AMD Radeon RX 9070 GRE vs NVIDIA GeForce RTX 4080 SUPER Comparison

The AMD Radeon RX 9070 GRE and NVIDIA GeForce RTX 4080 SUPER occupy adjacent performance percentiles, with the NVIDIA card sitting at the 86th percentile and the AMD card at the 87th percentile among all GPUs. Despite this near-identical overall standing, the head-to-head benchmark data reveals a significant performance gulf between the two, with the RTX 4080 SUPER winning both recorded tests by substantial margins. The average benchmark scores tell a more nuanced story, however, with the RX 9070 GRE posting a higher aggregate score of 57,367 against the RTX 4080 SUPER’s 54,209, suggesting the AMD card’s strength lies in a broader range of workloads not captured by the direct comparisons.

Head-to-Head Benchmarks

The most notable disparity appears in the Geekbench OpenCL compute test, where the NVIDIA GeForce RTX 4080 SUPER scores 219,065 against the AMD Radeon RX 9070 GRE’s 109,309. This represents a 50.1% advantage for the NVIDIA card, a margin that indicates a fundamental difference in raw compute throughput. The RTX 4080 SUPER’s FP32 performance of 52.22 TFLOPS compared to the RX 9070 GRE’s 34.28 TFLOPS aligns with this result, showing a 52.3% theoretical compute advantage that translates nearly proportionally into the OpenCL benchmark outcome.

In the 3DMark Steel Nomad DX12 test, the NVIDIA card again takes the win, scoring 6,600 against the AMD card’s 5,424, a 17.8% difference. This narrower margin suggests that gaming workloads, particularly those utilizing DirectX 12, respond to more than just raw compute power. The RTX 4080 SUPER’s higher pixel rate of 285.6 GPixel/s versus 267.8 GPixel/s on the RX 9070 GRE contributes to this advantage, as does its 816.0 GTexel/s texture rate compared to 535.7 GTexel/s. The AMD card’s 17.8% deficit in this test is notable because its average benchmark score is actually 5.8% higher than the NVIDIA card’s, implying that the RX 9070 GRE excels in other benchmark suites not present in the direct comparison.

The pattern of NVIDIA dominance in these two tests is clear, but the aggregate data complicates the narrative. The RX 9070 GRE’s nearest rivals include the Intel Arc A580 at 57,756 (-0.7%), the AMD Radeon RX 5600 OEM at 58,085 (-1.2%), and the AMD Radeon RX 6950 XT at 58,392 (-1.8%). In contrast, the RTX 4080 SUPER’s nearest rival is the base RTX 4080 at 54,247 (-0.1%), followed by the AMD Radeon Pro W5700X at 54,828 (-1.1%). This places the RX 9070 GRE in a performance tier where it competes with older flagship cards, while the RTX 4080 SUPER sits closer to its non-SUPER sibling, suggesting the SUPER variant offers only a marginal improvement over the original.

FAQ

Q: Which card has the higher overall average benchmark score?

A: The AMD Radeon RX 9070 GRE has a higher average benchmark score of 57,367 compared to the NVIDIA GeForce RTX 4080 SUPER’s 54,209, despite the NVIDIA card winning both direct head-to-head tests.

Q: How much faster is the RTX 4080 SUPER in the 3DMark Steel Nomad DX12 test?

A: The NVIDIA card scores 6,600 versus 5,424 for the AMD card, a 17.8% advantage in this DirectX 12 gaming benchmark.

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

A: The RTX 4080 SUPER provides 736.3 GB/s of bandwidth from its 16 GB of GDDR6X memory on a 256-bit bus, while the RX 9070 GRE offers 432.0 GB/s from 12 GB of GDDR6 on a 192-bit bus.

Q: Which card has a higher pixel fill rate?

A: The NVIDIA GeForce RTX 4080 SUPER achieves 285.6 GPixel/s, which is 6.6% higher than the AMD Radeon RX 9070 GRE’s 267.8 GPixel/s.

Q: How do the transistor counts compare between the two GPUs?

A: The AMD card uses 53,900 million transistors on a 357 mm² die, while the NVIDIA card uses 45,900 million transistors on a 379 mm² die, giving the RX 9070 GRE a higher transistor density of 151.0M per mm² versus 121.1M per mm².

Q: What do the nearest rival deltas indicate about each card’s market position?

A: The RX 9070 GRE sits within 1.8% of its nearest rivals, including the RX 6950 XT, while the RTX 4080 SUPER is within 2.8% of its nearest rivals, indicating both cards are tightly clustered in their respective performance brackets.

Architecture Differences

The two cards represent fundamentally different architectural approaches. The AMD Radeon RX 9070 GRE is built on the RDNA 4.0 architecture using the Navi 48 chip, manufactured on a 4 nm process at TSMC. The NVIDIA GeForce RTX 4080 SUPER employs the Ada Lovelace architecture with the AD103 chip, fabricated on a 5 nm process, also at TSMC. The process node difference gives AMD a density advantage, with 53,900 million transistors packed into a 357 mm² die (151.0M per mm²), versus NVIDIA’s 45,900 million transistors spread across a larger 379 mm² die (121.1M per mm²).

