AMD Radeon RX 7900 GRE vs NVIDIA GeForce RTX 5090 SE Comparison

AMD Radeon RX 7900 GRE and NVIDIA GeForce RTX 5090 SE occupy very different positions in the current GPU landscape. The RX 7900 GRE, released in July 2023, has a substantial set of recorded benchmark data, while the RTX 5090 SE, dated for late 2025, has no benchmark scores in the database, resulting in an average score of zero. This makes direct numerical comparison impossible for most tests, but the available specification data and the RX 7900 GRE's measured performance against its nearest rivals provide a clear picture of where each card stands.

Head-to-Head Benchmarks

The database currently holds no shared benchmark results for the AMD Radeon RX 7900 GRE and the NVIDIA GeForce RTX 5090 SE. The RTX 5090 SE has an empty benchmark array, meaning there are no recorded scores for any test, including 3DMark, Geekbench, or Passmark. Consequently, there are no direct wins for either card to report. The RX 7900 GRE, however, has ten recorded benchmark scores, which establish its performance baseline. Its average benchmark score is 32456, placing it in the 77th percentile of all GPUs. The RTX 5090 SE, with no scores, sits at the 50th percentile by default, a value that reflects the absence of data rather than actual performance parity.

For the RX 7900 GRE, the strongest result comes from Geekbench OpenCL, where it scores 175758 points. In Vulkan, it scores 99850. In Passmark tests, the card delivers a G3D score of 27089, a GPU compute score of 15016, and a G2D score of 1180. The lower-level DirectX tests show scores of 300 for DirectX 11, 310 for DirectX 9, 139 for DirectX 10, and 107 for DirectX 12. In 3DMark Steel Nomad (DX12), the RX 7900 GRE achieves a score of 4814. Without any RTX 5090 SE scores, the data cannot indicate which card wins in any specific workload; the only conclusion is that the RX 7900 GRE has measurable performance, while the RTX 5090 SE does not yet have recorded results.

The nearest rivals for the RX 7900 GRE, based on average benchmark scores, are all AMD cards. The AMD FirePro S10000 has an average score of 32388, which is 0.2% lower than the RX 7900 GRE. The AMD FirePro S9300 X2 scores 32540, which is 0.3% higher. The AMD Radeon RX 590 GME scores 32601, 0.4% higher, and the AMD Radeon Pro 570X scores 32176, 0.9% lower. These deltas are minimal, indicating that the RX 7900 GRE sits in a tightly clustered performance band. The RTX 5090 SE has no nearest rivals listed, so no such comparison is possible for it.

Where Each One Wins

Based on the recorded data, the AMD Radeon RX 7900 GRE demonstrates wins in every benchmark where it has a score, simply because the NVIDIA GeForce RTX 5090 SE has no recorded scores to challenge them. The RX 7900 GRE's highest margin appears in compute-oriented workloads, as its Geekbench OpenCL score of 175758 far exceeds its Vulkan score of 99850, suggesting a strong compute throughput relative to graphics-specific APIs. In Passmark, the G3D score of 27089 is nearly double the GPU compute score of 15016, indicating that the card's rasterization performance is stronger than its compute performance in that suite.

The RTX 5090 SE, lacking any benchmark entries, cannot be credited with wins in any category. However, the specification data suggests areas where it would likely dominate, though these are not measured results. For instance, the RTX 5090 SE has 14080 shading units versus 5120 on the RX 7900 GRE, and its FP32 throughput is 66.94 TFLOPS versus 45.98 TFLOPS. These numbers indicate a theoretical advantage in raw compute, but the database contains no scores to confirm real-world performance. Similarly, the RTX 5090 SE's memory bandwidth of 1.34 TB/s is more than double the RX 7900 GRE's 576.0 GB/s, yet no benchmark verifies the impact.

The RX 7900 GRE's wins are also contextualized by its percentile ranking. At the 77th percentile, it outperforms 77% of all GPUs in the database. The RTX 5090 SE's 50th percentile is a placeholder, not a performance metric. In practical terms, the RX 7900 GRE wins in any test where a score exists, and the RTX 5090 SE wins in no test because no test has been recorded for it.

Architecture Differences

The two GPUs are built on different architectures from different generations. The AMD Radeon RX 7900 GRE uses the RDNA 3.0 architecture on the Navi 31 chip, with the codename Plum Bonito. It belongs to the Navi III generation (RX 7000 series). The NVIDIA GeForce RTX 5090 SE uses the Blackwell 2.0 architecture on the GB202 chip, with no codename listed, and belongs to the GeForce 50 generation.

Both are manufactured by TSMC on a 5 nm process node, but the physical designs diverge sharply. The RX 7900 GRE has 57,700 million transistors on a 529 mm² die, yielding a transistor density of 109.1M per mm². The RTX 5090 SE has 92,200 million transistors on a 750 mm² die, with a density of 122.9M per mm². The RTX 5090 SE is physically larger and denser, which aligns with its higher shading unit count of 14080 versus 5120 on the RX 7900 GRE.

