AMD Radeon RX 9070 GRE vs NVIDIA GeForce RTX 5090 D Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between the NVIDIA GeForce RTX 5090 D and the AMD Radeon RX 9070 GRE. In the two shared benchmark tests, the RTX 5090 D wins both outright, with margins that are not close.

In 3DMark Steel Nomad DX12, the RTX 5090 D scores 14,326 points against the RX 9070 GRE's 5,424 points. That is a 164.1% advantage for the NVIDIA card. This test stresses modern DirectX 12 workloads, and the result indicates that the RTX 5090 D delivers roughly two and a half times the rasterization performance of the AMD part in this specific scenario.

The Geekbench OpenCL test shows an even larger gap. The RTX 5090 D records 310,674 points, while the RX 9070 GRE manages 109,309 points. The delta here is 184.2%, meaning the NVIDIA card is nearly three times faster in this compute-oriented workload. OpenCL performance often reflects general compute throughput, and the raw numbers align with the massive difference in shading units and memory bandwidth between the two cards.

Looking at the average benchmark scores in the database, the RTX 5090 D sits at 77,712 across all recorded tests, while the RX 9070 GRE averages 57,367. That places the NVIDIA card 35.5% higher on average, though this figure includes tests that were not run on both cards. The head-to-head results are the cleaner comparison, and they show a dominant NVIDIA victory in every shared test.

The percentile rankings also tell a story. The RTX 5090 D sits at the 92nd percentile among all GPUs in the database, while the RX 9070 GRE sits at the 87th percentile. Both are high-performing cards, but the RTX 5090 D is in a different tier. Its nearest rivals in the database include the AMD Radeon RX 6850M XT at 78,940 average score (1.6% higher) and the NVIDIA Tesla P100 PCIe 16 GB at 79,605 average score (2.4% higher). The RX 9070 GRE's nearest rivals are much closer in performance: the Intel Arc A580 at 57,756 average score (0.7% higher), the AMD Radeon RX 5600 OEM at 58,085 (1.2% higher), and the AMD Radeon RX 6950 XT at 58,392 (1.8% higher). This suggests the RX 9070 GRE competes in a crowded mid-range segment, while the RTX 5090 D sits near the top of the entire database.

Architecture Differences

The two cards come from fundamentally different design philosophies. The RTX 5090 D uses NVIDIA's Blackwell 2.0 architecture on the GB202 chip, built on a 5 nm process at TSMC. The RX 9070 GRE uses AMD's RDNA 4.0 architecture on the Navi 48 chip, built on a 4 nm process, also at TSMC. The process node difference is small, but the chip scale is not.

The GB202 die measures 750 mm² and contains 92,200 million transistors, giving a transistor density of 122.9 million per mm². The Navi 48 die is 357 mm² with 53,900 million transistors, for a density of 151.0 million per mm². The RTX 5090 D has a much larger physical die with more transistors, though the RX 9070 GRE packs its transistors more densely. The NVIDIA chip has 21,760 shading units, 680 texture mapping units, and 176 ROPs. The AMD chip has 3,072 shading units, 192 TMUs, and 96 ROPs. That is a 7x difference in shader count and a 3.5x difference in TMUs.

Ray tracing hardware also differs sharply. The RTX 5090 D has 170 RT cores, while the RX 9070 GRE has 48. The NVIDIA card also includes 680 tensor cores, which the AMD card lacks entirely. Memory configurations are equally divergent. The RTX 5090 D ships with 32 GB of GDDR7 on a 512-bit bus, yielding 1.79 TB/s of bandwidth. The RX 9070 GRE has 12 GB of GDDR6 on a 192-bit bus, for 432.0 GB/s. The bandwidth gap is roughly 4.1x in favor of NVIDIA.

Clock behavior is interesting. The RX 9070 GRE has a lower base clock at 1,420 MHz but boosts to 2,790 MHz, with a game clock of 2,220 MHz. The RTX 5090 D has a higher base clock at 2,017 MHz but a lower boost clock at 2,407 MHz. Despite the AMD card's higher boost frequency, the NVIDIA card still achieves far higher throughput due to its massive hardware resource advantage. The RTX 5090 D reaches 104.8 TFLOPS FP32 and FP16, while the RX 9070 GRE reaches 34.28 TFLOPS in both. The pixel rate is 423.6 GPixel/s versus 267.8 GPixel/s, and the texture rate is 1,636.8 GTexel/s versus 535.7 GTexel/s.

Power delivery tells a different story. The RTX 5090 D has a TDP of 575 W and requires a 950 W suggested PSU, using a single 16-pin connector. The RX 9070 GRE has a TDP of 220 W and a 550 W suggested PSU, using two 8-pin connectors. The AMD card draws less than half the power of the NVIDIA card, which matters for system build considerations. Both cards use PCIe 5.0 x16 and are dual-slot designs. Display outputs are similar, with the NVIDIA card offering 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the AMD card offers 1x HDMI 2.1b and 3x DisplayPort 2.1a. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Where Each One Wins

The RTX 5090 D wins in every category where data exists. In raw rasterization, the 164.1% lead in 3DMark Steel Nomad DX12 is the clearest signal. For compute workloads, the 184.2% lead in Geekbench OpenCL reinforces the same conclusion. The NVIDIA card also has a decisive advantage in memory capacity and bandwidth, which matters for high-resolution textures, large datasets, and future game installments that demand more VRAM.

