AMD Radeon RX 9070 vs NVIDIA GeForce RTX 5080 SUPER Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon RX 9070 records an average benchmark score of 23,877, while the NVIDIA GeForce RTX 5080 SUPER records 3,075. The RX 9070 leads by a substantial margin.

Q: How do the two cards compare in the 3DMark Steel Nomad DX12 test?

A: In 3DMark Steel Nomad DX12, the RX 9070 scores 6,290 against the RTX 5080 SUPER's 3,075. That is a 104.6% advantage for the AMD card.

Q: What is the memory configuration difference?

A: The RX 9070 uses 16 GB of GDDR6 memory on a 256-bit bus with 644.6 GB/s bandwidth. The RTX 5080 SUPER uses 24 GB of GDDR7 memory on a 256-bit bus with 1.02 TB/s bandwidth.

Q: Which GPU has more shading units?

A: The RTX 5080 SUPER has 10,752 shading units, compared to 3,584 on the RX 9070. The NVIDIA card also has 336 texture mapping units versus 224, and 84 RT cores versus 56.

Q: What is the launch MSRP for each card?

A: The RX 9070 has a launch MSRP of 549 USD. The RTX 5080 SUPER has a launch MSRP of 999 USD.

Q: How do the percentile ranks differ?

A: The RX 9070 sits at the 69th percentile among all GPUs in the database. The RTX 5080 SUPER sits at the 19th percentile.

Architecture Differences

The RX 9070 is built on AMD's RDNA 4.0 architecture, using the Navi 48 chip fabricated on TSMC's 4 nm process. The die measures 357 mm² and contains 53,900 million transistors, yielding a transistor density of 151.0M per mm². The RTX 5080 SUPER uses NVIDIA's Blackwell 2.0 architecture, built around the GB203 chip on TSMC's 5 nm process. Its die is slightly larger at 378 mm² but packs fewer transistors at 45,600 million, resulting in a lower density of 120.6M per mm².

The compute layouts diverge sharply. The RX 9070 fields 3,584 shading units, 224 TMUs, and 128 ROPs, along with 56 RT cores and no dedicated tensor cores. The RTX 5080 SUPER counters with 10,752 shading units, 336 TMUs, and 112 ROPs, plus 84 RT cores and 336 tensor cores. The NVIDIA card's tensor core count points toward a different compute philosophy, though the recorded benchmarks do not isolate AI workloads.

Clock behavior also differs. The RX 9070 has a base clock of 1330 MHz, a boost clock of 2520 MHz, and a game clock of 2070 MHz. The RTX 5080 SUPER starts at a much higher base of 2295 MHz and boosts to 2617 MHz, with no game clock listed. Memory clocks show the RTX 5080 SUPER's GDDR7 running at 2000 MHz with 32 Gbps effective transfer, while the RX 9070's GDDR6 runs at 2518 MHz with 20.1 Gbps effective.

Both cards support PCIe 5.0 x16 and share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs differ slightly: the RX 9070 offers 1x HDMI 2.1b and 3x DisplayPort 2.1a, while the RTX 5080 SUPER offers 1x HDMI 2.1b and 3x DisplayPort 2.1b. Power delivery differs as well, with the RX 9070 using 2x 8-pin connectors and the RTX 5080 SUPER using a single 16-pin connector.

Where Each One Wins

The RX 9070 wins the only head-to-head benchmark recorded in the database, the 3DMark Steel Nomad DX12 test, by a 104.6% margin. It also holds a dominant edge in the broader benchmark suite, with an average score of 23,877 versus 3,075. The RX 9070's percentile rank of 69 places it well above the RTX 5080 SUPER's 19th percentile.

The RTX 5080 SUPER does not win any recorded benchmark against the RX 9070. However, its architectural specifications suggest areas where it could theoretically excel: 24 GB of GDDR7 memory with 1.02 TB/s bandwidth, a 32 Gbps effective memory transfer rate, and a higher boost clock of 2617 MHz. The card also has triple the shading units and six times the tensor cores, which may matter for compute-heavy tasks not covered by the available tests.

The RX 9070's wins come from raw rasterization performance in the tested workload. Its 36.13 TFLOPS FP32 throughput and 564.5 GTexel/s texture rate outpace the RTX 5080 SUPER's 56.28 TFLOPS and 879.3 GTexel/s on paper, yet the AMD card delivers the higher actual score. The data shows the RX 9070 as the decisive winner in the recorded 3DMark test.