The compute resources diverge sharply. The RX 9070 GRE contains 3,072 shading units, 192 texture mapping units, 96 ROPs, and 48 ray tracing cores. The RTX 4080 SUPER dramatically increases these counts with 10,240 shading units, 320 TMUs, 112 ROPs, and 80 RT cores, plus 320 tensor cores that the AMD card lacks entirely. This translates to 52.22 TFLOPS of FP32 performance for the NVIDIA card versus 34.28 TFLOPS for the AMD card, with both achieving a 1:1 FP16 ratio.

Memory architecture also differs substantially. The RX 9070 GRE uses 12 GB of GDDR6 memory on a 192-bit bus, delivering 432.0 GB/s bandwidth. The RTX 4080 SUPER steps up to 16 GB of GDDR6X on a 256-bit bus, achieving 736.3 GB/s. The NVIDIA card’s memory clock runs at 1438 MHz (23 Gbps effective), while the AMD card’s memory operates at 2250 MHz (18 Gbps effective). The RX 9070 GRE’s higher memory clock cannot compensate for the narrower bus and older memory type.

Clock speeds present an interesting inversion. The AMD card has a base clock of 1420 MHz but boosts to 2790 MHz, with a game clock of 2220 MHz. The NVIDIA card starts higher at 2295 MHz base but only boosts to 2550 MHz. This gives the RX 9070 GRE a 9.4% higher boost clock, yet the NVIDIA card’s massive shading unit advantage overwhelms this frequency benefit. The RX 9070 GRE also features a PCIe 5.0 x16 interface versus the RTX 4080 SUPER’s PCIe 4.0 x16, though both support DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4.

The Verdict

The data presents a clear split between raw compute performance and aggregate benchmark standing. For applications that leverage FP32 compute, ray tracing, or tensor operations, the NVIDIA GeForce RTX 4080 SUPER is the decisive choice. Its 50.1% OpenCL advantage and 17.8% 3DMark Steel Nomad lead demonstrate superior performance in both compute-heavy and gaming scenarios. The 16 GB of GDDR6X memory with 736.3 GB/s bandwidth provides 33.3% more capacity and 70.4% more bandwidth than the RX 9070 GRE, making it the better option for texture-heavy workloads at high resolutions.

The AMD Radeon RX 9070 GRE, however, posts a higher average benchmark score of 57,367, which is 5.8% above the RTX 4080 SUPER’s 54,209. This suggests that in the broader benchmark ecosystem, the AMD card performs relatively better across a wider variety of tests, likely due to its significantly higher boost clock of 2790 MHz and its more efficient 220 W TDP compared to the NVIDIA card’s 320 W. The RX 9070 GRE also benefits from a newer 4 nm process node and higher transistor density, which may contribute to efficiency gains.

Users prioritizing peak performance in DirectX 12 gaming and OpenCL compute should select the RTX 4080 SUPER based on its direct benchmark victories. Those seeking a card with a higher aggregate benchmark profile and lower power requirements may find the RX 9070 GRE more suitable. The RTX 4080 SUPER is end-of-life with a successor already released, while the RX 9070 GRE remains active in production, which may factor into availability considerations. The RTX 4080 SUPER’s triple-slot design and 310 mm length also impose larger physical footprint requirements compared to the RX 9070 GRE’s dual-slot form factor.

Specification Differences

The two cards differ across nearly every major specification category. The RX 9070 GRE uses the Navi 48 chip on RDNA 4.0 architecture with a 4 nm process, while the RTX 4080 SUPER uses the AD103 chip on Ada Lovelace with a 5 nm process. Transistor counts differ at 53,900 million versus 45,900 million, with die sizes of 357 mm² and 379 mm² respectively. The AMD card has a base clock of 1420 MHz and boost of 2790 MHz, while the NVIDIA card runs at 2295 MHz base and 2550 MHz boost.

Memory configurations diverge with 12 GB GDDR6 on a 192-bit bus for AMD versus 16 GB GDDR6X on a 256-bit bus for NVIDIA, yielding bandwidths of 432.0 GB/s and 736.3 GB/s. The shading unit count differs dramatically at 3,072 versus 10,240, as do TMUs at 192 versus 320 and ROPs at 96 versus 112. Ray tracing cores number 48 on the AMD card versus 80 on the NVIDIA card, with the latter also featuring 320 tensor cores. Pixel rates are 267.8 GPixel/s versus 285.6 GPixel/s, and texture rates are 535.7 GTexel/s versus 816.0 GTexel/s. FP32 performance stands at 34.28 TFLOPS versus 52.22 TFLOPS.

Power and physical specifications also differ: the RX 9070 GRE has a 220 W TDP with dual-slot cooling and 2x 8-pin connectors, while the RTX 4080 SUPER has a 320 W TDP with triple-slot cooling and a 1x 16-pin connector. The suggested PSU is 550 W for AMD and 700 W for NVIDIA. The RX 9070 GRE uses PCIe 5.0 x16 and offers 1x HDMI 2.1b plus 3x DisplayPort 2.1a outputs, while the RTX 4080 SUPER uses PCIe 4.0 x16 with 1x HDMI 2.1 and 3x DisplayPort 1.4a. The NVIDIA card measures 310 mm in length, 140 mm in height, and 61 mm in width. The RX 9070 GRE was released on May 7, 2025 with a launch MSRP of 549 USD, while the RTX 4080 SUPER launched January 30, 2024 at 999 USD.