AMD Radeon RX 9070 vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The recorded data presents an unusual comparison, as the NVIDIA GeForce RTX 5090 SE has no benchmark entries in the database. Its average benchmark score is recorded as 0, and its percentile versus all GPUs sits at 50. The AMD Radeon RX 9070, by contrast, has a full suite of recorded measurements. Its average benchmark score is 23,877, placing it in the 69th percentile of all GPUs. Without a single recorded score for the RTX 5090 SE, a direct head-to-head numerical comparison is impossible; the database offers no deltas, no win counts, and no rival scores for the NVIDIA card.

The AMD Radeon RX 9070's available scores span multiple test suites. In 3DMark Steel Nomad (DX12), it records 6,290 points. Geekbench results show 131,539 points in OpenCL and 58,705 points in Vulkan. Passmark results include a G3D score of 25,381, a GPU Compute score of 14,737, and legacy API scores of 343 in DirectX 9, 281 in DirectX 11, 141 in DirectX 10, and 74 in DirectX 12. The G2D score is 1,280.

The nearest rivals for the RX 9070 provide context. The AMD Radeon RX 6800S scores 24,063, which is 0.8% higher. The NVIDIA GeForce RTX 2080 SUPER scores 24,170, 1.2% higher. The NVIDIA GeForce GTX TITAN Z scores 23,736, 0.6% lower, and the NVIDIA GeForce RTX 3080 Mobile scores 23,628, 1.1% lower. These margins are tight, placing the RX 9070 in a competitive band where no single rival dominates by more than 1.2%. The data indicates the RX 9070 sits near parity with these older or mobile parts, despite its newer architecture.

For the RTX 5090 SE, the absence of measurements means any performance claim would be unsupported. The database lists no rival comparisons, no percentile strength beyond the neutral 50th percentile baseline, and no test scores. The only numerical performance indicators are theoretical specifications, which appear in the architecture and specification sections below.

Architecture Differences

The two cards diverge sharply at the silicon level. The AMD Radeon RX 9070 uses the Navi 48 chip built on RDNA 4.0 architecture, fabricated on a 4 nm process at TSMC. The die measures 357 mm² and contains 53,900 million transistors, yielding a transistor density of 151.0 million per mm². The NVIDIA GeForce RTX 5090 SE uses the GB202 chip on Blackwell 2.0 architecture, also fabricated at TSMC but on a 5 nm process. Its die is 750 mm² with 92,200 million transistors, a density of 122.9 million per mm². The NVIDIA die is larger and packs more transistors, but the AMD process node is smaller and achieves higher density.

Clock behavior differs. The RX 9070 lists a base clock of 1,330 MHz, a boost clock of 2,520 MHz, and a game clock of 2,070 MHz. The RTX 5090 SE lists a base clock of 1,740 MHz and a boost clock of 2,377 MHz, with no game clock recorded. The AMD card boosts higher, while the NVIDIA card starts from a higher base.

Memory configurations are clearly distinct. The RX 9070 uses 16 GB of GDDR6 on a 256-bit bus, with 2,518 MHz memory clock (20.1 Gbps effective) and 644.6 GB/s bandwidth. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus, with 1,750 MHz memory clock (28 Gbps effective) and 1.34 TB/s bandwidth. The NVIDIA card has 50% more capacity and roughly double the bandwidth.

Compute resources favor the NVIDIA card heavily. The RX 9070 has 3,584 shading units, 224 texture mapping units, 128 ROPs, and 56 ray tracing cores. It records no tensor core count. The RTX 5090 SE has 14,080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, and 440 tensor cores. The NVIDIA card has 4x the shading units, nearly 2x the TMUs, and roughly 2x the RT cores. Pixel rate is 322.6 GPixel/s for AMD versus 380.3 GPixel/s for NVIDIA. Texture rate is 564.5 GTexel/s for AMD versus 1,045.9 GTexel/s for NVIDIA. FP32 compute is 36.13 TFLOPS for AMD versus 66.94 TFLOPS for NVIDIA, and FP16 is identical to FP32 on both (1:1 ratio).

Power and physical characteristics differ as well. The RX 9070 has a TDP of 220 W, uses dual-slot cooling, draws through 2x 8-pin connectors, and recommends a 550 W PSU. The RTX 5090 SE has a TDP of 500 W, also dual-slot, uses a single 16-pin connector, and recommends a 900 W PSU. Both use PCIe 5.0 x16. Display outputs are 1x HDMI 2.1b and 3x DisplayPort for both, but the AMD card uses DisplayPort 2.1a while the NVIDIA card uses DisplayPort 2.1b. API support is identical: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card has recorded dimensions of 267 mm length, 111 mm height, and 40 mm width; the AMD card has no dimensions recorded.

