AMD Radeon RX 6600 LE vs NVIDIA GeForce RTX 5080 SUPER Comparison

Head-to-Head Benchmarks

The benchmark database contains only one recorded test for the NVIDIA GeForce RTX 5080 SUPER, a 3DMark Steel Nomad DX12 run scoring 3075. The AMD Radeon RX 6600 LE has two recorded tests: Geekbench OpenCL at 69229 and Geekbench Vulkan at 72428. Direct score-to-score comparison is impossible because the two cards were evaluated under different benchmark suites. However, the percentile data and rival placements reveal the relative standing of each card within the broader GPU landscape.

The AMD Radeon RX 6600 LE sits at the 91st percentile among all GPUs in the database. Its average benchmark score is 70829. Its nearest rivals include the NVIDIA RTX A3000 Mobile with an average score of 70140, which is 1% behind the RX 6600 LE. The NVIDIA Quadro P6000 scores 69986, 1.2% lower. The AMD Radeon Pro WX 8200 trails by 1.4% with a score of 69870. The only rival that beats the RX 6600 LE in this cluster is the AMD Radeon RX 6650M, which scores 71768, a 1.3% advantage over the RX 6600 LE. These deltas are tight, all within a 2.7 percentage point band, indicating the RX 6600 LE performs at a level consistent with mid-range mobile and workstation GPUs from the previous generation.

The NVIDIA GeForce RTX 5080 SUPER, by contrast, sits at the 19th percentile among all GPUs, with an average benchmark score of 3075. Its nearest rivals are a different class entirely. The NVIDIA Quadro P1000 scores 3163, which is 2.8% higher than the RTX 5080 SUPER. The Intel Arc Pro B60 scores 3182, 3.4% higher. Behind the RTX 5080 SUPER are the NVIDIA GeForce 820A at 2983 (3.1% lower) and the NVIDIA GeForce GTX 860M at 2967 (3.6% lower). The percentile gap between the two cards is stark: 91st versus 19th. This is not a close contest in terms of database standing. The RX 6600 LE outperforms 72 percentage points more of the GPU population than the RTX 5080 SUPER does.

The raw compute specifications confirm the RX 6600 LE's stronger measured position. The RX 6600 LE delivers 8.942 TFLOPS FP32 performance, while the RTX 5080 SUPER is rated at 56.28 TFLOPS FP32. Yet the database benchmark for the RTX 5080 SUPER records only a 3075 score in 3DMark Steel Nomad DX12, a workload that likely does not reflect the card's full capability. The recorded data shows the RX 6600 LE as the better performer in its tested workloads, but the two test suites measure different things: Geekbench OpenCL and Vulkan for the RX 6600 LE versus 3DMark Steel Nomad DX12 for the RTX 5080 SUPER. The data does not support a direct head-to-head winner.

The wins counter in the database shows zero wins for either card, reflecting the absence of shared benchmark tests. The RX 6600 LE has a 91st percentile ranking, meaning it scores higher than 91% of all GPUs in the database. The RTX 5080 SUPER's 19th percentile means 81% of GPUs score higher. This is the clearest comparative signal available. The RX 6600 LE's average score of 70829 dwarfs the RTX 5080 SUPER's 3075, but again, different benchmarks prevent a fair numerical comparison.

The Verdict

The database indicates that the AMD Radeon RX 6600 LE is ranked far higher in overall GPU performance, sitting at the 91st percentile versus the NVIDIA GeForce RTX 5080 SUPER's 19th percentile. The RX 6600 LE's average benchmark score of 70829 places it among capable mid-range performers, with all four of its nearest rivals within a 1.4% delta. The RTX 5080 SUPER's single recorded score of 3075 places it near entry-level GPUs like the Quadro P1000 and GeForce 820A, which is anomalous given its specification sheet.

The RTX 5080 SUPER lists 10752 shading units, 336 texture mapping units, 112 render output units, 84 ray tracing cores, and 336 tensor cores. It has 24 GB of GDDR7 memory on a 256-bit bus with 1.02 TB/s bandwidth. The RX 6600 LE has 1792 shading units, 112 TMUs, 64 ROPs, 28 ray tracing cores, and no tensor cores. It has 8 GB of GDDR6 memory on a 128-bit bus with 224.0 GB/s bandwidth. The RTX 5080 SUPER's FP32 throughput of 56.28 TFLOPS is 6.3 times the RX 6600 LE's 8.942 TFLOPS. The pixel rate is 293.1 GPixel/s versus 159.7 GPixel/s. The texture rate is 879.3 GTexel/s versus 279.4 GTexel/s.