Specification Differences

| Specification | AMD Radeon RX 9070 | NVIDIA GeForce RTX 5080 SUPER |

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

| Architecture | RDNA 4.0 | Blackwell 2.0 |

| Process Node | 4 nm | 5 nm |

| Transistors | 53,900 million | 45,600 million |

| Die Size | 357 mm² | 378 mm² |

| Transistor Density | 151.0M / mm² | 120.6M / mm² |

| Base Clock | 1330 MHz | 2295 MHz |

| Boost Clock | 2520 MHz | 2617 MHz |

| Game Clock | 2070 MHz | Not listed |

| Memory Size | 16 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 256 bit | 256 bit |

| Memory Bandwidth | 644.6 GB/s | 1.02 TB/s |

| Shading Units | 3584 | 10752 |

| TMUs | 224 | 336 |

| ROPs | 128 | 112 |

| RT Cores | 56 | 84 |

| Tensor Cores | Not listed | 336 |

| Pixel Rate | 322.6 GPixel/s | 293.1 GPixel/s |

| Texture Rate | 564.5 GTexel/s | 879.3 GTexel/s |

| FP32 | 36.13 TFLOPS | 56.28 TFLOPS |

| FP16 | 36.13 TFLOPS (1:1) | 56.28 TFLOPS (1:1) |

| TDP | 220 W | 415 W |

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

| Suggested PSU | 550 W | Not listed |

| Dimensions | Not listed | 304 mm x 137 mm x 40 mm |

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

Head-to-Head Benchmarks

The only direct comparison in the database is 3DMark Steel Nomad DX12. The RX 9070 scores 6,290, while the RTX 5080 SUPER scores 3,075. That difference translates to a 104.6% lead for the AMD card, meaning the RX 9070 more than doubles the NVIDIA card's result in this particular test.

Looking at the broader benchmark picture, the RX 9070 records an average score of 23,877 across multiple tests, including Geekbench OpenCL at 131,539, Geekbench Vulkan at 58,705, and Passmark G3D at 25,381. The RTX 5080 SUPER has only one recorded benchmark result, the 3DMark Steel Nomad score of 3,075, which also serves as its average.

The RX 9070's nearest rivals in the database are the NVIDIA GeForce GTX TITAN Z (23,736, 0.6% behind), AMD Radeon RX 6800S (24,063, 0.8% ahead), NVIDIA GeForce RTX 3080 Mobile (23,628, 1.1% behind), and NVIDIA GeForce RTX 2080 SUPER (24,170, 1.2% ahead). The RX 9070 sits within a tight cluster around the 24,000 mark.

The RTX 5080 SUPER's nearest rivals tell a different story. The NVIDIA Quadro P1000 scores 3,163, which is 2.8% higher. The NVIDIA GeForce 820A scores 2,983, which is 3.1% lower. The Intel Arc Pro B60 scores 3,182, which is 3.4% higher, and the NVIDIA GeForce GTX 860M scores 2,967, which is 3.6% lower. The RTX 5080 SUPER is grouped with much older and lower-tier hardware in the database's rankings.

The discrepancy between the RX 9070's 69th percentile and the RTX 5080 SUPER's 19th percentile reinforces the benchmark gap. The recorded data places these cards in entirely different performance tiers, despite the RTX 5080 SUPER's higher theoretical specifications.

The Verdict

The recorded data clearly favors the AMD Radeon RX 9070. It wins the sole head-to-head benchmark by 104.6%, holds a 69th percentile rank versus the RTX 5080 SUPER's 19th, and averages 23,877 across all tests compared to 3,075. For anyone selecting a GPU based on the available benchmark results, the RX 9070 is the proven performer.

The RTX 5080 SUPER's specifications do not translate into benchmark success in the database. Its 10,752 shading units, 336 tensor cores, 24 GB of GDDR7 memory, and 1.02 TB/s bandwidth are all impressive on paper, but no recorded test shows that hardware delivering a win. The card's nearest rivals include the Quadro P1000 and GTX 860M, which are not contemporary high-end parts.

The RX 9070's wins are not narrow. Doubling the RTX 5080 SUPER's 3DMark Steel Nomad score indicates a fundamental performance gap in the tested workload. The AMD card also shows consistent results across Geekbench and Passmark tests, giving it a broader validation base.

The RTX 5080 SUPER may appeal to users who prioritize memory capacity or tensor core count, but the database contains no benchmark to support such a choice. The 24 GB frame buffer and higher FP32 throughput are documented, yet the actual scores do not follow.

The verdict from the data is straightforward: the RX 9070 delivers the higher measured performance, the better percentile ranking, and the stronger head-to-head result. The RTX 5080 SUPER remains an option only for those who value its specification sheet over recorded outcomes.