AMD Radeon RX 6700S vs NVIDIA GeForce RTX 2080 SUPER Comparison

FAQ

Q: Which GPU is faster in direct comparisons, the NVIDIA GeForce RTX 2080 SUPER or the AMD Radeon RX 6700S?

A: The NVIDIA GeForce RTX 2080 SUPER wins all 10 head-to-head benchmark tests recorded in the database. Its average benchmark score is 24,170 compared to 22,154 for the AMD Radeon RX 6700S.

Q: How large is the performance gap in the most demanding modern DirectX 12 test?

A: In the 3DMark Steel Nomad DX12 test, the RTX 2080 SUPER scores 1,882 while the RX 6700S scores 1,451, a 29.7% advantage for the NVIDIA card.

Q: Does the AMD card have any architectural advantage that could matter for specific workloads?

A: Yes. The RX 6700S uses a 7 nm process node with a transistor density of 46.7M per mm², versus 25.0M per mm² for the 12 nm RTX 2080 SUPER. It also runs on PCIe 4.0 x8, while the NVIDIA card uses PCIe 3.0 x16. However, these advantages do not translate into benchmark wins.

Q: What is the power draw difference between the two cards?

A: The RTX 2080 SUPER has a TDP of 250 W and requires a 600 W suggested PSU. The RX 6700S has an 80 W TDP and no external power connectors, making it far more power-efficient.

Q: Which card has better compute performance in OpenCL?

A: The RTX 2080 SUPER scores 99,226 in Geekbench OpenCL, which is 39.8% higher than the RX 6700S's 70,965.

Q: Are both cards in the same performance percentile among all GPUs?

A: They are close. The RTX 2080 SUPER sits at the 69th percentile, while the RX 6700S sits at the 67th percentile. The average score difference is about 9.1% in favor of the NVIDIA card.

Architecture Differences

The RTX 2080 SUPER is built on NVIDIA's Turing architecture, using the TU104 chip produced at TSMC's 12 nm node. It packs 13,600 million transistors on a 545 mm² die. The RX 6700S uses AMD's RDNA 2.0 architecture with the Navi 23 chip, built at 7 nm and housing 11,060 million transistors on a much smaller 237 mm² die. The transistor density tells the story: 25.0M per mm² for Turing versus 46.7M per mm² for RDNA 2.0, showing the newer process allows far more transistors per area.

Chip configuration differs substantially. The RTX 2080 SUPER has 3,072 shading units, 192 texture mapping units, and 64 ROPs. It also includes 48 RT cores and 384 tensor cores, enabling hardware ray tracing and AI-accelerated features. The RX 6700S has 1,792 shading units, 112 TMUs, and 64 ROPs, with 28 RT cores and no tensor cores. The NVIDIA card's FP32 throughput is 11.15 TFLOPS versus 7.168 TFLOPS for the AMD card, and FP16 rates are 22.30 TFLOPS and 14.34 TFLOPS respectively, both at a 2:1 ratio.

Memory subsystems diverge widely. Both have 8 GB of GDDR6, but the RTX 2080 SUPER uses a 256-bit bus delivering 495.9 GB/s of bandwidth, while the RX 6700S uses a 128-bit bus capped at 224.0 GB/s. That is less than half the bandwidth. Pixel fill rates are similar (116.2 GPixel/s versus 128.0 GPixel/s), but texture rate favors NVIDIA heavily: 348.5 GTexel/s versus 224.0 GTexel/s.

Form factor and power delivery contrast sharply. The RTX 2080 SUPER is a dual-slot card measuring 267 mm long, requiring a 250 W TDP, a 600 W suggested PSU, and 1x 6-pin plus 1x 8-pin power connectors. The RX 6700S is an IGP (integrated GPU platform) with an 80 W TDP and no power connectors, designed for portable devices. Display outputs also differ: the NVIDIA card has 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C, while the AMD card's outputs are portable device dependent.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 2080 SUPER was released on 2019-07-22 and is now end-of-life, with a successor in the GeForce 30 series. The RX 6700S launched later on 2022-01-03, also end-of-life, with no listed successor.

The Verdict

The recorded data is unambiguous: the RTX 2080 SUPER wins every single head-to-head benchmark, 10 wins to 0. If raw performance across DirectX 9 through 12, compute, and Vulkan is the only criterion, the NVIDIA card is the clear choice. Its average score of 24,170 versus 22,154 for the RX 6700S translates to roughly a 9% overall lead, and individual tests show leads ranging from 16.4% to 60.9%.

However, the RX 6700S is not without purpose. Its 7 nm process and 80 W TDP make it a mobile-first part, designed to fit into thin-and-light gaming laptops without external power connectors. The RTX 2080 SUPER cannot do that; it is a 250 W desktop card requiring a 600 W PSU. So the verdict splits by platform: for a desktop build where power and cooling are available, the RTX 2080 SUPER is decisively faster. For a portable system where power draw and physical size are constraints, the RX 6700S is the only viable option of the two, and its 67th percentile standing is respectable for such a low-power part.