Yet the recorded benchmark does not reflect this theoretical advantage. The RTX 5080 SUPER's 3DMark Steel Nomad DX12 score of 3075 is lower than the Quadro P1000's 3163 and the Intel Arc Pro B60's 3182. This suggests either the benchmark run was not representative, the driver state was suboptimal, or the test methodology captured an incomplete picture. The database records what it records, and the data shows the RTX 5080 SUPER underperforming its specifications dramatically.

For a user selecting based strictly on database measurements, the RX 6600 LE is the safer choice for compute workloads measured by Geekbench OpenCL and Vulkan. Its scores of 69229 and 72428 are strong for its class. The RTX 5080 SUPER's single 3DMark result offers no evidence of superior performance, despite its much larger memory pool and higher clock speeds. The card's 24 GB GDDR7 memory and 1.02 TB/s bandwidth are substantial assets, but the recorded data does not demonstrate their benefit in practice.

The RX 6600 LE also has advantages in physical footprint and power requirements. It has a 132 W TDP with a 300 W suggested PSU, while the RTX 5080 SUPER has a 415 W TDP and no suggested PSU listed. The RX 6600 LE is 190 mm long, 110 mm tall, and 40 mm wide, versus the RTX 5080 SUPER's 304 mm length, 137 mm height, and 40 mm width. The RX 6600 LE uses a single 8-pin power connector; the RTX 5080 SUPER uses a 16-pin connector. These differences matter for system integration, though the database does not score them.

FAQ

Q: Which GPU has the higher percentile ranking in the database?

A: The AMD Radeon RX 6600 LE ranks at the 91st percentile among all GPUs, while the NVIDIA GeForce RTX 5080 SUPER ranks at the 19th percentile.

Q: What is the average benchmark score for each card?

A: The RX 6600 LE has an average benchmark score of 70829 across its two recorded tests. The RTX 5080 SUPER has an average benchmark score of 3075 from its single recorded test.

Q: How does the RTX 5080 SUPER compare to its nearest rivals?

A: The RTX 5080 SUPER trails the NVIDIA Quadro P1000 by 2.8% (3163 vs 3075) and the Intel Arc Pro B60 by 3.4% (3182 vs 3075). It leads the NVIDIA GeForce 820A by 3.1% (2983) and the NVIDIA GeForce GTX 860M by 3.6% (2967).

Q: What memory specifications does each card use?

A: The RX 6600 LE has 8 GB of GDDR6 memory on a 128-bit bus with 224.0 GB/s bandwidth. The RTX 5080 SUPER has 24 GB of GDDR7 memory on a 256-bit bus with 1.02 TB/s bandwidth.

Q: What are the FP32 compute figures for the two cards?

A: The RX 6600 LE delivers 8.942 TFLOPS FP32, while the RTX 5080 SUPER delivers 56.28 TFLOPS FP32. The RTX 5080 SUPER also has 1:1 FP16 ratio at 56.28 TFLOPS, whereas the RX 6600 LE has 17.88 TFLOPS FP16 at a 2:1 ratio.

Q: Which card has a higher boost clock?

A: The RTX 5080 SUPER has a boost clock of 2617 MHz, compared to the RX 6600 LE's boost clock of 2495 MHz. The RTX 5080 SUPER also has a higher base clock at 2295 MHz versus 1626 MHz.

Specification Differences

The two cards differ across nearly every specification field. The RX 6600 LE uses the Navi 23 chip with RDNA 2.0 architecture, while the RTX 5080 SUPER uses the GB203 chip with Blackwell 2.0 architecture. The process node is 7 nm for the RX 6600 LE and 5 nm for the RTX 5080 SUPER, both fabricated by TSMC. Transistor counts are 11,060 million for the RX 6600 LE and 45,600 million for the RTX 5080 SUPER. Die sizes are 237 mm² versus 378 mm². Transistor density is 46.7M per mm² for the RX 6600 LE and 120.6M per mm² for the RTX 5080 SUPER.

Memory configurations differ substantially. The RX 6600 LE has 8 GB GDDR6, 128-bit bus, 224.0 GB/s bandwidth, and memory clock of 1750 MHz (14 Gbps effective). The RTX 5080 SUPER has 24 GB GDDR7, 256-bit bus, 1.02 TB/s bandwidth, and memory clock of 2000 MHz (32 Gbps effective).