The RX 9070 GRE's advantages are more practical than performance-based. Its 220 W TDP means it fits into systems with a 550 W PSU, while the RTX 5090 D demands a 950 W unit. The AMD card is also smaller in terms of die size and transistor count, which could translate to easier board design, though the database does not list its physical dimensions. The RX 9070 GRE's boost clock of 2,790 MHz is higher than the RTX 5090 D's 2,407 MHz, but that does not compensate for the massive shader and memory disadvantages.

For users who prioritize compute density per watt, the RX 9070 GRE offers 34.28 TFLOPS FP32 within a 220 W envelope, while the RTX 5090 D delivers 104.8 TFLOPS within 575 W. Per watt, the NVIDIA card still leads: 0.182 TFLOPS/W versus 0.156 TFLOPS/W for AMD. For users who prioritize absolute performance regardless of power, the RTX 5090 D is the clear choice. For users building a system with a modest PSU or who value lower power draw, the RX 9070 GRE is the more restrained option, though it sacrifices a large amount of performance.

The Verdict

The data is unambiguous. The NVIDIA GeForce RTX 5090 D outperforms the AMD Radeon RX 9070 GRE by 164.1% in 3DMark Steel Nomad DX12 and by 184.2% in Geekbench OpenCL. It has 7x the shading units, 3.5x the TMUs, 3.5x the RT cores, and more than 4x the memory bandwidth. Its 32 GB memory capacity is nearly three times the RX 9070 GRE's 12 GB.

The RX 9070 GRE is not a weak card. It sits at the 87th percentile among all GPUs, and its nearest rivals include the AMD Radeon RX 6950 XT, a previous-generation flagship. But the RTX 5090 D sits at the 92nd percentile, and its nearest rivals are different-class products entirely, including workstation Tesla P100 cards. The RTX 5090 D's average benchmark score of 77,712 is 35.5% higher than the RX 9070 GRE's 57,367.

Pick the RTX 5090 D if you demand the highest recorded performance in this comparison, need large memory capacity, or want the strongest compute results. Pick the RX 9070 GRE if your system cannot support a 575 W card with a 950 W PSU, or if you prioritize lower power consumption over raw speed. The performance gap is so large that no use case in the recorded data favors the AMD card on raw results.

FAQ

Q: How much faster is the RTX 5090 D than the RX 9070 GRE in 3DMark Steel Nomad DX12?

A: The RTX 5090 D scores 14,326 versus 5,424 for the RX 9070 GRE, a 164.1% advantage.

Q: What is the memory configuration difference?

A: The RTX 5090 D has 32 GB of GDDR7 on a 512-bit bus with 1.79 TB/s bandwidth. The RX 9070 GRE has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth.

Q: Which card has a higher boost clock?

A: The RX 9070 GRE boosts to 2,790 MHz, while the RTX 5090 D boosts to 2,407 MHz. Despite this, the RTX 5090 D is far faster due to its larger hardware resource pool.

Q: What are the power requirements?

A: The RTX 5090 D has a TDP of 575 W and a suggested PSU of 950 W. The RX 9070 GRE has a TDP of 220 W and a suggested PSU of 550 W.

Q: Does the RX 9070 GRE have tensor cores?

A: No. The RTX 5090 D includes 680 tensor cores, while the RX 9070 GRE lists none.

Q: How do their percentile rankings compare?

A: The RTX 5090 D is at the 92nd percentile among all GPUs, while the RX 9070 GRE is at the 87th percentile.

Specification Differences

| Field | NVIDIA GeForce RTX 5090 D | AMD Radeon RX 9070 GRE |

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

| Process Node | 5 nm | 4 nm |

| Transistors | 92,200 million | 53,900 million |

| Die Size | 750 mm² | 357 mm² |

| Transistor Density | 122.9M / mm² | 151.0M / mm² |

| Base Clock | 2017 MHz | 1420 MHz |

| Boost Clock | 2407 MHz | 2790 MHz |

| Game Clock | Not listed | 2220 MHz |

| Memory Clock | 1750 MHz (28 Gbps effective) | 2250 MHz (18 Gbps effective) |

| Memory Size | 32 GB | 12 GB |

| Memory Type | GDDR7 | GDDR6 |

| Memory Bus Width | 512 bit | 192 bit |

| Memory Bandwidth | 1.79 TB/s | 432.0 GB/s |

| Shading Units | 21,760 | 3,072 |

| TMUs | 680 | 192 |

| ROPs | 176 | 96 |

| RT Cores | 170 | 48 |

| Tensor Cores | 680 | None |

| Pixel Rate | 423.6 GPixel/s | 267.8 GPixel/s |

| Texture Rate | 1,636.8 GTexel/s | 535.7 GTexel/s |

| FP32 | 104.8 TFLOPS | 34.28 TFLOPS |

| FP16 | 104.8 TFLOPS (1:1) | 34.28 TFLOPS (1:1) |

| TDP | 575 W | 220 W |

| Power Connectors | 1x 16-pin | 2x 8-pin |

| Suggested PSU | 950 W | 550 W |

| Display Outputs | 1x HDMI 2.1b, 3x DisplayPort 2.1b | 1x HDMI 2.1b, 3x DisplayPort 2.1a |

| Release Date | 2025-01-29 | 2025-05-07 |

| Launch MSRP | 2,299 USD | 549 USD |

| Predecessor | GeForce 40 | Navi III |

| Successor | GeForce 60 | None listed |