FAQ

Q: Which card has more shading units?

A: The NVIDIA GeForce RTX 5090 SE has 14,080 shading units, while the AMD Radeon RX 9070 has 3,584.

Q: What is the memory bandwidth difference?

A: The RTX 5090 SE has 1.34 TB/s bandwidth from 24 GB of GDDR7 on a 384-bit bus. The RX 9070 has 644.6 GB/s from 16 GB of GDDR6 on a 256-bit bus.

Q: Which card has a higher boost clock?

A: The RX 9070 boosts to 2,520 MHz. The RTX 5090 SE boosts to 2,377 MHz.

Q: How do the process nodes compare?

A: The RX 9070 uses a 4 nm TSMC process. The RTX 5090 SE uses a 5 nm TSMC process.

Q: What are the power requirements?

A: The RX 9070 has a 220 W TDP and recommends a 550 W PSU. The RTX 5090 SE has a 500 W TDP and recommends a 900 W PSU.

Q: Does the RTX 5090 SE have any recorded benchmark scores?

A: No. The database lists no benchmark entries for the RTX 5090 SE, and its average benchmark score is 0.

The Verdict

The data supports only one clear choice for buyers who rely on recorded measurements: the AMD Radeon RX 9070. It has a complete set of benchmark results, a 69th percentile standing among all GPUs, and an average score of 23,877. The RTX 5090 SE has no recorded measurements whatsoever, making its real-world performance unverified in this database. Its percentile is listed at the neutral 50, and its average score is 0.

For users who prioritize theoretical specifications, the RTX 5090 SE holds the advantage on paper. It has more shading units, more memory, higher bandwidth, higher FP32 compute, and a larger die. It also consumes more power, at 500 W versus 220 W, and requires a 900 W PSU versus 550 W. The RX 9070 counters with a smaller 4 nm process, higher transistor density, a higher boost clock, and a lower power draw.

The recorded data, however, only validates the RX 9070. The RTX 5090 SE's launch MSRP is 1,499 USD, while the RX 9070's launch MSRP is 549 USD. Without benchmark scores, the NVIDIA card's performance remains unsubstantiated in the database. The RX 9070 is the only card in this comparison with empirical results, and those results place it near established parts like the RTX 2080 SUPER and RX 6800S within a 1.2% margin. The verdict from the data is straightforward: the RX 9070 is the verified performer, while the RTX 5090 SE is an unmeasured entry with strong specifications but no recorded output.

Specification Differences

| Specification | AMD Radeon RX 9070 | NVIDIA GeForce RTX 5090 SE |

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

| Chip | Navi 48 | GB202 |

| Architecture | RDNA 4.0 | Blackwell 2.0 |

| Process Node | 4 nm | 5 nm |

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

| Die Size | 357 mm² | 750 mm² |

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

| Base Clock | 1330 MHz | 1740 MHz |

| Boost Clock | 2520 MHz | 2377 MHz |

| Memory Size | 16 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 256 bit | 384 bit |

| Memory Clock | 2518 MHz (20.1 Gbps effective) | 1750 MHz (28 Gbps effective) |

| Memory Bandwidth | 644.6 GB/s | 1.34 TB/s |

| Shading Units | 3584 | 14080 |

| TMUs | 224 | 440 |

| ROPs | 128 | 160 |

| RT Cores | 56 | 110 |

| Tensor Cores | null | 440 |

| Pixel Rate | 322.6 GPixel/s | 380.3 GPixel/s |

| Texture Rate | 564.5 GTexel/s | 1,045.9 GTexel/s |

| FP32 | 36.13 TFLOPS | 66.94 TFLOPS |

| FP16 | 36.13 TFLOPS (1:1) | 66.94 TFLOPS (1:1) |

| TDP | 220 W | 500 W |

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

| Suggested PSU | 550 W | 900 W |

| DisplayPort Version | 2.1a | 2.1b |

| Dimensions | null | 267 mm x 111 mm x 40 mm |

| Launch MSRP | 549 USD | 1,499 USD |

| Release Date | 2025-03-05 | 2025-12-31 |

| Predecessor | Navi III | GeForce 40 |

| Successor | null | GeForce 60 |