Compute unit counts: the RX 6600 LE has 1792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores. The RTX 5080 SUPER has 10752 shading units, 336 TMUs, 112 ROPs, 84 RT cores, and 336 tensor cores. The RX 6600 LE has no tensor cores.

Clock speeds: the RX 6600 LE runs at 1626 MHz base, 2495 MHz boost, and 2045 MHz game clock. The RTX 5080 SUPER runs at 2295 MHz base and 2617 MHz boost, with no game clock listed.

Rates: the RX 6600 LE has a pixel rate of 159.7 GPixel/s and texture rate of 279.4 GTexel/s. The RTX 5080 SUPER has a pixel rate of 293.1 GPixel/s and texture rate of 879.3 GTexel/s. FP32 is 8.942 TFLOPS versus 56.28 TFLOPS. FP16 is 17.88 TFLOPS (2:1) versus 56.28 TFLOPS (1:1).

Power and physical: the RX 6600 LE has a 132 W TDP, 300 W suggested PSU, 1x 8-pin power connector, 190 mm length, 110 mm height, 40 mm width. The RTX 5080 SUPER has a 415 W TDP, no suggested PSU listed, 1x 16-pin power connector, 304 mm length, 137 mm height, 40 mm width. Both are dual-slot.

Bus interface: PCIe 4.0 x8 for the RX 6600 LE, PCIe 5.0 x16 for the RTX 5080 SUPER. Display outputs: 1x HDMI 2.1 and 3x DisplayPort 1.4a for the RX 6600 LE; 1x HDMI 2.1b and 3x DisplayPort 2.1b for the RTX 5080 SUPER.

Release dates: the RX 6600 LE launched on 2023-12-07, while the RTX 5080 SUPER has a release date of 2025-12-31. The RTX 5080 SUPER has a launch MSRP of 999 USD. The RX 6600 LE has no launch MSRP listed.

Architecture Differences

The RX 6600 LE is built on RDNA 2.0 architecture, part of the Navi II generation (RX 6000 series). The RTX 5080 SUPER uses Blackwell 2.0 architecture, part of the GeForce 50 generation. The process nodes differ: 7 nm for the RX 6600 LE versus 5 nm for the RTX 5080 SUPER, both from TSMC. The transistor density more than doubles, from 46.7M per mm² to 120.6M per mm², reflecting the newer process and design.

The RTX 5080 SUPER includes tensor cores (336 of them), which the RX 6600 LE lacks entirely. This indicates the RTX 5080 SUPER supports AI-accelerated workloads, while the RX 6600 LE does not. The RT core count also differs: 84 on the RTX 5080 SUPER versus 28 on the RX 6600 LE. The shading unit count is 10752 versus 1792, a 6x difference. TMUs are 336 versus 112, and ROPs are 112 versus 64.

The memory architecture is a major divergence. The RX 6600 LE uses GDDR6 with 224.0 GB/s bandwidth on a 128-bit bus. The RTX 5080 SUPER uses GDDR7 with 1.02 TB/s bandwidth on a 256-bit bus. The effective memory clock is 14 Gbps versus 32 Gbps. The RTX 5080 SUPER has three times the memory capacity at 24 GB versus 8 GB.

The FP16 compute ratio differs: the RX 6600 LE achieves 17.88 TFLOPS FP16 at a 2:1 ratio relative to FP32, meaning it uses half-rate FP16. The RTX 5080 SUPER achieves 56.28 TFLOPS FP16 at a 1:1 ratio, meaning full-rate FP16 execution matching FP32 throughput. This indicates the RTX 5080 SUPER is designed for compute workloads that benefit from FP16 precision.

The bus interface differs: PCIe 4.0 x8 for the RX 6600 LE, PCIe 5.0 x16 for the RTX 5080 SUPER. The display output standards also differ: the RX 6600 LE has HDMI 2.1 and DisplayPort 1.4a, while the RTX 5080 SUPER has HDMI 2.1b and DisplayPort 2.1b. The power delivery system differs: 1x 8-pin for the RX 6600 LE, 1x 16-pin for the RTX 5080 SUPER. The TDP is 132 W versus 415 W, a substantial difference in thermal design.

The RX 6600 LE has a predecessor listed as Navi and a successor as Navi III, while the RTX 5080 SUPER has neither predecessor nor successor listed. The production status for both is Active. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5080 SUPER is the larger card physically, at 304 mm versus 190 mm in length, and 137 mm versus 110 mm in height, with identical 40 mm width.