Specification Differences

• Process Node: 12 nm for RTX 2080 SUPER, 7 nm for RX 6700S
• Transistors: 13,600 million versus 11,060 million
• Die Size: 545 mm² versus 237 mm²
• Transistor Density: 25.0M / mm² versus 46.7M / mm²
• Base Clock: 1650 MHz versus 1700 MHz
• Boost Clock: 1815 MHz versus 2000 MHz
• Game Clock: null versus 1890 MHz
• Memory Clock: 1937 MHz (15.5 Gbps effective) versus 1750 MHz (14 Gbps effective)
• Memory Bus Width: 256 bit versus 128 bit
• Memory Bandwidth: 495.9 GB/s versus 224.0 GB/s
• Shading Units: 3072 versus 1792
• TMUs: 192 versus 112
• ROPs: 64 versus 64
• RT Cores: 48 versus 28
• Tensor Cores: 384 versus null
• Pixel Rate: 116.2 GPixel/s versus 128.0 GPixel/s
• Texture Rate: 348.5 GTexel/s versus 224.0 GTexel/s
• FP32: 11.15 TFLOPS versus 7.168 TFLOPS
• FP16: 22.30 TFLOPS versus 14.34 TFLOPS
• TDP: 250 W versus 80 W
• Slot Width: Dual-slot versus IGP
• Power Connectors: 1x 6-pin + 1x 8-pin versus None
• Suggested PSU: 600 W versus null
• Bus Interface: PCIe 3.0 x16 versus PCIe 4.0 x8
• Display Outputs: 1x HDMI 2.0, 3x DisplayPort 1.4a, 1x USB Type-C versus Portable Device Dependent
• Dimensions: 267 mm x 116 mm x 35 mm versus null
• Release Date: 2019-07-22 versus 2022-01-03
• Launch MSRP: 699 USD versus null

Head-to-Head Benchmarks

The RTX 2080 SUPER dominates every recorded test. In 3DMark Steel Nomad DX12, it scores 1,882 against 1,451, a 29.7% margin. That is the flagship modern test, and the NVIDIA card leads by nearly a third.

Geekbench results amplify the gap. In OpenCL, the RTX 2080 SUPER scores 99,226 versus 70,965, a 39.8% advantage. In Vulkan, the lead grows to 46.1% (111,284 versus 76,150). Compute workloads clearly favor the NVIDIA architecture, with the tensor cores likely contributing to the wide spreads.

PassMark results show consistent wins across every DirectX version. DirectX 9: 227 versus 195, a 16.4% lead. DirectX 10: 140 versus 87, the largest single delta at 60.9%. DirectX 11: 165 versus 134, a 23.1% lead. DirectX 12: 75 versus 58, a 29.3% advantage. The RTX 2080 SUPER is faster in every API generation, from legacy DX9 to modern DX12.

The 2D and 3D PassMark tests also side with NVIDIA. PassMark G2D scores 920 versus 739, a 24.5% lead. PassMark G3D scores 19,490 versus 15,066, a 29.4% margin. GPU compute in PassMark gives the RTX 2080 SUPER 8,290 versus 5,990, a 38.4% advantage.

The smallest win is in DirectX 9 at 16.4%, and the largest is DirectX 10 at 60.9%. No test comes close to a tie. The RX 6700S never leads in any measured category, despite its higher boost clock (2000 MHz versus 1815 MHz) and higher pixel rate (128.0 GPixel/s versus 116.2 GPixel/s). The NVIDIA card's massive memory bandwidth and higher shader count simply overpower those advantages.

Where Each One Wins

The RTX 2080 SUPER wins everywhere that performance matters and power is available. It is the better choice for desktop gaming at high resolutions or high refresh rates, especially in DirectX 12 titles where its 29.7% lead in Steel Nomad shows modern engines favor its architecture. It also excels in compute-heavy tasks: OpenCL, Vulkan, and PassMark GPU compute all show leads above 38%, making it the stronger pick for rendering, video encoding, or any workload that offloads to the GPU. Its 384 tensor cores give it a unique advantage for AI-accelerated features that the RX 6700S cannot match, since the AMD card has no tensor cores at all.

The RX 6700S wins in portability and efficiency, not in speed. At 80 W TDP with no power connectors, it fits into platforms where the 250 W RTX 2080 SUPER simply cannot exist. It is the only choice for a thin-and-light laptop with gaming ambitions. Its 7 nm process and PCIe 4.0 x8 interface indicate a more modern platform, and its 67th percentile ranking among all GPUs shows it is still a capable mobile part, just one that trails the desktop-class Turing card by roughly 9% on average. For a user who prioritizes battery life, low heat, and a compact chassis over raw frame rates, the RX 6700S is the functional pick. For anyone with a desktop slot, the RTX 2080 SUPER is the definitive performance winner in every recorded benchmark.