a clean split: the RTX 5090 D V2 wins the modern API battle outright. In the only head-to-head benchmark available, 3DMark Steel Nomad DX12, it achieves a score of 16,504 against the RX 7600 XT’s 2,348. This test is the definitive measure of contemporary DirectX 12 performance, and the NVIDIA card’s 85.8% lead indicates it is optimized for the features and draw calls used in current game engines. If your workload is exclusively modern titles with ray tracing and high polygon counts, this is the card that wins.

The RX 7600 XT wins the versatility battle. It has a score in every major synthetic benchmark category: 92,426 in Geekbench OpenCL, 48,366 in Geekbench Vulkan, and a suite of PassMark scores ranging from 65 in DirectX 12 to 228 in DirectX 9. It also posts a PassMark G3D score of 17,132 and a G2D score of 1,030. The RTX 5090 D V2 has no data for these tests, meaning the AMD card is the only one of the two with proven performance in legacy DirectX, OpenCL compute, and 2D acceleration. For a mixed-use system that handles older games, productivity apps, and compute tasks, the RX 7600 XT is the safer, data-backed choice.

Architecture Differences

The two cards are built on fundamentally different architectures from different generations. The AMD Radeon RX 7600 XT uses the Navi 33 chip based on RDNA 3.0 architecture, codenamed “Hotpink Bonefish,” and belongs to the Navi III (RX 7000) generation. It is fabricated on a 6 nm process at TSMC with 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2M per mm². Its compute layout includes 2,048 shading units, 128 texture mapping units (TMUs), 64 raster operation units (ROPs), and 32 ray tracing cores. It has no dedicated tensor cores. The memory subsystem uses 16 GB of GDDR6 on a 128-bit bus, achieving 288.0 GB/s bandwidth. The card operates at a base clock of 1980 MHz, a boost clock of 2755 MHz, and a game clock of 2470 MHz, with memory running at 2250 MHz (18 Gbps effective).

The NVIDIA GeForce RTX 5090 D V2 uses the GB202 chip based on Blackwell 2.0 architecture from the GeForce 50 generation. It is fabricated on a 5 nm process at TSMC with 92,200 million transistors on a 750 mm² die, yielding a transistor density of 122.9M per mm². This is a significantly larger and denser chip. Its compute layout is dramatically different: 21,760 shading units, 680 TMUs, 176 ROPs, 170 ray tracing cores, and 680 tensor cores. The memory subsystem uses 24 GB of GDDR7 on a 384-bit bus, achieving 1.34 TB/s bandwidth. The base clock is 2017 MHz and the boost clock is 2407 MHz, with memory at 1750 MHz (28 Gbps effective). The NVIDIA card also supports PCIe 5.0 x16, while the AMD card uses PCIe 4.0 x8. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon RX 7600 XT has an average benchmark score of 17,083 across ten tests, while the NVIDIA GeForce RTX 5090 D V2 has an average of 16,504 based on a single test.

Q: How do their percentile rankings compare?

A: The RX 7600 XT ranks in the 60th percentile of all GPUs, while the RTX 5090 D V2 ranks in the 59th percentile. The AMD card is slightly better positioned relative to the entire GPU market.

Q: Which card has more memory and bandwidth?

A: The RTX 5090 D V2 has 24 GB of GDDR7 memory with 1.34 TB/s bandwidth on a 384-bit bus. The RX 7600 XT has 16 GB of GDDR6 memory with 288.0 GB/s bandwidth on a 128-bit bus.

Q: What are the power connector and PSU requirements?

A: The RX 7600 XT uses a single 8-pin connector with a 450 W suggested PSU. The RTX 5090 D V2 uses a single 16-pin connector with a 950 W suggested PSU.

Q: Which card has more ray tracing cores?

A: The RTX 5090 D V2 has 170 ray tracing cores, while the RX 7600 XT has 32 ray tracing cores. The NVIDIA card also has 680 tensor cores, which the AMD card lacks entirely.

Q: Are there any benchmark tests where the AMD card wins?

A: In the head-to-head benchmark data, the AMD card wins zero tests. The NVIDIA card wins the single 3DMark Steel Nomad DX12 test. However, the AMD card has scores in ten different benchmarks, while the NVIDIA card only has data for one.

Head-to-Head Benchmarks

The only direct comparison available is the 3DMark Steel Nomad DX12 test, and the result is decisive. The NVIDIA GeForce RTX 5090 D V2 scores 16,504, while the AMD Radeon RX 7600 XT scores 2,348. The delta percentage of -85.8% means the AMD card is nearly 86% slower in this specific workload. This is the single biggest win in the dataset, and it dwarfs any other comparison. The RTX 5090 D V2’s massive lead here is attributable to its 21,760 shading units versus 2,048, its 170 ray tracing cores versus 32, and its 1.34 TB/s memory bandwidth versus 288.0 GB/s. The NVIDIA card’s 104.8 TFLOPS FP32 performance is nearly five times the AMD card’s 22.57 TFLOPS.

The RX 7600 XT, however, has no equivalent head-to-head win because the NVIDIA card lacks data in every other benchmark. In the broader context, the AMD card’s PassMark G3D score of 17,132 and Geekbench OpenCL score of 92,426 suggest it would be competitive in compute-heavy tasks, but the absence of NVIDIA scores in those tests prevents a direct numerical comparison. The data shows that the RTX 5090 D V2 is a specialized instrument for modern DirectX 12 gaming, while the RX 7600 XT is a generalist with proven results across a wider range of software.

Specification Differences

The two cards differ in nearly every measurable specification. The process node is 6 nm for AMD and 5 nm for NVIDIA, both from TSMC. The transistor count is 13,300 million for AMD versus 92,200 million for NVIDIA, with die sizes of 204 mm² and 750 mm² respectively, giving transistor densities of 65.2M/mm² and 122.9M/mm². The shading units are 2,048 for AMD and 21,760 for NVIDIA. TMUs are 128 versus 680, and ROPs are 64 versus 176. Ray tracing cores are 32 versus 170, and the NVIDIA card has 680 tensor cores while the AMD card has none. Memory is 16 GB GDDR6 on a 128-bit bus for AMD versus 24 GB GDDR7 on a 384-bit bus for NVIDIA, with bandwidth of 288.0 GB/s versus 1.34 TB/s. Clocks differ: AMD has a base of 1980 MHz and boost of 2755 MHz with a game clock of 2470 MHz, while NVIDIA has a base of 2017 MHz and boost of 2407 MHz with no game clock listed. Memory clocks are 2250 MHz (18 Gbps) for AMD versus 1750 MHz (28 Gbps) for NVIDIA. Pixel rate is 176.3 GPixel/s versus 423.6 GPixel/s, and texture rate is 352.6 GTexel/s versus 1,636.8 GTexel/s. FP32 performance is 22.57 TFLOPS versus 104.8 TFLOPS. TDP is 190 W versus 575 W. The power connector is 1x 8-pin versus 1x 16-pin, with suggested PSUs of 450 W versus 950 W. Bus interface is PCIe 4.0 x8 versus PCIe 5.0 x16. Dimensions are 204 mm x 115 mm for AMD versus 304 mm x 137 mm x 48 mm for NVIDIA. Display outputs are 1x HDMI 2.1a and 3x DisplayPort 2.1 for AMD versus 1x HDMI 2.1b and 3x DisplayPort 2.1b for NVIDIA.