Memory architecture differs significantly. The RX 7900 GRE uses 16 GB of GDDR6 on a 256-bit bus, with a bandwidth of 576.0 GB/s. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus, with a bandwidth of 1.34 TB/s. The RTX 5090 SE also has more texture mapping units (440 versus 320) and more ray tracing cores (110 versus 80). The RX 7900 GRE has no tensor cores listed, while the RTX 5090 SE has 440 tensor cores. Both have 160 ROPs.

Clock behavior differs as well. The RX 7900 GRE has a base clock of 1287 MHz, a boost clock of 2245 MHz, and a game clock of 1880 MHz. The RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz, with no game clock listed. The memory clocks also differ: the RX 7900 GRE runs at 2250 MHz (18 Gbps effective), while the RTX 5090 SE runs at 1750 MHz (28 Gbps effective). The FP16 throughput reveals a design split: the RX 7900 GRE achieves 91.96 TFLOPS at a 2:1 ratio, while the RTX 5090 SE achieves 66.94 TFLOPS at a 1:1 ratio.

FAQ

Q: Which card has a higher average benchmark score?

A: The AMD Radeon RX 7900 GRE has an average benchmark score of 32456, while the NVIDIA GeForce RTX 5090 SE has an average score of 0 because it has no recorded benchmarks.

Q: How does the RX 7900 GRE compare to its nearest rival, the AMD FirePro S10000?

A: The RX 7900 GRE's average score of 32456 is 0.2% higher than the FirePro S10000's 32388.

Q: What is the memory bandwidth difference between the two cards?

A: The RX 7900 GRE has a memory bandwidth of 576.0 GB/s, while the RTX 5090 SE has a bandwidth of 1.34 TB/s.

Q: Does the RTX 5090 SE have tensor cores?

A: Yes, the RTX 5090 SE has 440 tensor cores, while the RX 7900 GRE has no tensor cores listed.

Q: What is the transistor count on each chip?

A: The RX 7900 GRE has 57,700 million transistors, and the RTX 5090 SE has 92,200 million transistors.

Q: Which card has a higher boost clock?

A: The RTX 5090 SE has a boost clock of 2377 MHz, which is higher than the RX 7900 GRE's boost clock of 2245 MHz.

Specification Differences

The two cards differ in nearly every major specification category. The RX 7900 GRE uses the Navi 31 chip with RDNA 3.0 architecture, while the RTX 5090 SE uses the GB202 chip with Blackwell 2.0 architecture. The die size is 529 mm² for the RX 7900 GRE and 750 mm² for the RTX 5090 SE. Transistor counts are 57,700 million and 92,200 million, respectively, with densities of 109.1M per mm² and 122.9M per mm².

Base clocks are 1287 MHz for the RX 7900 GRE and 1740 MHz for the RTX 5090 SE. Boost clocks are 2245 MHz and 2377 MHz, respectively. The RX 7900 GRE has a game clock of 1880 MHz, a feature absent on the RTX 5090 SE. Memory size differs: 16 GB GDDR6 versus 24 GB GDDR7. Bus width is 256-bit versus 384-bit, and bandwidth is 576.0 GB/s versus 1.34 TB/s.

Shading units are 5120 versus 14080. TMUs are 320 versus 440. ROPs are identical at 160. Ray tracing cores are 80 versus 110. Tensor cores are absent on the RX 7900 GRE and present at 440 on the RTX 5090 SE. Pixel rate is 359.2 GPixel/s versus 380.3 GPixel/s. Texture rate is 718.4 GTexel/s versus 1,045.9 GTexel/s. FP32 performance is 45.98 TFLOPS versus 66.94 TFLOPS. FP16 performance is 91.96 TFLOPS (2:1) versus 66.94 TFLOPS (1:1).

Power and connectivity differ as well. TDP is 260 W for the RX 7900 GRE and 500 W for the RTX 5090 SE. The RX 7900 GRE uses 2x 8-pin power connectors and suggests a 600 W PSU, while the RTX 5090 SE uses 1x 16-pin and suggests a 900 W PSU. The bus interface is PCIe 4.0 x16 versus PCIe 5.0 x16. Display outputs are 1x HDMI 2.1a, 2x DisplayPort 2.1, and 1x USB Type-C for the RX 7900 GRE, versus 1x HDMI 2.1b and 3x DisplayPort 2.1b for the RTX 5090 SE. Dimensions also vary: the RX 7900 GRE is 276 mm long, 110 mm high, and 51 mm wide, while the RTX 5090 SE is 267 mm long, 111 mm high, and 40 mm wide. Release dates are July 2023 for the RX 7900 GRE and December 2025 for the RTX 5090 SE.